9 code implementations • 13 Nov 2018 • Buyu Li, Yu Liu, Xiaogang Wang
Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i. e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples.
Ranked #165 on Object Detection on COCO test-dev
3 code implementations • ICCV 2023 • Zhuofan Zong, Guanglu Song, Yu Liu
This new training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training the multiple parallel auxiliary heads supervised by one-to-many label assignments such as ATSS and Faster RCNN.
Ranked #1 on Object Detection on LVIS v1.0 val (using extra training data)
6 code implementations • 20 Feb 2023 • Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, Jingren Zhou
Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.
1 code implementation • 9 Mar 2023 • Zhiheng Liu, Ruili Feng, Kai Zhu, Yifei Zhang, Kecheng Zheng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao
Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.
2 code implementations • 18 Jul 2023 • Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, Hengshuang Zhao
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way.
4 code implementations • 17 Jan 2020 • Hao Shao, Shengju Qian, Yu Liu
In this way, a heavy temporal model is replaced by a simple interlacing operator.
3 code implementations • CVPR 2021 • Junting Pan, Siyu Chen, Mike Zheng Shou, Yu Liu, Jing Shao, Hongsheng Li
We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
Ranked #2 on Action Recognition on AVA v2.1
3 code implementations • ICLR 2022 • Kunchang Li, Yali Wang, Gao Peng, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 8% and 71. 4% top-1 accuracy respectively.
Ranked #8 on Action Recognition on Something-Something V1
2 code implementations • 12 Jan 2022 • Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.
1 code implementation • 7 Dec 2023 • Yujie Wei, Shiwei Zhang, Zhiwu Qing, Hangjie Yuan, Zhiheng Liu, Yu Liu, Yingya Zhang, Jingren Zhou, Hongming Shan
In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern.
2 code implementations • 14 Dec 2023 • Xiang Wang, Shiwei Zhang, Han Zhang, Yu Liu, Yingya Zhang, Changxin Gao, Nong Sang
Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models.
1 code implementation • 12 Dec 2023 • Yinmin Zhang, Jie Liu, Chuming Li, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang
In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining.
10 code implementations • 12 Nov 2018 • Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li
However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.
Ranked #4 on Traffic Prediction on SZ-Taxi
2 code implementations • ICCV 2019 • Baoyun Peng, Xiao Jin, Jiaheng Liu, Shunfeng Zhou, Yi-Chao Wu, Yu Liu, Dongsheng Li, Zhaoning Zhang
Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level.
1 code implementation • NeurIPS 2023 • Yazhe Niu, Yuan Pu, Zhenjie Yang, Xueyan Li, Tong Zhou, Jiyuan Ren, Shuai Hu, Hongsheng Li, Yu Liu
Building agents based on tree-search planning capabilities with learned models has achieved remarkable success in classic decision-making problems, such as Go and Atari.
1 code implementation • 20 Jul 2018 • Hang Zhou, Yu Liu, Ziwei Liu, Ping Luo, Xiaogang Wang
Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech.
7 code implementations • 24 Jan 2022 • Kunchang Li, Yali Wang, Junhao Zhang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao
Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.
Ranked #153 on Image Classification on ImageNet
1 code implementation • ICCV 2019 • Xiao Jin, Baoyun Peng, Yi-Chao Wu, Yu Liu, Jiaheng Liu, Ding Liang, Xiaolin Hu
However, we find that the representation of a converged heavy model is still a strong constraint for training a small student model, which leads to a high lower bound of congruence loss.
1 code implementation • 30 May 2023 • Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao
Synthesizing images with user-specified subjects has received growing attention due to its practical applications.
1 code implementation • CVPR 2020 • Hang Zhou, Jihao Liu, Ziwei Liu, Yu Liu, Xiaogang Wang
Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods.
1 code implementation • 12 Mar 2020 • Manyuan Zhang, Hao Shao, Guanglu Song, Yu Liu, Junjie Yan
In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019.
1 code implementation • 28 Jul 2022 • Hao Shao, Letian Wang, RuoBing Chen, Hongsheng Li, Yu Liu
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns.
Ranked #2 on Autonomous Driving on CARLA Leaderboard
2 code implementations • 17 Mar 2020 • Yu Liu, Guanglu Song, Yuhang Zang, Yan Gao, Enze Xie, Junjie Yan, Chen Change Loy, Xiaogang Wang
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
2 code implementations • CVPR 2020 • Guanglu Song, Yu Liu, Xiaogang Wang
The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years.
Ranked #67 on Object Detection on COCO test-dev
2 code implementations • 7 Jul 2023 • Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Yu Liu, Kai Chen, Ping Luo
Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence.
Ranked #1 on Visual Question Answering (VQA) on VCR (Q-AR) test
1 code implementation • 12 Dec 2023 • Hao Shao, Yuxuan Hu, Letian Wang, Steven L. Waslander, Yu Liu, Hongsheng Li
On the other hand, previous autonomous driving methods tend to rely on limited-format inputs (e. g. sensor data and navigation waypoints), restricting the vehicle's ability to understand language information and interact with humans.
1 code implementation • 1 Feb 2024 • Fu-Yun Wang, Zhaoyang Huang, Xiaoyu Shi, Weikang Bian, Guanglu Song, Yu Liu, Hongsheng Li
We validate the proposed strategy in image-conditioned video generation and layout-conditioned video generation, all achieving top-performing results.
1 code implementation • 29 May 2023 • Fu-Yun Wang, Wenshuo Chen, Guanglu Song, Han-Jia Ye, Yu Liu, Hongsheng Li
To address this challenge, we introduce a novel paradigm dubbed as Gen-L-Video, capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising hundreds of frames with diverse semantic segments without introducing additional training, all while preserving content consistency.
1 code implementation • ICCV 2017 • Yu Liu, Hongyang Li, Junjie Yan, Fangyin Wei, Xiaogang Wang, Xiaoou Tang
To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid.
Ranked #3 on Face Detection on Annotated Faces in the Wild
2 code implementations • 22 Oct 2018 • Enqiang Guo, Xinsha Fu, Jiawei Zhu, Min Deng, Yu Liu, Qing Zhu, Haifeng Li
A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to define and measure since the noisy changes and semantic ones are entangled.
2 code implementations • 16 Jun 2020 • Siyu Chen, Junting Pan, Guanglu Song, Manyuan Zhang, Hao Shao, Ziyi Lin, Jing Shao, Hongsheng Li, Yu Liu
This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.
1 code implementation • 8 Oct 2016 • Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
1 code implementation • 29 Nov 2022 • Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang
In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.
Ranked #1 on SMAC on SMAC 3s5z_vs_3s6z
1 code implementation • 2 Oct 2017 • Yu Liu, Hongyang Li, Xiaogang Wang
Feature matters.
1 code implementation • 22 Feb 2017 • Yu Liu, Hongyang Li, Xiaogang Wang
Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance.
1 code implementation • CVPR 2020 • Ling Yang, Liangliang Li, Zilun Zhang, Xinyu Zhou, Erjin Zhou, Yu Liu
To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example.
Ranked #2 on Few-Shot Learning on Mini-ImageNet - 1-Shot Learning
1 code implementation • ICCV 2023 • Zhuofan Zong, Dongzhi Jiang, Guanglu Song, Zeyue Xue, Jingyong Su, Hongsheng Li, Yu Liu
The HoP approach is straightforward: given the current timestamp t, we generate a pseudo Bird's-Eye View (BEV) feature of timestamp t-k from its adjacent frames and utilize this feature to predict the object set at timestamp t-k. Our approach is motivated by the observation that enforcing the detector to capture both the spatial location and temporal motion of objects occurring at historical timestamps can lead to more accurate BEV feature learning.
Ranked #3 on 3D Object Detection on nuScenes Camera Only
2 code implementations • 8 Apr 2024 • Dazhong Shen, Guanglu Song, Zeyue Xue, Fu-Yun Wang, Yu Liu
Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space.
2 code implementations • 4 Apr 2024 • Dongzhi Jiang, Guanglu Song, Xiaoshi Wu, Renrui Zhang, Dazhong Shen, Zhuofan Zong, Yu Liu, Hongsheng Li
We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm.
2 code implementations • 7 Mar 2020 • Jie Chen, Ziyang Yuan, Jian Peng, Li Chen, Haozhe Huang, Jiawei Zhu, Yu Liu, Haifeng Li
However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information.
1 code implementation • 2 Sep 2019 • Yu Liu, Guanglu Song, Manyuan Zhang, Jihao Liu, Yucong Zhou, Junjie Yan
Large scale face recognition is challenging especially when the computational budget is limited.
1 code implementation • CVPR 2023 • Jihao Liu, Xin Huang, Jinliang Zheng, Yu Liu, Hongsheng Li
In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers.
Ranked #2 on Image Classification on Places205
1 code implementation • CVPR 2020 • Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan
In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.
1 code implementation • 19 Mar 2024 • Linjiang Huang, Rongyao Fang, Aiping Zhang, Guanglu Song, Si Liu, Yu Liu, Hongsheng Li
In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their trained resolutions.
1 code implementation • CVPR 2017 • Yu Liu, Junjie Yan, Wanli Ouyang
In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage.
Ranked #6 on Face Verification on YouTube Faces DB
1 code implementation • 30 Apr 2022 • Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu, Hongyang Li, Junchi Yan
Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges.
2 code implementations • 12 Jul 2022 • Jihao Liu, Xin Huang, Guanglu Song, Hongsheng Li, Yu Liu
Finally, we integrate configurable operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm to fully explore the optimal combination of the operators.
Ranked #12 on Neural Architecture Search on ImageNet
1 code implementation • 18 Jul 2022 • Jihao Liu, Boxiao Liu, Hang Zhou, Hongsheng Li, Yu Liu
In this paper, we propose a novel data augmentation technique TokenMix to improve the performance of vision transformers.
1 code implementation • ECCV 2020 • Zhengkai Jiang, Yu Liu, Ceyuan Yang, Jihao Liu, Peng Gao, Qian Zhang, Shiming Xiang, Chunhong Pan
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.
Ranked #22 on Video Object Detection on ImageNet VID
1 code implementation • CVPR 2021 • Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.
1 code implementation • 4 Mar 2022 • Lei Dong, Rui Du, Yu Liu
China's demographic changes have important global economic and geopolitical implications.
1 code implementation • 24 Nov 2021 • Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
1 code implementation • ICCV 2023 • Ruowei Wang, Yu Liu, Pei Su, Jianwei Zhang, Qijun Zhao
Our method utilizes implicit functions as the 3D shape representation and combines a novel latent-space GAN with a linear subspace model to discover semantic dimensions in the local latent space of 3D shapes.
1 code implementation • 16 Jan 2024 • Xin Zhang, Yu Liu, Yuming Lin, Qingmin Liao, Yong Li
Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities.
1 code implementation • 20 Oct 2022 • Zeyue Xue, Jianming Liang, Guanglu Song, Zhuofan Zong, Liang Chen, Yu Liu, Ping Luo
To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.
1 code implementation • 19 Apr 2024 • Zhuofan Zong, Bingqi Ma, Dazhong Shen, Guanglu Song, Hao Shao, Dongzhi Jiang, Hongsheng Li, Yu Liu
Although some large-scale pretrained vision encoders such as vision encoders in CLIP and DINOv2 have brought promising performance, we found that there is still no single vision encoder that can dominate various image content understanding, e. g., the CLIP vision encoder leads to outstanding results on general image understanding but poor performance on document or chart content.
1 code implementation • 18 Aug 2022 • Jianming Liang, Guanglu Song, Biao Leng, Yu Liu
The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture.
1 code implementation • 8 May 2023 • Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, RuoBing Chen, Yu Liu, Steven L. Waslander
Inspired by this, we propose ASAP-RL, an efficient reinforcement learning algorithm for autonomous driving that simultaneously leverages motion skills and expert priors.
2 code implementations • 17 Oct 2022 • Baoxiong Jia, Yu Liu, Siyuan Huang
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning.
1 code implementation • 30 Jun 2018 • Yu Liu, Guanlong Zhao, Boyuan Gong, Yang Li, Ritu Raj, Niraj Goel, Satya Kesav, Sandeep Gottimukkala, Zhangyang Wang, Wenqi Ren, DaCheng Tao
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.
1 code implementation • 29 Jan 2020 • Yu Liu, Jie Li, Xia Yuan, Chunxia Zhao, Roland Siegwart, Ian Reid, Cesar Cadena
We propose PALNet, a novel hybrid network for SSC based on single depth.
1 code implementation • ICCV 2023 • Jihao Liu, Tai Wang, Boxiao Liu, Qihang Zhang, Yu Liu, Hongsheng Li
In this paper, we propose Geometry Enhanced Masked Image Modeling (GeoMIM) to transfer the knowledge of the LiDAR model in a pretrain-finetune paradigm for improving the multi-view camera-based 3D detection.
1 code implementation • 18 Mar 2024 • Yang Zhou, Hao Shao, Letian Wang, Steven L. Waslander, Hongsheng Li, Yu Liu
Context information, such as road maps and surrounding agents' states, provides crucial geometric and semantic information for motion behavior prediction.
1 code implementation • 25 Mar 2024 • Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, Hongsheng Li
This paper presents Visual CoT, a novel pipeline that leverages the reasoning capabilities of multi-modal large language models (MLLMs) by incorporating visual Chain-of-Thought (CoT) reasoning.
1 code implementation • CVPR 2021 • Lianghua Huang, Yu Liu, Bin Wang, Pan Pan, Yinghui Xu, Rong Jin
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias.
1 code implementation • 5 Jun 2023 • Siyuan Yang, Lu Zhang, Yu Liu, Zhizhuo Jiang, You He
We construct a local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction.
1 code implementation • 21 Dec 2023 • Qinying Liu, Wei Wu, Kecheng Zheng, Zhan Tong, Jiawei Liu, Yu Liu, Wei Chen, Zilei Wang, Yujun Shen
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data.
1 code implementation • 20 Mar 2024 • Fu-Yun Wang, Xiaoshi Wu, Zhaoyang Huang, Xiaoyu Shi, Dazhong Shen, Guanglu Song, Yu Liu, Hongsheng Li
We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation, a diffusion-based pipeline that leverages both the intrinsic data-specific patterns of the source video and the image/video generative prior for effective outpainting.
2 code implementations • ICCV 2019 • Haokui Zhang, Chunhua Shen, Ying Li, Yuanzhouhan Cao, Yu Liu, Youliang Yan
The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion.
Ranked #5 on Monocular Depth Estimation on Mid-Air Dataset
1 code implementation • 22 Nov 2022 • Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li
In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors.
1 code implementation • 13 Sep 2017 • Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang
A key observation is that it is difficult to classify anchors of different sizes with the same set of features.
Ranked #2 on Region Proposal on COCO test-dev
1 code implementation • 19 Feb 2017 • Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang
In this paper, we propose a zoom-out-and-in network for generating object proposals.
3 code implementations • 20 Nov 2018 • Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin, Yu Liu, Shin-Fang Ch'ng, Thanh-Toan Do, Ian Reid
Our approaches rely on local features with an encoding technique to represent an image as a single vector.
1 code implementation • 8 May 2018 • Yu Liu, Guanlong Zhao
In this work, we investigate the possibility of replacing the $\ell_2$ loss with perceptually derived loss functions (SSIM, MS-SSIM, etc.)
1 code implementation • CVPR 2022 • Qi Jia, Shuilian Yao, Yu Liu, Xin Fan, Risheng Liu, Zhongxuan Luo
To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.
1 code implementation • ICCV 2023 • Ziye Chen, Yu Liu, Mingming Gong, Bo Du, Guoqi Qian, Kate Smith-Miles
While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line's global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies.
Ranked #1 on Lane Detection on CurveLanes
1 code implementation • 5 Oct 2023 • Zhanhui Zhou, Jie Liu, Chao Yang, Jing Shao, Yu Liu, Xiangyu Yue, Wanli Ouyang, Yu Qiao
A single language model (LM), despite aligning well with an average labeler through reinforcement learning from human feedback (RLHF), may not universally suit diverse human preferences.
1 code implementation • 15 Oct 2020 • Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
1 code implementation • 25 Feb 2023 • Yu Liu, Xin Zhang, Jingtao Ding, Yanxin Xi, Yong Li
To address such issues, in this paper, we propose a Knowledge-infused Contrastive Learning (KnowCL) model for urban imagery-based socioeconomic prediction.
1 code implementation • 19 Sep 2023 • Zhilun Zhou, Jingtao Ding, Yu Liu, Depeng Jin, Yong Li
To capture the effect of multiple factors on urban flow, such as region features and urban environment, we employ diffusion model to generate urban flow for regions under different conditions.
1 code implementation • 8 Jul 2020 • Yu Liu, Quanming Yao, Yong Li
With the rapid development of knowledge bases (KBs), link prediction task, which completes KBs with missing facts, has been broadly studied in especially binary relational KBs (a. k. a knowledge graph) with powerful tensor decomposition related methods.
1 code implementation • ECCV 2020 • Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars
Since those regularization strategies are mostly associated with classifier outputs, we propose a MUlti-Classifier (MUC) incremental learning paradigm that integrates an ensemble of auxiliary classifiers to estimate more effective regularization constraints.
1 code implementation • 25 Apr 2020 • Zhe Sun, Zihao Huang, Feng Duan, Yu Liu
It has been already shown in literature that the hybrid of EEG and NIRS has better results than their respective individual signals.
Human-Computer Interaction Signal Processing
1 code implementation • 11 Feb 2020 • Haokui Zhang, Yu Liu, Bei Fang, Ying Li, Lingqiao Liu, Ian Reid
Hyperspectral image(HSI) classification has been improved with convolutional neural network(CNN) in very recent years.
2 code implementations • 19 Jun 2022 • Hao Guo, Andre Python, Yu Liu
In spatial regression models, spatial heterogeneity may be considered with either continuous or discrete specifications.
1 code implementation • 18 Aug 2022 • Xizhe Xue, Dongdong Yu, Lingqiao Liu, Yu Liu, Satoshi Tsutsui, Ying Li, Zehuan Yuan, Ping Song, Mike Zheng Shou
Based on the single-stage instance segmentation framework, we propose a regularization model to predict foreground pixels and use its relation to instance segmentation to construct a cross-task consistency loss.
1 code implementation • 1 Aug 2023 • Yanxin Xi, Yu Liu, Tong Li, Jintao Ding, Yunke Zhang, Sasu Tarkoma, Yong Li, Pan Hui
Especially satellite imagery is a potential data source for studying sustainable urban development.
1 code implementation • 28 Mar 2024 • Pingcheng Dong, Yonghao Tan, Dong Zhang, Tianwei Ni, Xuejiao Liu, Yu Liu, Peng Luo, Luhong Liang, Shih-Yang Liu, Xijie Huang, Huaiyu Zhu, Yun Pan, Fengwei An, Kwang-Ting Cheng
Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs.
1 code implementation • 9 Dec 2021 • Yunpeng Bai, Chen Gong, Bin Zhang, Guoliang Fan, Xinwen Hou, Yu Liu
HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards.
1 code implementation • 23 Mar 2022 • Xiao Liu, Bonan Gao, Basem Suleiman, Han You, Zisu Ma, Yu Liu, Ali Anaissi
Recommender systems have been successfully used in many domains with the help of machine learning algorithms.
1 code implementation • 6 Aug 2020 • Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
1 code implementation • 2 Jan 2020 • Lei Dong, Zhou Huang, Jiang Zhang, Yu Liu
Understanding quantitative relationships between urban elements is crucial for a wide range of applications.
Physics and Society
1 code implementation • 12 Feb 2024 • Xiaowei Zhao, Yong Zhou, Xiujuan Xu, Yu Liu
This paper presents the Extensible Multi-Granularity Fusion (EMGF) network, which integrates information from dependency and constituent syntactic, attention semantic , and external knowledge graphs.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
1 code implementation • 20 Apr 2021 • Yu Liu, Quanming Yao, Yong Li
N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts.
1 code implementation • 6 Jan 2023 • Chao Li, Chen Gong, Qiang He, Xinwen Hou, Yu Liu
To explicitly encourage exploration in continuous control tasks, we propose CCEP (Centralized Cooperative Exploration Policy), which utilizes underestimation and overestimation of value functions to maintain the capacity of exploration.
1 code implementation • 26 Feb 2021 • Yu Liu, Fan Yang, Dominique Ginhac
Interpreting human actions requires understanding the spatial and temporal context of the scenes.
1 code implementation • IEEE ROBOTICS AND AUTOMATION LETTERS 2023 • Weimin WANG, Ting Yang, Yu Du, Yu Liu
The proposed approach first constructs the CRF based on k-nearest neighbors with the snow confidence derived from the physical priors of snow, such as intensity and distribution.
1 code implementation • 7 Feb 2024 • Jinwei Zeng, Yu Liu, Jingtao Ding, Jian Yuan, Yong Li
To relieve this issue by utilizing the strong pattern recognition of artificial intelligence, we incorporate two sources of open data representative of the transportation demand and capacity factors, the origin-destination (OD) flow data and the road network data, to build a hierarchical heterogeneous graph learning method for on-road carbon emission estimation (HENCE).
no code implementations • CVPR 2018 • Guanglu Song, Yu Liu, Ming Jiang, Yujie Wang, Junjie Yan, Biao Leng
Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone.
no code implementations • 18 Nov 2017 • Huaxin Xiao, Yunchao Wei, Yu Liu, Maojun Zhang, Jiashi Feng
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations.
no code implementations • CVPR 2018 • Yu Liu, Fangyin Wei, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification.
no code implementations • 23 Nov 2017 • Guanglu Song, Biao Leng, Yu Liu, Congrui Hetang, Shaofan Cai
One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination.
no code implementations • 29 Jul 2017 • Yu Liu, Hantian Zhang, Luyuan Zeng, Wentao Wu, Ce Zhang
We then compare the performance of the top winning code available from Kaggle with that of running machine learning clouds from both Azure and Amazon on mlbench.
no code implementations • CVPR 2017 • Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan, Xiu Li, Xiaolin Hu
Then the scale histogram guides the zoom-in and zoom-out of the image.
no code implementations • NeurIPS 2017 • Yu Liu, Jianshu Chen, Li Deng
Although it is harder to optimize in its functional form, a stochastic primal-dual gradient method is developed to effectively solve the problem.
no code implementations • NeurIPS 2016 • Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu
Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.
no code implementations • 16 Nov 2016 • Yu Liu, Yanming Guo, Michael S. Lew
Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules.
no code implementations • 19 Oct 2016 • Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan
In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.
no code implementations • 2 Jun 2016 • Yu Liu, Jianlong Fu, Tao Mei, Chang Wen Chen
Second, by using sGRU as basic units, the BMRNN is trained to align the local storylines into the global sequential timeline.
no code implementations • 4 Aug 2014 • Yu Liu, Osvaldo Simeone, Alexander M. Haimovich, Wei Su
A novel Bayesian modulation classification scheme is proposed for a single-antenna system over frequency-selective fading channels.
no code implementations • 11 Aug 2018 • Kai Wang, Yu Liu, Xiujuan Xu, Dan Lin
Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space.
no code implementations • 19 Nov 2018 • Jinwei Zhao, Qizhou Wang, YuFei Wang, Xinhong Hei, Yu Liu
In other words, there is a gap between the deep learning model and the cognitive mode.
no code implementations • 24 Nov 2018 • Haokui Zhang, Ying Li, Peng Wang, Yu Liu, Chunhua Shen
Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition.
no code implementations • 21 Nov 2018 • Jinwei Zhao, Qizhou Wang, YuFei Wang, Yu Liu, Zhenghao Shi, Xinhong Hei
In this paper, a quantitative index of the interpretability is proposed and its rationality is proved, and equilibrium problem between the interpretability and the generalization performance is analyzed.
no code implementations • NeurIPS 2018 • Yu Liu, Kris De Brabanter
We propose a nonparametric derivative estimation method for random design without having to estimate the regression function.
no code implementations • CVPR 2018 • Xingping Dong, Jianbing Shen, Wenguan Wang, Yu Liu, Ling Shao, Fatih Porikli
Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process.
no code implementations • CVPR 2018 • Huaxin Xiao, Jiashi Feng, Guosheng Lin, Yu Liu, Maojun Zhang
In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i. e., frame representation learning and segmentation refinement.
no code implementations • ECCV 2018 • Yu Liu, Guanglu Song, Jing Shao, Xiao Jin, Xiaogang Wang
It is inspired by the observation of the weights in classification layer (called extit{anchors}) converge to the central direction of each class in hyperspace.
no code implementations • 12 Jan 2019 • Yu Liu, Lingqiao Liu, Hamid Rezatofighi, Thanh-Toan Do, Qinfeng Shi, Ian Reid
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.
no code implementations • CVPR 2016 • Yu Liu, Michael S. Lew
We consider these false positives in the supervision, and are able to achieve high performance for better edge detection.
no code implementations • ICCV 2017 • Yu Liu, Yanming Guo, Erwin M. Bakker, Michael S. Lew
A major challenge in matching between vision and language is that they typically have completely different features and representations.
no code implementations • CVPR 2019 • Jie Li, Yu Liu, Dong Gong, Qinfeng Shi, Xia Yuan, Chunxia Zhao, Ian Reid
RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).
Ranked #19 on 3D Semantic Scene Completion on NYUv2
no code implementations • CVPR 2019 • Rui Liu, Yu Liu, Xinyu Gong, Xiaogang Wang, Hongsheng Li
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions.
no code implementations • 6 May 2019 • Yuhao Kang, Qingyuan Jia, Song Gao, Xiaohuan Zeng, Yueyao Wang, Stephan Angsuesser, Yu Liu, Xinyue Ye, Teng Fei
In this study, a novel framework for extracting human emotions from large-scale georeferenced photos at different places is proposed.
no code implementations • 6 Jun 2019 • Yu Liu, Li Deng, Jianshu Chen, Chang Wen Chen
To remove the need for the parallel training corpora has practical significance for real-world applications, and it is one of the main goals of unsupervised learning.
no code implementations • 3 Jul 2019 • Rafael S. Gonçalves, Matthew Horridge, Rui Li, Yu Liu, Mark A. Musen, Csongor I. Nyulas, Evelyn Obamos, Dhananjay Shrouty, David Temple
In this paper, we present the engineering of an OWL ontology---the Pinterest Taxonomy---that forms the core of Pinterest's knowledge graph, the Pinterest Taste Graph.
no code implementations • ICCV 2019 • Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin, Yu Liu, Thanh-Toan Do, Ian Reid
Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.
no code implementations • 5 Aug 2019 • Weichang Wu, Huanxi Liu, Xiaohu Zhang, Yu Liu, Hongyuan Zha
Temporal point process is widely used for sequential data modeling.
no code implementations • 19 Aug 2019 • Yu Liu, Yutong Dai, Anh-Dzung Doan, Lingqiao Liu, Ian Reid
Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i. e. online fine-tuning on the target instance.
no code implementations • 10 Sep 2019 • Changqing Xu, Wenrui Zhang, Yu Liu, Peng Li
Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15. 93x, 13. 88x, and 86. 21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA.
no code implementations • 28 Sep 2019 • Yu Liu, Lingqiao Liu, Haokui Zhang, Hamid Rezatofighi, Ian Reid
This paper tackles the problem of video object segmentation.
no code implementations • 9 Oct 2019 • Yinglong Wang, Haokui Zhang, Yu Liu, Qinfeng Shi, Bing Zeng
However, the existing methods usually do not have good generalization ability, which leads to the fact that almost all of existing methods have a satisfied performance on removing a specific type of rain streaks, but may have a relatively poor performance on other types of rain streaks.
no code implementations • 21 Oct 2019 • Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, YuFei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, Xinhong Hei
The reason is, we believe that: the network is essentially a perceptual model.
no code implementations • ICCV 2019 • Yu Liu, Jihao Liu, Ailing Zeng, Xiaogang Wang
This paper proposes a differentiable kernel evolution (DKE) algorithm to find a better layer-operator for the convolutional neural network.
no code implementations • CVPR 2020 • Yu Liu, Xuhui Jia, Mingxing Tan, Raviteja Vemulapalli, Yukun Zhu, Bradley Green, Xiaogang Wang
Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture.
no code implementations • 17 Feb 2020 • Yu Liu, Jie Li, Qingsen Yan, Xia Yuan, Chunxia Zhao, Ian Reid, Cesar Cadena
This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.
Ranked #14 on 3D Semantic Scene Completion on NYUv2
no code implementations • 17 Mar 2020 • Guanglu Song, Yu Liu, Yuhang Zang, Xiaogang Wang, Biao Leng, Qingsheng Yuan
The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors.
no code implementations • 8 Apr 2020 • Xiao Jiang, Gang Li, Yu Liu, Xiao-Ping Zhang, You He
To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST).
no code implementations • 20 Jul 2020 • Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang, Manyuan Zhang, Wei Wu, Yu Liu, Hongsheng Li, Junjie Yan
Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.
no code implementations • ECCV 2020 • Manyuan Zhang, Guanglu Song, Hang Zhou, Yu Liu
We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set.
no code implementations • 17 Sep 2020 • Shen Yan, Yang Pen, Shiming Lai, Yu Liu, Maojun Zhang
Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall.
no code implementations • 18 Sep 2020 • Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic, Yu Liu, Luc van Gool, Matthew Blaschko, Tinne Tuytelaars, Marie-Francine Moens
In this work, we deviate from recent, popular task settings and consider the problem under an autonomous vehicle scenario.
Ranked #3 on Referring Expression Comprehension on Talk2Car
no code implementations • 1 Jan 2021 • Jihao Liu, Yangting Sun, Ming Zhang, Boxiao Liu, Yu Liu
Further, a life-long knowledge pool together with a block similarity function is proposed to utilize the lifelong parameter knowledge and reduces the searching time by 2 times.
no code implementations • 1 Jan 2021 • Hao Shao, Yu Liu, Hongsheng Li
Inspired by spatial-based contrastive SSL, we show that significant improvement can be achieved by a proposed temporal-based contrastive learning approach, which includes three novel and efficient modules: temporal augmentations, temporal memory bank and SSTL loss.
no code implementations • 16 Jul 2014 • Chaogui Kang, Yu Liu, Lun Wu
Travel activities have been widely applied to quantify spatial interactions between places, regions and nations.
Physics and Society Social and Information Networks
no code implementations • 14 Oct 2020 • Kai Wang, Yu Liu, Qian Ma, Quan Z. Sheng
Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs).
no code implementations • 12 Jan 2018 • Yu Liu
This paper is a follow-up work about the artificial ecosystem model: number soup (Liu and Sumpter, J. Royal Soc.
no code implementations • 12 Nov 2020 • Chun-Xiao Liu, Sergej Schuwalow, Yu Liu, Kostas Vilkelis, A. L. R. Manesco, P. Krogstrup, Michael Wimmer
We study the electronic properties of InAs/EuS/Al heterostructures as explored in a recent experiment [S. Vaitiekenas \emph{et al.}, Nat.
Mesoscale and Nanoscale Physics
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 • 9 Dec 2020 • Zhixiang Hu, Qianheng Du, Yu Liu, D. Graf, C. Petrovic
We report quantum oscillation measurements of LaAlGe, a Lorentz-violating type-II Weyl semimetal with tilted Weyl cones.
Mesoscale and Nanoscale Physics Materials Science
no code implementations • 31 Dec 2020 • Yu Liu, Ming-Guang Hu, Matthew A. Nichols, Dongzheng Yang, Daiqian Xie, Hua Guo, Kang-Kuen Ni
Chemical reactions represent a class of quantum problems that challenge both the current theoretical understanding and computational capabilities.
Chemical Physics Atomic Physics Quantum Physics
no code implementations • 27 Jan 2021 • Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
no code implementations • 9 Feb 2021 • Yu Liu, Lianghua Huang, Pan Pan, Bin Wang, Yinghui Xu, Rong Jin
However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.
no code implementations • Findings (EMNLP) 2021 • Kai Wang, Yu Liu, Dan Lin, Quan Z. Sheng
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space.
no code implementations • 7 Aug 2020 • Hui Li, Qianhui Huang, Yu Liu, Lana X Garmire
Human placenta is a complex and heterogeneous organ interfacing between the mother and the fetus that supports fetal development.
no code implementations • 11 Apr 2021 • Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy.
no code implementations • 25 Apr 2021 • Jinglin Sun, Zhipeng Wu, Han Wang, Peiguang Jing, Yu Liu
However, most current eye trackers focus on 2D point of gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3D displays, we propose a novel binocular eye tracking device with stereo stimuli to provide highly accurate 3D PoG estimation.
no code implementations • 25 May 2021 • Jihao Liu, Ming Zhang, Yangting Sun, Boxiao Liu, Guanglu Song, Yu Liu, Hongsheng Li
Further, an architecture knowledge pool together with a block similarity function is proposed to utilize parameter knowledge and reduces the searching time by 2 times.
no code implementations • 30 Jun 2021 • Haifeng Li, Jun Cao, Jiawei Zhu, Yu Liu, Qing Zhu, Guohua Wu
And we propose Curvature Graph Neural Network (CGNN), which effectively improves the adaptive locality ability of GNNs by leveraging the structural property of graph curvature.
no code implementations • CVPR 2021 • Liuyihan Song, Kang Zhao, Pan Pan, Yu Liu, Yingya Zhang, Yinghui Xu, Rong Jin
Different from all of them, we regard large and small gradients selection as the exploitation and exploration of gradient information, respectively.
no code implementations • 27 Jul 2021 • Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
no code implementations • 9 Aug 2021 • Chi Zhang, Xiaoning Ma, Yu Liu, Le Wang, Yuanqi SU, Yuehu Liu
Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes.
no code implementations • 10 Aug 2021 • Ting Pan, Jizhong Duan, Junfeng Wang, Yu Liu
Recent methods have exploited the nonlocal self-similarity (NSS) of images by imposing nonlocal low-rankness of similar patches to achieve a superior performance.
no code implementations • 15 Aug 2021 • Shuhui Gong, Xiaopeng Mo, Rui Cao, Yu Liu, Wei Tu, Ruibin Bai
Parking demand forecasting and behaviour analysis have received increasing attention in recent years because of their critical role in mitigating traffic congestion and understanding travel behaviours.
no code implementations • 22 Sep 2021 • Xiaoyu Chen, Chen Gong, Qiang He, Xinwen Hou, Yu Liu
Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications.
no code implementations • 24 Sep 2021 • Chen Gong, Qiang He, Yunpeng Bai, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie Zhang, Yu Liu, Guoliang Fan
In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.
no code implementations • ICCV 2021 • Boxiao Liu, Guanglu Song, Manyuan Zhang, Haihang You, Yu Liu
When collaborated with the popular ArcFace on million-level data representation learning, we found that the switchable manner in SKH can effectively eliminate the gradient conflict generated by real-world label noise on a single K-class hyperplane.
no code implementations • 8 Oct 2021 • Jihao Liu, Hongsheng Li, Guanglu Song, Xin Huang, Yu Liu
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks.
Ranked #239 on Image Classification on ImageNet
no code implementations • 29 Sep 2021 • Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
no code implementations • 13 Oct 2021 • Zhiming Liu, Xuefei Zhang, Chongyang Liu, Hao Wang, Chao Sun, Bin Li, Weifeng Sun, Pu Huang, Qingjun Li, Yu Liu, Haipeng Kuang, Jihong Xiu
To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.
no code implementations • 1 Nov 2021 • Yu Liu, Jingtao Ding, Yong Li
Specifically, motivated by distilled knowledge and rich semantics in KG, we firstly construct an urban KG (UrbanKG) with cities' key elements and semantic relationships captured.
no code implementations • EMNLP 2021 • Kangli Zi, Shi Wang, Yu Liu, Jicun Li, Yanan Cao, Cungen Cao
Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English.
no code implementations • 1 Nov 2021 • Huandong Wang, Qiaohong Yu, Yu Liu, Depeng Jin, Yong Li
Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers temporal dynamics of the mobility patterns and utilizes PoI categories as the auxiliary information and background knowledge.
no code implementations • 16 Nov 2021 • Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
no code implementations • 21 Nov 2021 • Jian Peng, Xian Sun, Min Deng, Chao Tao, Bo Tang, Wenbo Li, Guohua Wu, QingZhu, Yu Liu, Tao Lin, Haifeng Li
This paper presents a learning model by active forgetting mechanism with artificial neural networks.
no code implementations • 23 Nov 2021 • Yifan Chang, Wenbo Li, Jian Peng, Bo Tang, Yu Kang, Yinjie Lei, Yuanmiao Gui, Qing Zhu, Yu Liu, Haifeng Li
Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.
no code implementations • 24 Nov 2021 • Yu Liu, Mingbo Zhao, Zhao Zhang, Haijun Zhang, Shuicheng Yan
Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person.
no code implementations • 23 Nov 2021 • Thomas Richardson, Yu Liu, James McQueen, Doug Hains
Given observations on the number of unique users participating in an initial period, we present a simple but novel Bayesian method for predicting the number of additional individuals who will participate during a subsequent period.
no code implementations • 28 Nov 2021 • Yu Liu, Sheng Hong, Cunhua Pan, Yinlu Wang, Yijin Pan, Ming Chen
Reconfigurable intelligent surface (RIS) is a promising technology for future millimeter-wave (mmWave) communication systems.
no code implementations • 4 Dec 2021 • Jian Peng, Dingqi Ye, Bo Tang, Yinjie Lei, Yu Liu, Haifeng Li
This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.
no code implementations • 22 Dec 2021 • Qingyuan Gong, Yu Liu, Liqiang Zhang, Renhe Liu
Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance.
no code implementations • 3 Jan 2022 • Kai Wang, Yu Liu, Quan Z. Sheng
Knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks.
no code implementations • 24 Jan 2022 • Liqiang Zhang, Kai Guo, Yu Liu
Kalman filter-based Inertial Navigation System (INS) is a reliable and efficient method to estimate the position of a pedestrian indoors.
no code implementations • ICCV 2021 • Boxiao Liu, Shenghan Zhang, Guanglu Song, Haihang You, Yu Liu
In this paper, we first quantitatively define the uniformity of the sampled data for training, providing a unified view for methods that learn from biased data.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
no code implementations • 16 Feb 2022 • Jihao Liu, Boxiao Liu, Hongsheng Li, Yu Liu
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations.
Ranked #135 on Image Classification on ImageNet
no code implementations • 11 Mar 2022 • Xiaohan Liu, Yanwei Pang, Ruiqi Jin, Yu Liu, ZhenChang Wang
Purpose: To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data.
no code implementations • 17 May 2022 • Yuhao Mo, Chu Han, Yu Liu, Min Liu, Zhenwei Shi, Jiatai Lin, Bingchao Zhao, Chunwang Huang, Bingjiang Qiu, Yanfen Cui, Lei Wu, Xipeng Pan, Zeyan Xu, Xiaomei Huang, Zaiyi Liu, Ying Wang, Changhong Liang
In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.
no code implementations • 28 May 2022 • Kai Hu, Yu Liu, Renhe Liu, Wei Lu, Gang Yu, Bin Fu
In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy.
no code implementations • 27 Jun 2022 • Yu Liu, Kurt Weiss, Nassir Navab, Carsten Marr, Jan Huisken, Tingying Peng
Light-sheet fluorescence microscopy (LSFM) is a cutting-edge volumetric imaging technique that allows for three-dimensional imaging of mesoscopic samples with decoupled illumination and detection paths.
no code implementations • 8 Aug 2022 • Bingqi Ma, Guanglu Song, Boxiao Liu, Yu Liu
To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities|K^C-clusters.
no code implementations • 29 Aug 2022 • Manyuan Zhang, Guanglu Song, Yu Liu, Hongsheng Li
To eliminate the bias of single-aspect research and provide an overall understanding of the face recognition model design, we first carefully design the search space for each aspect, then a comprehensive search method is introduced to jointly search optimal data cleaning, architecture, and loss function design.
no code implementations • 8 Sep 2022 • Yu Liu, Hao Zhao, Rencheng Song, Xudong Chen, Chang Li, Xun Chen
The final output of the SOM-Net is the full predicted induced current, from which the scattered field and the permittivity image can also be deduced analytically.
no code implementations • IEEE Sensors Journal 2022 • Chang Li, Xuejuan Lin, Yu Liu, Rencheng Song, Juan Cheng, Xun Chen
To achieve a simple and effective model with supervised learning, we propose an efficient CNN and contrastive learning (ECNN-C) method for EEG-based emotion recognition.
no code implementations • 16 Oct 2022 • Yueqin Yin, Lianghua Huang, Yu Liu, Kaiqi Huang
In this work, we first design a group of mechanisms to simulate generative artifacts of popular generators (i. e., GANs, autoregressive models, and diffusion models), given real images.
no code implementations • 3 Nov 2022 • Yuan Hu, Zhibin Wang, Zhou Huang, Yu Liu
Given a set of polygon queries, the model learns the relations among them and encodes context information from the image to predict the final set of building polygons with fixed vertex numbers.
no code implementations • 7 Nov 2022 • Yu Liu, Ming Chen, Cunhua Pan, Yijin Pan, Yinlu Wang, Yaoming Huang, Tianyang Cao, Jiangzhou Wang
The emerging reconfigurable intelligent surface (RIS) technology is promising for applications in the millimeter wave (mmWave) communication systems to effectively compensate for propagation loss or tackle the blockage issue.
no code implementations • 19 Nov 2022 • Xiang Wang, Yimin Yang, Zhichang Guo, Zhili Zhou, Yu Liu, Qixiang Pang, Shan Du
First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain.
no code implementations • 18 Nov 2022 • Xiang Wang, Yimin Yang, Qixiang Pang, Xiao Lu, Yu Liu, Shan Du
In this paper, we propose a novel face super-resolution method, namely Semantic Encoder guided Generative Adversarial Face Ultra-Resolution Network (SEGA-FURN) to ultra-resolve an unaligned tiny LR face image to its HR counterpart with multiple ultra-upscaling factors (e. g., 4x and 8x).
no code implementations • 22 Nov 2022 • Siyu Xing, Chen Gong, Hewei Guo, Xiao-Yu Zhang, Xinwen Hou, Yu Liu
In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing.