no code implementations • Findings (ACL) 2022 • Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Yanyang Li, Bowen Li, Jian Sun, Yongbin Li
The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing.
no code implementations • 8 Jul 2025 • Yuhang Zhang, Jiaqi Liu, Chengkai Xu, Peng Hang, Jian Sun
A principal barrier to large-scale deployment of urban autonomous driving systems lies in the prevalence of complex scenarios and edge cases.
1 code implementation • 16 Jun 2025 • MiniMax, :, Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, Chengjun Xiao, Chengyu Du, Chi Zhang, Chu Qiao, Chunhao Zhang, Chunhui Du, Congchao Guo, Da Chen, Deming Ding, Dianjun Sun, Dong Li, Enwei Jiao, Haigang Zhou, Haimo Zhang, Han Ding, Haohai Sun, HaoYu Feng, Huaiguang Cai, Haichao Zhu, Jian Sun, Jiaqi Zhuang, Jiaren Cai, Jiayuan Song, Jin Zhu, Jingyang Li, Jinhao Tian, Jinli Liu, Junhao Xu, Junjie Yan, Junteng Liu, Junxian He, Kaiyi Feng, Ke Yang, Kecheng Xiao, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Li, Lin Zheng, Linge Du, Lingyu Yang, Lunbin Zeng, Minghui Yu, Mingliang Tao, Mingyuan Chi, Mozhi Zhang, Mujie Lin, Nan Hu, Nongyu Di, Peng Gao, Pengfei Li, Pengyu Zhao, Qibing Ren, Qidi Xu, Qile Li, Qin Wang, Rong Tian, Ruitao Leng, Shaoxiang Chen, Shaoyu Chen, Shengmin Shi, Shitong Weng, Shuchang Guan, Shuqi Yu, Sichen Li, Songquan Zhu, Tengfei Li, Tianchi Cai, Tianrun Liang, Weiyu Cheng, Weize Kong, Wenkai Li, Xiancai Chen, Xiangjun Song, Xiao Luo, Xiao Su, Xiaobo Li, Xiaodong Han, Xinzhu Hou, Xuan Lu, Xun Zou, Xuyang Shen, Yan Gong, Yan Ma, Yang Wang, Yiqi Shi, Yiran Zhong, Yonghong Duan, Yongxiang Fu, Yongyi Hu, Yu Gao, Yuanxiang Fan, Yufeng Yang, Yuhao Li, Yulin Hu, Yunan Huang, Yunji Li, Yunzhi Xu, Yuxin Mao, Yuxuan Shi, Yuze Wenren, Zehan Li, Zelin Li, Zhanxu Tian, Zhengmao Zhu, Zhenhua Fan, Zhenzhen Wu, Zhichao Xu, Zhihang Yu, Zhiheng Lyu, Zhuo Jiang, Zibo Gao, Zijia Wu, Zijian Song, Zijun Sun
We release two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively, where the 40K model represents an intermediate phase of the 80K training.
no code implementations • 15 Jun 2025 • Chen-Bin Feng, Kangdao Liu, Jian Sun, Jiping Jin, Yiguo Jiang, Chi-Man Vong
Beyond malformed hand refinement, we propose a novel hand pose transformation method.
1 code implementation • 27 May 2025 • Xiaole Tang, Xiaoyi He, Xiang Gu, Jian Sun
Despite remarkable advances made in all-in-one image restoration (AIR) for handling different types of degradations simultaneously, existing methods remain vulnerable to out-of-distribution degradations and images, limiting their real-world applicability.
no code implementations • 23 May 2025 • Taoran Zheng, Xing Li, Yan Yang, Xiang Gu, Zongben Xu, Jian Sun
To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path.
no code implementations • 19 May 2025 • Dongyi Wang, Yuanwei Jiang, Zhenyi Zhang, Xiang Gu, Peijie Zhou, Jian Sun
The destructive measurement technique and cell proliferation/death result in unpaired and unbalanced data between snapshots, making the learning of the underlying dynamics challenging.
no code implementations • 14 May 2025 • Wenjie Liu, Yifei Li, Jian Sun, Gang Wang, Keyou You, Lihua Xie, Jie Chen
Extensions to both linear and nonlinear MASs are discussed.
no code implementations • 8 May 2025 • Zhaohan Feng, Ruiqi Xue, Lei Yuan, Yang Yu, Ning Ding, Meiqin Liu, Bingzhao Gao, Jian Sun, Xinhu Zheng, Gang Wang
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments.
no code implementations • 2 May 2025 • Yuewen Mei, Tong Nie, Jian Sun, Ye Tian
Simulation-based testing is crucial for validating autonomous vehicles (AVs), yet existing scenario generation methods either overfit to common driving patterns or operate in an offline, non-interactive manner that fails to expose rare, safety-critical corner cases.
no code implementations • 30 Mar 2025 • Zhangcun Yan, Jianqing Li, Peng Hang, Jian Sun
With the acceleration of urbanization and the growth of transportation demands, the safety of vulnerable road users (VRUs, such as pedestrians and cyclists) in mixed traffic flows has become increasingly prominent, necessitating high-precision and diverse trajectory data to support the development and optimization of autonomous driving systems.
no code implementations • 30 Mar 2025 • Wei Zeng, Xuebin Chang, Jianghao Su, Xiang Gu, Jian Sun, Zongben Xu
In this work, we innovate a cross-domain alignment and generation model that introduces a canonical latent space representation based on geometric mapping to align the cross-domain latent spaces in a rigorous and precise manner, thus avoiding mode collapse and mixture in the encoder-decoder generation architectures.
no code implementations • 28 Mar 2025 • Shuze Wang, Yunpeng Mei, Hongjie Cao, Yetian Yuan, Gang Wang, Jian Sun, Jie Chen
Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations.
1 code implementation • 27 Mar 2025 • Tong Nie, Jian Sun, Wei Ma
For each role, our review spans diverse applications, from traffic prediction and autonomous driving to safety analytics and urban mobility optimization, highlighting how emergent capabilities of LLMs such as in-context learning and step-by-step reasoning can enhance the operation and management of transportation systems.
no code implementations • 3 Feb 2025 • Chengkai Xu, Jiaqi Liu, Shiyu Fang, Yiming Cui, Dong Chen, Peng Hang, Jian Sun
To address these limitations, we propose TeLL-Drive, a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.
no code implementations • 27 Jan 2025 • Yuewen Mei, Tong Nie, Jian Sun, Ye Tian
However, the complexity of real-world scenarios, with numerous participants and diverse behaviors, makes identification challenging.
no code implementations • 20 Jan 2025 • Tong Nie, Wei Ma, Jian Sun, Yu Yang, Jiannong Cao
We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning, incorporating hierarchical modulation and normalization techniques to accommodate multiscale representations and reduce variance in response to heterogeneity.
no code implementations • 7 Jan 2025 • Hao Zhang, Qi Wang, Jian Sun, Zhijie Wen, Jun Shi, Shihui Ying
Additionally, we design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction, incorporating imaging physics and image priors to guide the reconstruction process.
no code implementations • 3 Jan 2025 • Elvis Kimara, Kunle S. Oguntoye, Jian Sun
This paper introduces PersonaAI, a cutting-edge application that leverages Retrieval-Augmented Generation (RAG) and the LLAMA model to create highly personalized digital avatars capable of accurately mimicking individual personalities.
no code implementations • 22 Dec 2024 • Hanhua Long, Wenbin Bi, Jian Sun
Lightweight design, as a key approach to mitigate disparity between computational requirements of deep learning models and hardware performance, plays a pivotal role in advancing application of deep learning technologies on mobile and embedded devices, alongside rapid development of smart home, telemedicine, and autonomous driving.
no code implementations • 30 Nov 2024 • Xinzheng Wu, Junyi Chen, Xingyu Xing, Jian Sun, Ye Tian, Lihao Liu, Yong Shen
In fact, all the subspaces representing danger in the logical scenario space, rather than only the most critical concrete scenario, play a more significant role for the safety evaluation.
2 code implementations • 3 Nov 2024 • Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun
More crucially, we design the transport map for restoration as a two-pass DA-RCOT map, in which the transport residual is computed in the first pass and then encoded as multi-scale residual embeddings to condition the second-pass restoration.
Ranked #1 on
Unified Image Restoration
on Rain100L
(Average PSNR (dB) metric, using extra
training data)
5-Degradation Blind All-in-One Image Restoration
Blind All-in-One Image Restoration
no code implementations • 25 Oct 2024 • Muath Alsuhaibani, Ali Pourramezan Fard, Jian Sun, Farida Far Poor, Peter S. Pressman, Mohammad H. Mahoor
This review paper explores recent advances in deep learning approaches for non-invasive cognitive impairment detection.
1 code implementation • 19 Sep 2024 • Shiyu Fang, Jiaqi Liu, Mingyu Ding, Yiming Cui, Chen Lv, Peng Hang, Jian Sun
At present, Connected Autonomous Vehicles (CAVs) have begun to open road testing around the world, but their safety and efficiency performance in complex scenarios is still not satisfactory.
1 code implementation • 3 Sep 2024 • Qiang Zheng, Chao Zhang, Jian Sun
Point cloud classification plays a crucial role in the processing and analysis of data from 3D sensors such as LiDAR, which are commonly used in applications like autonomous vehicles, robotics, and environmental monitoring.
no code implementations • 3 Sep 2024 • Qiang Zheng, Chao Zhang, Jian Sun
This paper introduces PMT-MAE (Point MLP-Transformer Masked Autoencoder), a novel self-supervised learning framework for point cloud classification.
no code implementations • 3 Sep 2024 • Qiang Zheng, Chao Zhang, Jian Sun
To address these challenges, we introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models, thereby reducing hardware demands.
no code implementations • 30 Aug 2024 • Tong Nie, Junlin He, Yuewen Mei, Guoyang Qin, Guilong Li, Jian Sun, Wei Ma
The proliferation of e-commerce and urbanization has significantly intensified delivery operations in urban areas, boosting the volume and complexity of delivery demand.
1 code implementation • 19 Aug 2024 • Sihan Yang, Haixia Bi, Hai Zhang, Jian Sun
We train SAM-UNet on SA-Med2D-16M, the largest 2-dimensional medical image segmentation dataset to date, yielding a universal pretrained model for medical images.
no code implementations • 10 Aug 2024 • Qiang Zheng, Chao Zhang, Jian Sun
In recent years, point cloud analysis methods based on the Transformer architecture have made significant progress, particularly in the context of multimedia applications such as 3D modeling, virtual reality, and autonomous systems.
no code implementations • 2 Aug 2024 • Yucheng Yang, Xiang Gu, Jian Sun
The existence of domain and category shift makes the task challenging and requires us to distinguish "known" samples (i. e., samples whose labels exist in both domains) and "unknown" samples (i. e., samples whose labels exist in only one domain) in both domains before reducing the domain gap.
no code implementations • 28 Jul 2024 • Yuewen Mei, Tong Nie, Jian Sun, Ye Tian
Hence, Fault Injection (FI) testing is conducted by practitioners to evaluate the safety level of HAVs.
no code implementations • 26 Jul 2024 • Zhipeng Zhang, Yanjun Zhang, Jian Sun
This paper introduces an innovative singularity-free output feedback model reference adaptive control (MRAC) method applicable to a wide range of continuous-time linear time-invariant (LTI) systems with general relative degrees.
1 code implementation • 24 Jul 2024 • Tong Nie, Yuewen Mei, Guoyang Qin, Jian Sun, Wei Ma
The former adopts individual channel treatment and has been shown to be more robust to distribution shifts, but lacks sufficient capacity to model meaningful channel interactions.
no code implementations • 18 Jul 2024 • Jian Sun, Yuqi Dai, Chi-Man Vong, Qing Xu, Shengbo Eben Li, Jianqiang Wang, Lei He, Keqiang Li
Based on prior knowledge about the main composition of the BEV surrounding environment varying with the increase of distance intervals, long-sequence global modeling is utilized to improve the model's understanding and perception of the environment.
no code implementations • 17 Jul 2024 • Yuqi Dai, Jian Sun, Shengbo Eben Li, Qing Xu, Jianqiang Wang, Lei He, Keqiang Li
Perception is essential for autonomous driving system.
no code implementations • 10 Jul 2024 • Yichun Ye, He Zhang, Ye Tian, Jian Sun, Karl Meinke
To solve it, we devise a method to represent, generate, and reweight the distribution of risky rare events.
no code implementations • 1 Jul 2024 • Qiang Zheng, Yafei Qi, Chen Wang, Chao Zhang, Jian Sun
These results underscore the potential and efficiency of PointViG in point cloud analysis.
no code implementations • 13 Jun 2024 • Tong Nie, Guoyang Qin, Wei Ma, Jian Sun
$\textbf{This is the conference version of our paper: Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner}$.
1 code implementation • 6 May 2024 • Tong Nie, Guoyang Qin, Wei Ma, Jian Sun
Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system.
1 code implementation • 5 May 2024 • Xiaole Tang, Xin Hu, Xiang Gu, Jian Sun
In this work, we propose a novel Residual-Conditioned Optimal Transport (RCOT) approach, which models image restoration as an optimal transport (OT) problem for both unpaired and paired settings, introducing the transport residual as a unique degradation-specific cue for both the transport cost and the transport map.
Ranked #4 on
Image Super-Resolution
on DIV2K val - 4x upscaling
1 code implementation • 26 Apr 2024 • Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu
To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach.
no code implementations • 3 Feb 2024 • Emily Lin, Jian Sun, Hsingyu Chen, Mohammad H. Mahoor
Additionally, we found that data quality significantly impacts the training of a robust model.
no code implementations • 27 Jan 2024 • Jian Sun, Huabin Cheng, Jian Wu, Zhanyang Zhu, Yu Chen
FA-GSS uses the Golden Section strategy to optimize both wirelength and area targets.
no code implementations • 9 Jan 2024 • Yuzhou Wei, Giorgia Disarò, Wenjie Liu, Jian Sun, Maria Elena Valcher, Gang Wang
A sufficient condition for the existence of such a DUIO is recalled, and a new one is proposed, that is prone to a data-driven adaption.
1 code implementation • CVPR 2024 • Ruixuan Yu, Jian Sun
In this paper we propose a novel pose-transformed equivariant network in which the points are firstly uniquely normalized and then transformed by the learned pose transformations upon which the points after motion are predicted and aggregated.
2 code implementations • 4 Dec 2023 • Tong Nie, Guoyang Qin, Wei Ma, Yuewen Mei, Jian Sun
The exploitation of the inherent structures of spatiotemporal data enables our model to learn balanced signal-noise representations, making it generalizable for a variety of imputation problems.
no code implementations • 1 Dec 2023 • Ji Bian, Jian Sun, Cheng-Xiang Wang, Rui Feng, Jie Huang, Yang Yang, Minggao Zhang
In this paper, a three-dimensional (3-D) non-stationary wideband multiple-input multiple-output (MIMO) channel model based on the WINNER+ channel model is proposed.
no code implementations • 19 Nov 2023 • Wenjie Liu, Yifei Li, Jian Sun, Gang Wang, Jie Chen
This paper investigates the problem of data-driven stabilization for linear discrete-time switched systems with unknown switching dynamics.
no code implementations • 14 Nov 2023 • Wenjie Liu, Lidong Li, Jian Sun, Fang Deng, Gang Wang, Jie Chen
To this end, a general FDI attack model is presented, which imposes minimally constraints on the switching frequency of attack channels and the magnitude of attack matrices.
1 code implementation • 2 Nov 2023 • Xiang Gu, Liwei Yang, Jian Sun, Zongben Xu
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation.
no code implementations • 19 Oct 2023 • Yifei Li, Xin Wang, Jian Sun, Gang Wang, Jie Chen
In the presence of external disturbances, a model-based STC scheme is put forth for $\mathcal{H}_{\infty}$-consensus of MASs, serving as a baseline for the data-driven STC.
1 code implementation • NeurIPS 2023 • Weipu Zhang, Gang Wang, Jian Sun, Yetian Yuan, Gao Huang
The performance of these algorithms heavily relies on the sequence modeling and generation capabilities of the world model.
Ranked #5 on
Atari Games 100k
on Atari 100k
no code implementations • 26 Sep 2023 • Xiaoqin Huang, Asma Poursoroush, Jian Sun, Michael V. Boland, Chris Johnson, Siamak Yousefi
We characterized the subtypes based on demographic, clinical, ocular, and VF factors at the baseline.
no code implementations • ICCV 2023 • Cuican Yu, Guansong Lu, Yihan Zeng, Jian Sun, Xiaodan Liang, Huibin Li, Zongben Xu, Songcen Xu, Wei zhang, Hang Xu
In this paper, we propose a text-guided 3D faces generation method, refer as TG-3DFace, for generating realistic 3D faces using text guidance.
no code implementations • 20 Aug 2023 • Yechen Zhang, Jian Sun, Gang Wang, Zhuo Li, Wei Chen
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games.
no code implementations • 14 Jul 2023 • Yifei Li, Wenjie Liu, Jian Sun, Gang Wang, Lihua Xie, Jie Chen
This method utilizes measured data and a noise-matrix polytope to ensure near-optimal output synchronization.
1 code implementation • 4 Jul 2023 • Tong Nie, Guoyang Qin, Lijun Sun, Wei Ma, Yu Mei, Jian Sun
Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
1 code implementation • 9 May 2023 • Runqing Wang, Gang Wang, Jian Sun, Fang Deng, Jie Chen
The complex relationships between operations and machines are represented precisely and concisely, for which a dual-attention network (DAN) comprising several interconnected operation message attention blocks and machine message attention blocks is proposed.
no code implementations • 5 May 2023 • Hao Lang, Yinhe Zheng, Yixuan Li, Jian Sun, Fei Huang, Yongbin Li
Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
no code implementations • 2 May 2023 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
In this work, a data-based formulation for computing the steady-state Kalman gain is proposed based on semi-definite programming (SDP) using some noise-free input-state-output data.
no code implementations • 11 Apr 2023 • Jian Sun, Hiroko H. Dodge, Mohammad H. Mahoor
Deep machine learning models including Convolutional Neural Networks (CNN) have been successful in the detection of Mild Cognitive Impairment (MCI) using medical images, questionnaires, and videos.
2 code implementations • 23 Mar 2023 • Xiang Gu, Yucheng Yang, Wei Zeng, Jian Sun, Zongben Xu
In this paper, we propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL) that searches for the optimal matching (i. e., transport plan) guided by the keypoints in OT.
1 code implementation • 10 Mar 2023 • Tong Nie, Guoyang Qin, Yunpeng Wang, Jian Sun
Traffic volume is an indispensable ingredient to provide fine-grained information for traffic management and control.
1 code implementation • 3 Mar 2023 • Liwei Yang, Xiang Gu, Jian Sun
SSDP aims to reduce domain gap by projecting data to the source domain, while MLCL is a learning scheme to learn discriminative and generalizable features on the projected data.
1 code implementation • 15 Feb 2023 • Shihan Liu, Junlin Zha, Jian Sun, Zhuo Li, Gang Wang
This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms.
no code implementations • 14 Feb 2023 • Wenjie Liu, Masashi Wakaiki, Jian Sun, Gang Wang, Jie Chen
If, in addition, the transmission protocols at the controller-to-actuator (C-A) and sensor-to-controller (S-C) channels can be adapted, the self-triggered control architecture can be considerably simplified, leveraging a delicate observer-based deadbeat controller to eliminate the need for running the controller in parallel at the encoder side.
1 code implementation • NeurIPS 2021 • Lin Song, Songyang Zhang, Songtao Liu, Zeming Li, Xuming He, Hongbin Sun, Jian Sun, Nanning Zheng
Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region.
no code implementations • 29 Nov 2022 • Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Liu, Jian Sun, Yongbin Li, Bin Wang
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts.
1 code implementation • 23 Nov 2022 • Yingxiu Zhao, Yinhe Zheng, Bowen Yu, Zhiliang Tian, Dongkyu Lee, Jian Sun, Haiyang Yu, Yongbin Li, Nevin L. Zhang
In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data.
no code implementations • 21 Nov 2022 • Yinpei Dai, Wanwei He, Bowen Li, Yuchuan Wu, Zheng Cao, Zhongqi An, Jian Sun, Yongbin Li
Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data.
no code implementations • 10 Nov 2022 • Hao Lang, Yinhe Zheng, Jian Sun, Fei Huang, Luo Si, Yongbin Li
Out-of-Domain (OOD) intent detection is important for practical dialog systems.
1 code implementation • 21 Oct 2022 • Tong Nie, Guoyang Qin, Yunpeng Wang, Jian Sun
In addition, sensors are prone to error or missing data due to various kinds of reasons, speeds from these sensors can become highly noisy.
no code implementations • 20 Oct 2022 • Haomin Fu, Yeqin Zhang, Haiyang Yu, Jian Sun, Fei Huang, Luo Si, Yongbin Li, Cam-Tu Nguyen
This paper introduces Doc2Bot, a novel dataset for building machines that help users seek information via conversations.
1 code implementation • 14 Oct 2022 • Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Bowen Yu, Haiyang Yu, Yongbin Li, Jian Sun, Nevin L. Zhang
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
no code implementations • 27 Sep 2022 • Yeganeh Madadi, Vahid Seydi, Jian Sun, Edward Chaum, Siamak Yousefi
We extend Maximum Mean Discrepancy (MMD), Low-rank coding, and Correlation Alignment (CORAL) to compute the adaptation loss in three base models.
1 code implementation • 14 Sep 2022 • Wanwei He, Yinpei Dai, Min Yang, Jian Sun, Fei Huang, Luo Si, Yongbin Li
To capture the structured dialog semantics, we pre-train the dialog understanding module via a novel tree-induced semi-supervised contrastive learning objective with the help of extra dialog annotations.
no code implementations • 8 Sep 2022 • Jian Sun, Kristopher Innanen
Compared to FWI, which is sensitive to the initial model, IFWI benefits from the increased degrees of freedom with deep learning optimization, thus allowing to start from a random initialization, which greatly reduces the risk of non-uniqueness and being trapped in local minima.
no code implementations • 29 Aug 2022 • Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, Fei Huang, Yongbin Li
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
no code implementations • 22 Aug 2022 • Xin Wang, Jian Sun, Gang Wang, Frank Allgöwer, Jie Chen
The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems (a. k. a.
no code implementations • CVPR 2023 • Xuanyang Zhang, Yonggang Li, Xiangyu Zhang, Yongtao Wang, Jian Sun
Differentiable architecture search (DARTS) has significantly promoted the development of NAS techniques because of its high search efficiency and effectiveness but suffers from performance collapse.
Ranked #13 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
no code implementations • 1 Aug 2022 • Xin Wang, Jian Sun, Gang Wang, Jie Chen
This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme.
1 code implementation • 22 Jul 2022 • Jinrong Yang, Lin Song, Songtao Liu, Weixin Mao, Zeming Li, Xiaoping Li, Hongbin Sun, Jian Sun, Nanning Zheng
Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference.
no code implementations • 21 Jul 2022 • Jinrong Yang, Songtao Liu, Zeming Li, Xiaoping Li, Jian Sun
In this paper, we explore the performance of real time models on this metric and endow the models with the capacity of predicting the future, significantly improving the results for streaming perception.
no code implementations • 18 Jul 2022 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity.
no code implementations • 14 Jul 2022 • Zhenyu Zhang, Bowen Yu, Haiyang Yu, Tingwen Liu, Cheng Fu, Jingyang Li, Chengguang Tang, Jian Sun, Yongbin Li
In this paper, we propose a Layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents (VRDs), so as to generate accurate responses in dialogue systems.
2 code implementations • 6 Jul 2022 • HongYu Zhou, Zheng Ge, Songtao Liu, Weixin Mao, Zeming Li, Haiyan Yu, Jian Sun
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters.
1 code implementation • ICCV 2023 • Yingfei Liu, Junjie Yan, Fan Jia, Shuailin Li, Aqi Gao, Tiancai Wang, Xiangyu Zhang, Jian Sun
More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling.
Ranked #2 on
Bird's-Eye View Semantic Segmentation
on nuScenes
(IoU lane - 224x480 - 100x100 at 0.5 metric)
1 code implementation • 1 Jun 2022 • Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian Sun, Jiaya Jia
To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space.
1 code implementation • CVPR 2022 • Yanwei Li, Xiaojuan Qi, Yukang Chen, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion.
1 code implementation • 30 May 2022 • Angtian Wang, Peng Wang, Jian Sun, Adam Kortylewski, Alan Yuille
The Gaussian reconstruction kernels have been proposed by Westover (1990) and studied by the computer graphics community back in the 90s, which gives an alternative representation of object 3D geometry from meshes and point clouds.
no code implementations • 30 May 2022 • Ting-En Lin, Yuchuan Wu, Fei Huang, Luo Si, Jian Sun, Yongbin Li
In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human.
no code implementations • 25 May 2022 • Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw, Aleš Leonardis, Radu Timofte, Zexin Zhang, Cen Liu, Yunbo Peng, Yue Lin, Gaocheng Yu, Jin Zhang, Zhe Ma, Hongbin Wang, Xiangyu Chen, Xintao Wang, Haiwei Wu, Lin Liu, Chao Dong, Jiantao Zhou, Qingsen Yan, Song Zhang, Weiye Chen, Yuhang Liu, Zhen Zhang, Yanning Zhang, Javen Qinfeng Shi, Dong Gong, Dan Zhu, Mengdi Sun, Guannan Chen, Yang Hu, Haowei Li, Baozhu Zou, Zhen Liu, Wenjie Lin, Ting Jiang, Chengzhi Jiang, Xinpeng Li, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Juan Marín-Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Chunyang Li, Long Bao, Gang He, Ziyao Xu, Li Xu, Gen Zhan, Ming Sun, Xing Wen, Junlin Li, Shuang Feng, Fei Lei, Rui Liu, Junxiang Ruan, Tianhong Dai, Wei Li, Zhan Lu, Hengyan Liu, Peian Huang, Guangyu Ren, Yonglin Luo, Chang Liu, Qiang Tu, Fangya Li, Ruipeng Gang, Chenghua Li, Jinjing Li, Sai Ma, Chenming Liu, Yizhen Cao, Steven Tel, Barthelemy Heyrman, Dominique Ginhac, Chul Lee, Gahyeon Kim, Seonghyun Park, An Gia Vien, Truong Thanh Nhat Mai, Howoon Yoon, Tu Vo, Alexander Holston, Sheir Zaheer, Chan Y. Park
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
no code implementations • 24 May 2022 • Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Haiyang Yu, Jian Sun, Yongbin Li
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora.
Ranked #1 on
Open Information Extraction
on CaRB
Knowledge Base Construction
Natural Language Understanding
+2
1 code implementation • 19 May 2022 • Tong Nie, Guoyang Qin, Jian Sun
Rapid advances in sensor, wireless communication, cloud computing and data science have brought unprecedented amount of data to assist transportation engineers and researchers in making better decisions.
2 code implementations • 11 May 2022 • Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
2 code implementations • CVPR 2022 • Yukang Chen, Yanwei Li, Xiangyu Zhang, Jian Sun, Jiaya Jia
In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction.
1 code implementation • 18 Apr 2022 • Ziwei Luo, Youwei Li, Shen Cheng, Lei Yu, Qi Wu, Zhihong Wen, Haoqiang Fan, Jian Sun, Shuaicheng Liu
To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction.
Ranked #1 on
Burst Image Super-Resolution
on SyntheticBurst
1 code implementation • 11 Apr 2022 • Guocheng Qian, Xuanyang Zhang, Guohao Li, Chen Zhao, Yukang Chen, Xiangyu Zhang, Bernard Ghanem, Jian Sun
TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture.
13 code implementations • 10 Apr 2022 • Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, Jian Sun
Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods.
Ranked #1 on
Deblurring
on MSU BASED
1 code implementation • CVPR 2022 • Yisheng He, Yao Wang, Haoqiang Fan, Jian Sun, Qifeng Chen
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models.
no code implementations • 28 Mar 2022 • Junjie Fu, Jian Sun, Gang Wang
Extensive experiments demonstrate that our method can not only improve the attack success rates, but also reduces the number of queries compared to other methods.
1 code implementation • CVPR 2022 • Jinrong Yang, Songtao Liu, Zeming Li, Xiaoping Li, Jian Sun
In this paper, instead of searching trade-offs between accuracy and speed like previous works, we point out that endowing real-time models with the ability to predict the future is the key to dealing with this problem.
Ranked #1 on
Real-Time Object Detection
on Argoverse-HD (Full-Stack, Val)
(sAP metric, using extra
training data)
no code implementations • ACL 2022 • Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin L. Zhang
Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available.
2 code implementations • 22 Mar 2022 • Zhisheng Zhong, Jiequan Cui, Zeming Li, Eric Lo, Jian Sun, Jiaya Jia
Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition.
Ranked #5 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
1 code implementation • Findings (ACL) 2022 • Sai Zhang, Yuwei Hu, Yuchuan Wu, Jiaman Wu, Yongbin Li, Jian Sun, Caixia Yuan, Xiaojie Wang
We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task.
Ranked #1 on
SSTOD
on SSD_NAME
1 code implementation • CVPR 2022 • Zhiyuan Liang, Tiancai Wang, Xiangyu Zhang, Jian Sun, Jianbing Shen
The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss.
2 code implementations • CVPR 2022 • Anlin Zheng, Yuang Zhang, Xiangyu Zhang, Xiaojuan Qi, Jian Sun
Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
Ranked #1 on
Object Detection
on CrowdHuman
no code implementations • 14 Mar 2022 • Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Bowen Li, Jian Sun, Yongbin Li
The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing.
8 code implementations • CVPR 2022 • Xiaohan Ding, Xiangyu Zhang, Yizhuang Zhou, Jungong Han, Guiguang Ding, Jian Sun
We revisit large kernel design in modern convolutional neural networks (CNNs).
Ranked #68 on
Image Classification
on ImageNet
1 code implementation • 10 Mar 2022 • Yingfei Liu, Tiancai Wang, Xiangyu Zhang, Jian Sun
Object query can perceive the 3D position-aware features and perform end-to-end object detection.
Ranked #3 on
3D Object Detection
on TruckScenes
no code implementations • 6 Mar 2022 • Yisheng He, Haoqiang Fan, Haibin Huang, Qifeng Chen, Jian Sun
Instead, we propose a label-free method that learns to enforce the geometric consistency between category template mesh and observed object point cloud under a self-supervision manner.
no code implementations • 16 Feb 2022 • Xin Wang, Julian Berberich, Jian Sun, Gang Wang, Frank Allgöwer, Jie Chen
To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived.
2 code implementations • CVPR 2022 • Yin-Yin He, Peizhen Zhang, Xiu-Shen Wei, Xiangyu Zhang, Jian Sun
In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one.
no code implementations • 8 Dec 2021 • Jian Sun, Yu Zhou, Chengqing Zong
To address the problem, we propose a novel model, called DyMen, to dynamically adjust the subsequent linking target based on the previously linked entities via reinforcement learning, enabling the model to select a link target that can fully use previously linked information.
1 code implementation • NeurIPS 2021 • Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu
To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data.
Ranked #1 on
Partial Domain Adaptation
on DomainNet
no code implementations • NeurIPS 2021 • Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang, Jian Sun
Specifically, 1) we introduce the assumptions that can lead to equilibrium state in SMD, and prove equilibrium can be reached in a linear rate regime under given assumptions; 2) we propose ``angular update" as a substitute for effective learning rate to depict the state of SMD, and derive the theoretical value of angular update in equilibrium state; 3) we verify our assumptions and theoretical results on various large-scale computer vision tasks including ImageNet and MSCOCO with standard settings.
1 code implementation • 29 Nov 2021 • Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, Jian Sun, Yongbin Li
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
Ranked #1 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
1 code implementation • 21 Nov 2021 • Jian Sun, Ali Pourramezan Fard, Mohammad H. Mahoor
To address the computational burdens of the Dynamic Routing mechanism, this paper proposes new Fully Connected (FC) layers by xnorizing the linear projection outside or inside the Dynamic Routing within the CapsFC layer.
Ranked #12 on
Image Classification
on MNIST
(Accuracy metric)
no code implementations • 18 Nov 2021 • Bowen Qin, Lihan Wang, Binyuan Hui, Ruiying Geng, Zheng Cao, Min Yang, Jian Sun, Yongbin Li
Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network.
no code implementations • 6 Nov 2021 • Xia Jiang, Xianlin Zeng, Jian Sun, Jie Chen, Lihua Xie
We prove that local variable estimates generated by the proposed algorithm achieve consensus and are attracted to a neighborhood of the optimal solution in expectation with an $\mathcal{O}(\frac{1}{T}+\frac{1}{\sqrt{T}})$ convergence rate, where $T$ is the total number of iterations.
no code implementations • 29 Oct 2021 • Guanglin Niu, Yang Li, Chengguang Tang, Zhongkai Hu, Shibin Yang, Peng Li, Chengyu Wang, Hao Wang, Jian Sun
The multi-relational Knowledge Base Question Answering (KBQA) system performs multi-hop reasoning over the knowledge graph (KG) to achieve the answer.
Knowledge Base Question Answering
Knowledge Graph Embedding
+1
1 code implementation • NeurIPS 2021 • Zijian Kang, Peizhen Zhang, Xiangyu Zhang, Jian Sun, Nanning Zheng
Knowledge distillation has shown great success in classification, however, it is still challenging for detection.
no code implementations • 25 Oct 2021 • Xin Wang, Jian Sun, Julian Berberich, Gang Wang, Frank Allgöwer, Jie Chen
Data-based representations for time-invariant linear systems with known or unknown system input matrices are first developed, along with a novel class of dynamic triggering schemes for sampled-data systems with time delays.
no code implementations • 25 Oct 2021 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
Finally, a numerical example is given to validate the effectiveness of the proposed control method.
no code implementations • 26 Sep 2021 • Xuanyang Zhang, Xiangyu Zhang, Jian Sun
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher.
1 code implementation • EMNLP 2021 • Che Liu, Rui Wang, Jinghua Liu, Jian Sun, Fei Huang, Luo Si
Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability.
1 code implementation • 23 Sep 2021 • Peizhen Zhang, Zijian Kang, Tong Yang, Xiangyu Zhang, Nanning Zheng, Jian Sun
Instead, we generate an instructive knowledge based only on student representations and regular labels.
2 code implementations • 15 Sep 2021 • Yingming Wang, Xiangyu Zhang, Tong Yang, Jian Sun
Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs.
Ranked #115 on
Object Detection
on COCO minival
1 code implementation • 17 Aug 2021 • Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
1 code implementation • LREC 2022 • Yinhe Zheng, Guanyi Chen, Xin Liu, Jian Sun
To better investigate this issue, we manually annotate 100K dialogues from MMChat and further filter the corpus accordingly, which yields MMChat-hf.
1 code implementation • ICCV 2021 • Xin Wei, Yifei Gong, Fudong Wang, Xing Sun, Jian Sun
In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition.
no code implementations • ACL 2021 • Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.
1 code implementation • 27 Jul 2021 • Songyang Zhang, Lin Song, Songtao Liu, Zheng Ge, Zeming Li, Xuming He, Jian Sun
In this report, we introduce our real-time 2D object detection system for the realistic autonomous driving scenario.
1 code implementation • 26 Jul 2021 • Heran Yang, Jian Sun, Liwei Yang, Zongben Xu
Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image.
42 code implementations • 18 Jul 2021 • Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, Jian Sun
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.
Ranked #1 on
Real-Time Object Detection
on Argoverse-HD (Detection-Only, Val)
(using extra training data)
no code implementations • 9 Jul 2021 • Fangcao Xu, Jian Sun, Guido Cervone, Mark Salvador
Atmospheric correction errors can significantly alter the spectral signature of the observations, and lead to invalid classifications or target detection.
2 code implementations • Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2021 • Ziwei Luo, Lei Yu, Xuan Mo, Youwei Li, Lanpeng Jia, Haoqiang Fan, Jian Sun, Shuaicheng Liu
We propose a novel architecture to handle the problem of multi-frame super-resolution (MFSR).
Ranked #2 on
Burst Image Super-Resolution
on SyntheticBurst
no code implementations • 7 Jun 2021 • Goutam Bhat, Martin Danelljan, Radu Timofte, Kazutoshi Akita, Wooyeong Cho, Haoqiang Fan, Lanpeng Jia, Daeshik Kim, Bruno Lecouat, Youwei Li, Shuaicheng Liu, Ziluan Liu, Ziwei Luo, Takahiro Maeda, Julien Mairal, Christian Micheloni, Xuan Mo, Takeru Oba, Pavel Ostyakov, Jean Ponce, Sanghyeok Son, Jian Sun, Norimichi Ukita, Rao Muhammad Umer, Youliang Yan, Lei Yu, Magauiya Zhussip, Xueyi Zou
This paper reviews the NTIRE2021 challenge on burst super-resolution.
no code implementations • 1 Jun 2021 • Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.
Ranked #1 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
8 code implementations • 22 May 2021 • Zhen Liu, Wenjie Lin, Xinpeng Li, Qing Rao, Ting Jiang, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.
Ranked #5 on
Face Alignment
on WFW (Extra Data)
1 code implementation • CVPR 2021 • Zhibo Fan, Yuchen Ma, Zeming Li, Jian Sun
Recently few-shot object detection is widely adopted to deal with data-limited situations.
1 code implementation • 17 May 2021 • Andrey Ignatov, Kim Byeoung-su, Radu Timofte, Angeline Pouget, Fenglong Song, Cheng Li, Shuai Xiao, Zhongqian Fu, Matteo Maggioni, Yibin Huang, Shen Cheng, Xin Lu, Yifeng Zhou, Liangyu Chen, Donghao Liu, Xiangyu Zhang, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Bin Huang, Tianbao Zhou, Shuai Liu, Lei Lei, Chaoyu Feng, Liguang Huang, Zhikun Lei, Feifei Chen
A detailed description of all models developed in the challenge is provided in this paper.
1 code implementation • 27 Apr 2021 • Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng, Jian Dai, Qiao Liu, Hao Wang, Jian Sun, Fei Huang, Luo Si
Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances.
1 code implementation • CVPR 2021 • Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei zhang, Jian Sun
We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points.
no code implementations • CVPR 2021 • Yuchen Ma, Songtao Liu, Zeming Li, Jian Sun
We propose a dense object detector with an instance-wise sampling strategy, named IQDet.
no code implementations • 13 Apr 2021 • Thomas Eboli, Jian Sun, Jean Ponce
We address the problem of non-blind deblurring and demosaicking of noisy raw images.
1 code implementation • CVPR 2021 • Songyang Zhang, Zeming Li, Shipeng Yan, Xuming He, Jian Sun
Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition.
Ranked #19 on
Long-tail Learning
on Places-LT
2 code implementations • CVPR 2021 • Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, Jian Sun
Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object.
Ranked #77 on
Object Detection
on COCO test-dev
no code implementations • 22 Mar 2021 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals.
6 code implementations • CVPR 2021 • Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun
From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.
Ranked #146 on
Object Detection
on COCO test-dev
1 code implementation • CVPR 2021 • Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu
To balance plasticity and stability of network in continual learning, in this paper, we propose a novel network training algorithm called Adam-NSCL, which sequentially optimizes network parameters in the null space of previous tasks.
1 code implementation • CVPR 2021 • Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qian Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Chi Zhang, Yichen Wei, Jian Sun
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.
Ranked #32 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
no code implementations • 7 Mar 2021 • Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu
In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.
3 code implementations • CVPR 2021 • Yisheng He, Haibin Huang, Haoqiang Fan, Qifeng Chen, Jian Sun
Moreover, at the output representation stage, we designed a simple but effective 3D keypoints selection algorithm considering the texture and geometry information of objects, which simplifies keypoint localization for precise pose estimation.
Ranked #1 on
6D Pose Estimation
on LineMOD
no code implementations • 4 Feb 2021 • Manzhu Yu, Fangcao Xu, Weiming Hu, Jian Sun, Guido Cervone
Meanwhile, by using IoT observations, the spatial resolution of air temperature predictions is significantly improved.
1 code implementation • CVPR 2021 • Xuanyang Zhang, Pengfei Hou, Xiangyu Zhang, Jian Sun
In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS).
1 code implementation • 19 Jan 2021 • Zeming Li, Songtao Liu, Jian Sun
The teacher's weight is a momentum update of the student, and the teacher's BN statistics is a momentum update of those in history.
25 code implementations • CVPR 2021 • Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun
We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a multi-branch topology.
Ranked #49 on
Semantic Segmentation
on Cityscapes val
2 code implementations • 5 Jan 2021 • Binyuan Hui, Ruiying Geng, Qiyu Ren, Binhua Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Pengfei Zhu, Xiaodan Zhu
Semantic parsing has long been a fundamental problem in natural language processing.
Ranked #5 on
Dialogue State Tracking
on CoSQL
no code implementations • 1 Jan 2021 • Xiang Gu, Jiasun Feng, Jian Sun, Zongben Xu
In this framework, we model the domain generalization as a learning problem that enforces the learner to be able to generalize well for any train/val subsets splitting of the training dataset.
no code implementations • 25 Dec 2020 • Tiancai Wang, Xiangyu Zhang, Jian Sun
In this paper, we present an implicit feature pyramid network (i-FPN) for object detection.
no code implementations • 13 Dec 2020 • Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, GuanAn Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
1 code implementation • NeurIPS 2020 • Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng
To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation.
1 code implementation • NeurIPS 2020 • Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Xiangyu Zhang, Hongbin Sun, Jian Sun, Nanning Zheng
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation.
1 code implementation • CVPR 2021 • JianFeng Wang, Lin Song, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng
Mainstream object detectors based on the fully convolutional network has achieved impressive performance.
no code implementations • NeurIPS 2020 • Gang Wang, Songtao Lu, Georgios Giannakis, Gerald Tesauro, Jian Sun
The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability.
no code implementations • COLING 2020 • Jian Sun, Yu Zhou, Chengqing Zong
The hierarchical attention adaptively aggregates the low-hierarchy and the high-hierarchy information, which is beneficial to balance the neighborhood information of counterpart entities and distinguish non-counterpart entities with similar structures.
2 code implementations • CVPR 2021 • Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun
By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.
Ranked #1 on
Optical Flow Estimation
on Sintel Final unsupervised
6 code implementations • CVPR 2021 • Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.
Ranked #1 on
Panoptic Segmentation
on COCO minival
(SQ metric)
no code implementations • 27 Nov 2020 • Songtao Liu, Zeming Li, Jian Sun
Our Faster R-CNN (ResNet50-FPN) baseline achieves 39. 8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet.
no code implementations • ECCV 2020 • Ruixuan Yu, Xin Wei, Federico Tombari, Jian Sun
In this work, we propose a novel deep network for point clouds by incorporating positional information of points as inputs while yielding rotation-invariance.
no code implementations • 6 Oct 2020 • Zeming Li, Yuchen Ma, Yukang Chen, Xiangyu Zhang, Jian Sun
In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation.
1 code implementation • 5 Oct 2020 • Benjin Zhu, Junqiang Huang, Zeming Li, Xiangyu Zhang, Jian Sun
In this paper, we propose EqCo (Equivalent Rules for Contrastive Learning) to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning framework.
5 code implementations • CVPR 2021 • Ningning Ma, Xiangyu Zhang, Ming Liu, Jian Sun
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.
no code implementations • 28 Jul 2020 • Yunzeng Li, Wensheng Zhang, Cheng-Xiang Wang, Jian Sun, Yu Liu
Then, the vacant channels in the selected segment will be aggregated for satisfying the user requirement.
no code implementations • 28 Jul 2020 • Qingshan Chen, Cheng-Xiang Wang, Jian Sun, Wensheng Zhang, Qiuming Zhu
The study of the underlying VLC channel is the basis for designing the VLC communication system.
no code implementations • 28 Jul 2020 • Jie Huang, Cheng-Xiang Wang, Hengtai Chang, Jian Sun, Xiqi Gao
Millimeter wave (mmWave) bands have been utilized for the fifth generation (5G) communication systems and will no doubt continue to be deployed for beyond 5G (B5G).
no code implementations • 26 Jul 2020 • Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun
Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases.
2 code implementations • ECCV 2020 • Ningning Ma, Xiangyu Zhang, Jiawei Huang, Jian Sun
WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space.
7 code implementations • ECCV 2020 • Ningning Ma, Xiangyu Zhang, Jian Sun
We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.
2 code implementations • ECCV 2020 • Han Qiu, Yuchen Ma, Zeming Li, Songtao Liu, Jian Sun
In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature.
no code implementations • 17 Jul 2020 • Mehmet Ekmekci, Leandro Gorno, Lucas Maestri, Jian Sun, Dong Wei
The principal learns about the agent's type from a noisy performance measure, which can be manipulated by the agent via a costly and hidden action.
2 code implementations • 7 Jul 2020 • Benjin Zhu, Jian-Feng Wang, Zhengkai Jiang, Fuhang Zong, Songtao Liu, Zeming Li, Jian Sun
During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions.
1 code implementation • ECCV 2020 • Miao Hao, Yitao Liu, Xiangyu Zhang, Jian Sun
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems.
1 code implementation • ECCV 2020 • Thomas Eboli, Jian Sun, Jean Ponce
Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates.
no code implementations • ACL 2020 • Yinpei Dai, Hangyu Li, Chengguang Tang, Yongbin Li, Jian Sun, Xiaodan Zhu
Existing end-to-end dialog systems perform less effectively when data is scarce.
no code implementations • 16 Jun 2020 • Thomas Eboli, Alex Nowak-Vila, Jian Sun, Francis Bach, Jean Ponce, Alessandro Rudi
We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning.
no code implementations • 16 Jun 2020 • Qingtao Zhao, Jennie Si, Jian Sun
In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives.
no code implementations • 15 Jun 2020 • Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang, Jian Sun
In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD).
no code implementations • 18 May 2020 • Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
no code implementations • ACL 2020 • Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification.
no code implementations • 5 May 2020 • Yinpei Dai, Huihua Yu, Yixuan Jiang, Chengguang Tang, Yongbin Li, Jian Sun
Dialog management (DM) is a crucial component in a task-oriented dialog system.
1 code implementation • ECCV 2020 • Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan, Xiangyu Zhang, Yichen Wei, Qingyi Gu, Jian Sun
Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.
4 code implementations • 26 Apr 2020 • Yukang Chen, Peizhen Zhang, Zeming Li, Yanwei Li, Xiangyu Zhang, Lu Qi, Jian Sun, Jiaya Jia
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
1 code implementation • CVPR 2020 • Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.
1 code implementation • CVPR 2020 • Tiancai Wang, Tong Yang, Martin Danelljan, Fahad Shahbaz Khan, Xiangyu Zhang, Jian Sun
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
no code implementations • CVPR 2021 • Jin Chen, Xijun Wang, Zichao Guo, Xiangyu Zhang, Jian Sun
More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose.
Ranked #22 on
Semantic Segmentation
on MCubeS
1 code implementation • CVPR 2020 • Yanwei Li, Lin Song, Yukang Chen, Zeming Li, Xiangyu Zhang, Xingang Wang, Jian Sun
To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space.
3 code implementations • CVPR 2020 • Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, Jian Sun
We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.
Ranked #2 on
Pedestrian Detection
on TJU-Ped-campus