no code implementations • 26 Sep 2023 • Qiao Yang, Yu Zhang, Jian Zhang, Zijing Zhao, Shunli Zhang, Jinqiao Wang, Junzhe Chen
Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i. e., yielding edge-blurring effect or unrecognizable for object detectors.
no code implementations • 26 Sep 2023 • Qiao Yang, Yu Zhang, Jian Zhang, Zijing Zhao, Shunli Zhang, Jinqiao Wang, Junzhe Chen
Infrared and visible image fusion (IVIF) is used to generate fusion images with comprehensive features of both images, which is beneficial for downstream vision tasks.
no code implementations • 21 Sep 2023 • Xiaozhou You, Jian Zhang
Text-guided image generation aimed to generate desired images conditioned on given texts, while text-guided image manipulation refers to semantically edit parts of a given image based on specified texts.
no code implementations • 12 Sep 2023 • Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao
Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape.
no code implementations • 5 Sep 2023 • Shunyang Zhang, Senzhang Wang, Xianzhen Tan, Ruochen Liu, Jian Zhang, Jianxin Wang
Spatial time series imputation is critically important to many real applications such as intelligent transportation and air quality monitoring.
1 code implementation • 26 Aug 2023 • Bin Chen, Xuanyu Zhang, Shuai Liu, Yongbing Zhang, Jian Zhang
Compressed sensing (CS) is a promising tool for reducing sampling costs.
no code implementations • 22 Aug 2023 • Wenbo Xu, Huaxi Huang, Ming Cheng, Litao Yu, Qiang Wu, Jian Zhang
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images.
Ranked #24 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
1 code implementation • ICCV 2023 • Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao
To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test.
no code implementations • 18 Aug 2023 • Shuzhou Yang, Xuanyu Zhang, Yinhuai Wang, Jiwen Yu, YuHan Wang, Jian Zhang
Specifically, we adopt a naive unsupervised enhancement algorithm to realize preliminary restoration and design two zero-shot plug-and-play modules based on diffusion model to improve generalization and effectiveness.
1 code implementation • ICCV 2023 • Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi
Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains.
no code implementations • 27 Jul 2023 • Bo Yang, Xinyu Zhang, Jiahao Zhu, Jian Zhang, Dongjian Tian, Jun Luo, Mingliang Zhou, Yangjun Pi
Single-frame infrared small target detection is considered to be a challenging task, due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small targets, and small target information is easy to lose in the high-level semantic layer.
1 code implementation • 18 Jul 2023 • Bin Chen, Jiechong Song, Jingfen Xie, Jian Zhang
By absorbing the merits of both the model- and data-driven methods, deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction.
1 code implementation • 11 Jul 2023 • Jian Zhang, Runwei Ding, Miaoju Ban, Ge Yang
It follows the unsupervised setting and only normal (defect-free) images are used for training.
1 code implementation • 5 Jul 2023 • Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang
Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model.
1 code implementation • 30 Jun 2023 • Zhuchen Shao, Yang Chen, Hao Bian, Jian Zhang, Guojun Liu, Yongbing Zhang
Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag.
1 code implementation • 28 Jun 2023 • Jiechong Song, Bin Chen, Jian Zhang
Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance.
no code implementations • 15 Jun 2023 • Zhili He, Wang Chen, Jian Zhang, Yu-Hsing Wang
Cracks provide an essential indicator of infrastructure performance degradation, and achieving high-precision pixel-level crack segmentation is an issue of concern.
1 code implementation • 26 May 2023 • Jiwen Yu, Xuanyu Zhang, Youmin Xu, Jian Zhang
Current image steganography techniques are mainly focused on cover-based methods, which commonly have the risk of leaking secret images and poor robustness against degraded container images.
1 code implementation • 25 May 2023 • Qiantong Xu, Fenglu Hong, Bo Li, Changran Hu, Zhengyu Chen, Jian Zhang
In this paper, we ask can we enhance open-source LLMs to be competitive to leading closed LLM APIs in tool manipulation, with practical amount of human supervision.
no code implementations • 23 May 2023 • Xiaoshui Huang, Guofeng Mei, Jian Zhang
The emerging topic of cross-source point cloud (CSPC) registration has attracted increasing attention with the fast development background of 3D sensor technologies.
no code implementations • 12 May 2023 • Yanmin Wu, Yunzhou Zhang, Delong Zhu, Zhiqiang Deng, Wenkai Sun, Xin Chen, Jian Zhang
Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching.
no code implementations • 4 May 2023 • Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan
Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios.
1 code implementation • Tiny Papers @ ICLR 2023 • Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You
We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.
Ranked #1 on
Dialog Relation Extraction
on DialogRE
1 code implementation • CVPR 2023 • Jiechong Song, Chong Mou, Shiqi Wang, Siwei Ma, Jian Zhang
And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block.
no code implementations • 26 Apr 2023 • Xiaopeng Sun, Weiqi Li, Zhenyu Zhang, Qiufang Ma, Xuhan Sheng, Ming Cheng, Haoyu Ma, Shijie Zhao, Jian Zhang, Junlin Li, Li Zhang
Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images.
1 code implementation • CVPR 2023 • Chong Mou, Youmin Xu, Jiechong Song, Chen Zhao, Bernard Ghanem, Jian Zhang
For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN).
1 code implementation • CVPR 2023 • Guofeng Mei, Hao Tang, Xiaoshui Huang, Weijie Wang, Juan Liu, Jian Zhang, Luc van Gool, Qiang Wu
Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data.
1 code implementation • ICCV 2023 • Shuzhou Yang, Moxuan Ding, Yanmin Wu, Zihan Li, Jian Zhang
Finally, extensive experiments demonstrate the robustness and superior effectiveness of our proposed NeRCo.
1 code implementation • ICCV 2023 • Qiankun Gao, Chen Zhao, Yifan Sun, Teng Xi, Gang Zhang, Bernard Ghanem, Jian Zhang
1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble.
no code implementations • 17 Mar 2023 • Xuanyu Zhang, Bin Chen, Wenzhen Zou, Shuai Liu, Yongbing Zhang, Ruiqin Xiong, Jian Zhang
Hyperspectral imaging plays a pivotal role in a wide range of applications, like remote sensing, medicine, and cytology.
1 code implementation • ICCV 2023 • Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, Jian Zhang
In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions.
1 code implementation • 1 Mar 2023 • Yinhuai Wang, Jiwen Yu, Runyi Yu, Jian Zhang
Our simple, parameter-free approaches can be used not only for image restoration but also for image generation of unlimited sizes, with the potential to be a general tool for diffusion models.
2 code implementations • 16 Feb 2023 • Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, XiaoHu Qie
In this paper, we aim to ``dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly.
no code implementations • 26 Jan 2023 • Chuang Zhao, Hongke Zhao, Ming He, Jian Zhang, Jianping Fan
Specifically, we first construct a unified cross-domain heterogeneous graph and redefine the message passing mechanism of graph convolutional networks to capture high-order similarity of users and items across domains.
1 code implementation • 8 Jan 2023 • Fangzhi Xu, Jun Liu, Qika Lin, Tianzhe Zhao, Jian Zhang, Lingling Zhang
(2) How to enhance the perception of reasoning types for the models?
no code implementations • ICCV 2023 • Wenjie Wei, Malu Zhang, Hong Qu, Ammar Belatreche, Jian Zhang, Hong Chen
As a temporal encoding scheme for SNNs, Time-To-First-Spike (TTFS) encodes information using the timing of a single spike, which allows spiking neurons to transmit information through sparse spike trains and results in lower power consumption and higher computational efficiency compared to traditional rate-based encoding counterparts.
no code implementations • CVPR 2023 • Xinhua Cheng, Yanmin Wu, Mengxi Jia, Qian Wang, Jian Zhang
In this work, we attempt to learn an object-compositional neural implicit representation for editable scene rendering by leveraging labels inferred from the off-the-shelf 2D panoptic segmentation networks instead of the ground truth annotations.
no code implementations • 17 Dec 2022 • Yongshun Gong, Xue Dong, Jian Zhang, Meng Chen
Our method focuses on learning the low-dimensional representations of networks and capturing the evolving patterns of these learned latent representations simultaneously.
1 code implementation • 10 Dec 2022 • Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Yian Zhao, Jian Zhang, Guoli Song, Jie Chen
By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.
no code implementations • 9 Dec 2022 • So Yeon Min, Yao-Hung Hubert Tsai, Wei Ding, Ali Farhadi, Ruslan Salakhutdinov, Yonatan Bisk, Jian Zhang
In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.
2 code implementations • 1 Dec 2022 • Yinhuai Wang, Jiwen Yu, Jian Zhang
Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.
Ranked #1 on
Image Deblurring
on CelebA
1 code implementation • 24 Nov 2022 • Yinhuai Wang, Yujie Hu, Jiwen Yu, Jian Zhang
Consistency and realness have always been the two critical issues of image super-resolution.
no code implementations • 19 Nov 2022 • Zhongnian Li, Jian Zhang, Mengting Xu, Xinzheng Xu, Daoqiang Zhang
In this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase.
1 code implementation • 9 Nov 2022 • Jie Wu, Ying Peng, Shengming Zhang, Weigang Qi, Jian Zhang
MVLT is trained in two stages: in the first stage, we design a STR-tailored pretraining method based on a masking strategy; in the second stage, we fine-tune our model and adopt an iterative correction method to improve the performance.
1 code implementation • 17 Oct 2022 • Guofeng Mei, Fabio Poiesi, Cristiano Saltori, Jian Zhang, Elisa Ricci, Nicu Sebe
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations.
no code implementations • CVPR 2023 • Zhaozhi Wang, Kefan Su, Jian Zhang, Huizhu Jia, Qixiang Ye, Xiaodong Xie, Zongqing Lu
In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML).
1 code implementation • 6 Oct 2022 • Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Jian Zhang, Elisa Ricci, Nicu Sebe, Qiang Wu
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.
2 code implementations • CVPR 2023 • Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang
3D visual grounding aims to find the object within point clouds mentioned by free-form natural language descriptions with rich semantic cues.
no code implementations • 27 Sep 2022 • Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi, Jian Zhang
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc.
no code implementations • 23 Sep 2022 • Mario Srouji, Hugues Thomas, Hubert Tsai, Ali Farhadi, Jian Zhang
Collision avoidance is key for mobile robots and agents to operate safely in the real world.
no code implementations • 27 Jul 2022 • Weiqi Li, Bin Chen, Jian Zhang
By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) for CS imaging with the capability of transmitting high-throughput feature-level image representation through all the unfolded stages.
1 code implementation • 25 Jul 2022 • Chong Mou, Jian Zhang
Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements.
no code implementations • 24 Jul 2022 • Litao Yu, Jian Zhang, Mohammed Bennamoun, Xiaojun Chang, Vute Sirivivatnanon, Ali Nezhad
Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections.
1 code implementation • 19 Jul 2022 • Bin Chen, Jian Zhang
To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction.
Ranked #1 on
Image Compressed Sensing
on CBSD68
1 code implementation • 12 Jul 2022 • Yuyang Long, Qilong Zhang, Boheng Zeng, Lianli Gao, Xianglong Liu, Jian Zhang, Jingkuan Song
Specifically, we apply a spectrum transformation to the input and thus perform the model augmentation in the frequency domain.
no code implementations • 10 Jul 2022 • Litao Yu, Jian Zhang
Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies.
1 code implementation • 10 Jul 2022 • Litao Yu, Zhibin Li, Jian Zhang, Qiang Wu
Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.
1 code implementation • ICLR 2020 • Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, Ming-Chang Yang
Graph neural networks (GNNs) have been widely used for representation learning on graph data.
1 code implementation • 26 Jun 2022 • Hao Bian, Zhuchen Shao, Yang Chen, Yifeng Wang, Haoqian Wang, Jian Zhang, Yongbing Zhang
We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level.
no code implementations • 24 Jun 2022 • Xia Jiang, Jian Zhang, Xiaoyu Shi, Jian Cheng
Meanwhile, the simulation results demonstrate the effectiveness of the delay reward, which is designed to outperform distributed reward mechanism} Compared with normal car-following behavior, the sensitivity analysis reveals that the energy can be saved to different extends (39. 27%-82. 51%) by adjusting the relative importance of the optimization goal.
no code implementations • 24 Jun 2022 • Xia Jiang, Jian Zhang, Dan Li
This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections.
no code implementations • 21 Jun 2022 • Yi Cui, Wenfeng Shen, Jian Zhang, Weijia Lu, Chuang Liu, Lin Sun, Si Chen
The generator in IDS-EBGAN is responsible for converting the original malicious network traffic in the training set into adversarial malicious examples.
no code implementations • 7 Jun 2022 • Yuqing Liu, Qi Jia, Jian Zhang, Xin Fan, Shanshe Wang, Siwei Ma, Wen Gao
As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years.
no code implementations • CVPR 2022 • Jian Zhang, Yuanqing Zhang, Huan Fu, Xiaowei Zhou, Bowen Cai, Jinchi Huang, Rongfei Jia, Binqiang Zhao, Xing Tang
Neural Radiance Fields (NeRF) have emerged as a potent paradigm for representing scenes and synthesizing photo-realistic images.
1 code implementation • 10 May 2022 • Chong Mou, Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang, Ying Shan
Instead of using known degradation levels as explicit supervision to the interactive mechanism, we propose a metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner.
1 code implementation • CVPR 2022 • Chong Mou, Qian Wang, Jian Zhang
Concretely, without loss of interpretability, we integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation.
1 code implementation • 26 Apr 2022 • Minghao Zhao, Le Wu, Yile Liang, Lei Chen, Jian Zhang, Qilin Deng, Kai Wang, Xudong Shen, Tangjie Lv, Runze Wu
While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?"
1 code implementation • 26 Apr 2022 • Yuqing Liu, Qi Jia, Jian Zhang, Xin Fan, Shanshe Wang, Siwei Ma, Wen Gao
Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth.
1 code implementation • 24 Apr 2022 • Jingfen Xie, Jian Zhang, Yongbing Zhang, Xiangyang Ji
Compressed Sensing MRI (CS-MRI) aims at reconstructing de-aliased images from sub-Nyquist sampling k-space data to accelerate MR Imaging, thus presenting two basic issues, i. e., where to sample and how to reconstruct.
1 code implementation • 24 Mar 2022 • Qiankun Gao, Chen Zhao, Bernard Ghanem, Jian Zhang
After RRL, the classification head is refined with global class-balanced classification loss to address the data imbalance issue as well as learn the decision boundaries between new and previous classes.
no code implementations • 21 Mar 2022 • Yuting Yang, Pei Huang, Juan Cao, Jintao Li, Yun Lin, Jin Song Dong, Feifei Ma, Jian Zhang
Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).
no code implementations • 18 Mar 2022 • Jin Huang, Lu Zhang, Yongshun Gong, Jian Zhang, Xiushan Nie, Yilong Yin
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos.
1 code implementation • 16 Mar 2022 • Yinhuai Wang, Yujie Hu, Jian Zhang
Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i. e.}, StyleGAN2) as GAN Prior.
1 code implementation • 10 Mar 2022 • Yinhuai Wang, Shuzhou Yang, Yujie Hu, Jian Zhang
Unlike the pinhole, the thin lens refracts rays of a scene point, so its imaging on the sensor plane is scattered as a circle of confusion (CoC).
no code implementations • 5 Feb 2022 • Guofeng Mei, Litao Yu, Qiang Wu, Jian Zhang, Mohammed Bennamoun
This paper proposes a general unsupervised approach, named \textbf{ConClu}, to perform the learning of point-wise and global features by jointly leveraging point-level clustering and instance-level contrasting.
no code implementations • 11 Jan 2022 • Yuting Yang, Pei Huang, Feifei Ma, Juan Cao, Meishan Zhang, Jian Zhang, Jintao Li
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.
no code implementations • CVPR 2022 • Youmin Xu, Chong Mou, Yujie Hu, Jingfen Xie, Jian Zhang
Previous image steganography methods are limited in hiding capacity and robustness, commonly vulnerable to distortion on container images such as Gaussian noise, Poisson noise, and lossy compression.
1 code implementation • CVPR 2022 • Xiyao Liu, Ziping Ma, Junxing Ma, Jian Zhang, Gerald Schaefer, Hui Fang
Conventional steganography approaches embed a secret message into a carrier for concealed communication but are prone to attack by recent advanced steganalysis tools.
1 code implementation • 31 Dec 2021 • Dongjie Ye, Zhangkai Ni, Hanli Wang, Jian Zhang, Shiqi Wang, Sam Kwong
The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery.
no code implementations • 29 Dec 2021 • Guofeng Mei, Xiaoshui Huang, Litao Yu, Jian Zhang, Mohammed Bennamoun
Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration.
1 code implementation • 23 Dec 2021 • Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao
Beyond the training stage, overfitting could also cause unstable prediction in the test stage.
1 code implementation • CVPR 2022 • Xuanyu Zhang, Yongbing Zhang, Ruiqin Xiong, Qilin Sun, Jian Zhang
Hyperspectral imaging is an essential imaging modality for a wide range of applications, especially in remote sensing, agriculture, and medicine.
no code implementations • 23 Nov 2021 • Xiaoshui Huang, Zongyi Xu, Guofeng Mei, Sheng Li, Jian Zhang, Yifan Zuo, Yucheng Wang
To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.
no code implementations • 15 Nov 2021 • Minghao Liu, Fuqi Jia, Pei Huang, Fan Zhang, Yuchen Sun, Shaowei Cai, Feifei Ma, Jian Zhang
With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning.
no code implementations • 29 Oct 2021 • Pei Huang, Yuting Yang, Minghao Liu, Fuqi Jia, Feifei Ma, Jian Zhang
This paper introduces a notation of $\varepsilon$-weakened robustness for analyzing the reliability and stability of deep neural networks (DNNs).
no code implementations • 26 Oct 2021 • Huichen Ma, Junjie Zhou, Jian Zhang, Lingyu Zhang
After training with sample data, the BP neural network model can represent the relation between the manipulator tip position and the pressure applied to the chambers.
1 code implementation • 19 Oct 2021 • Jiechong Song, Bin Chen, Jian Zhang
By understanding DUNs from the perspective of the human brain's memory processing, we find there exists two issues in existing DUNs.
1 code implementation • 17 Oct 2021 • Yinghuan Shi, Jian Zhang, Tong Ling, Jiwen Lu, Yefeng Zheng, Qian Yu, Lei Qi, Yang Gao
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
no code implementations • 8 Oct 2021 • Jinyin Chen, Haiyang Xiong, Haibin Zheng, Jian Zhang, Guodong Jiang, Yi Liu
Backdoor attacks induce the DLP methods to make wrong prediction by the malicious training data, i. e., generating a subgraph sequence as the trigger and embedding it to the training data.
no code implementations • 18 Sep 2021 • Cheng Tan, Zhichao Li, Jian Zhang, Yu Cao, Sikai Qi, Zherui Liu, Yibo Zhu, Chuanxiong Guo
With MIG, A100 can be the most cost-efficient GPU ever for serving Deep Neural Networks (DNNs).
1 code implementation • ICCV 2021 • Chong Mou, Jian Zhang, Zhuoyuan Wu
Specifically, we propose an improved graph model to perform patch-wise graph convolution with a dynamic and adaptive number of neighbors for each node.
1 code implementation • ICCV 2021 • Zhuoyuan Wu, Jian Zhang, Chong Mou
To better exploit the spatial-temporal correlation among frames and address the problem of information loss between adjacent phases in existing DUNs, we propose to adopt the 3D-CNN prior in our proximal mapping module and develop a novel dense feature map (DFM) strategy, respectively.
1 code implementation • ICCV 2021 • Zeren Sun, Yazhou Yao, Xiu-Shen Wei, Yongshun Zhang, Fumin Shen, Jianxin Wu, Jian Zhang, Heng-Tao Shen
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets.
no code implementations • 22 Jul 2021 • Ke-Yue Zhang, Taiping Yao, Jian Zhang, Shice Liu, Bangjie Yin, Shouhong Ding, Jilin Li
In pursuit of consolidating the face verification systems, prior face anti-spoofing studies excavate the hidden cues in original images to discriminate real persons and diverse attack types with the assistance of auxiliary supervision.
1 code implementation • 16 Jul 2021 • Jinyin Chen, Haiyang Xiong, Haibin Zhenga, Dunjie Zhang, Jian Zhang, Mingwei Jia, Yi Liu
To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness.
no code implementations • 15 Jul 2021 • Qing Chen, Jian Zhang
Most current applications of contrastive learning benefit only a single representation from the last layer of an encoder. In this paper, we propose a multi-level contrasitive learning approach which applies contrastive losses at different layers of an encoder to learn multiple representations from the encoder.
1 code implementation • 15 Jul 2021 • Di You, Jian Zhang, Jingfen Xie, Bin Chen, Siwei Ma
In this paper, we propose a novel COntrollable Arbitrary-Sampling neTwork, dubbed COAST, to solve CS problems of arbitrary-sampling matrices (including unseen sampling matrices) with one single model.
no code implementations • 6 Jul 2021 • Mengxi Jia, Xinhua Cheng, Shijian Lu, Jian Zhang
To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features.
no code implementations • CVPR 2021 • Jing Zhao, Ruiqin Xiong, Hangfan Liu, Jian Zhang, Tiejun Huang
Different from the conventional digital cameras that compact the photoelectric information within the exposure interval into a single snapshot, the spike camera produces a continuous spike stream to record the dynamic light intensity variation process.
2 code implementations • NeurIPS 2021 • Zhuchen Shao, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang, Xiangyang Ji, Yongbing Zhang
Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis.
no code implementations • 21 May 2021 • Yinglin Zhang, Risa Higashita, Huazhu Fu, Yanwu Xu, Yang Zhang, Haofeng Liu, Jian Zhang, Jiang Liu
Corneal endothelial cell segmentation plays a vital role inquantifying clinical indicators such as cell density, coefficient of variation, and hexagonality.
no code implementations • 18 May 2021 • Bofeng Wu, guocheng niu, Jun Yu, Xinyan Xiao, Jian Zhang, Hua Wu
This paper proposes an approach to Dense Video Captioning (DVC) without pairwise event-sentence annotation.
2 code implementations • 17 May 2021 • Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
no code implementations • 9 May 2021 • Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu
The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.
no code implementations • 26 Apr 2021 • Jie Chen, Jie Liu, Chang Liu, Jian Zhang, Bing Han
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
no code implementations • 26 Mar 2021 • Dewang Hou, Yang Zhao, Yuyao Ye, Jiayu Yang, Jian Zhang, Ronggang Wang
Scaling and lossy coding are widely used in video transmission and storage.
1 code implementation • CVPR 2021 • Yazhou Yao, Tao Chen, GuoSen Xie, Chuanyi Zhang, Fumin Shen, Qi Wu, Zhenmin Tang, Jian Zhang
To further mine the non-salient region objects, we propose to exert the segmentation network's self-correction ability.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
no code implementations • CVPR 2021 • Yazhou Yao, Zeren Sun, Chuanyi Zhang, Fumin Shen, Qi Wu, Jian Zhang, Zhenmin Tang
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance.
1 code implementation • 22 Mar 2021 • Di You, Jingfen Xie, Jian Zhang
While deep neural networks have achieved impressive success in image compressive sensing (CS), most of them lack flexibility when dealing with multi-ratio tasks and multi-scene images in practical applications.
no code implementations • 12 Mar 2021 • Jianhui Chang, Zhenghui Zhao, Lingbo Yang, Chuanmin Jia, Jian Zhang, Siwei Ma
To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis.
2 code implementations • 10 Mar 2021 • Chong Mou, Jian Zhang, Xiaopeng Fan, Hangfan Liu, Ronggang Wang
Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance.
no code implementations • 3 Mar 2021 • Xiaoshui Huang, Guofeng Mei, Jian Zhang, Rana Abbas
This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight.
no code implementations • 25 Feb 2021 • Shengran Lin, Changfeng Weng, Yuanjie Yang, Jiaxin Zhao, Yuhang Guo, Jian Zhang, Liren Lou, Wei Zhu, Guanzhong Wang
Nitrogen-vacancy (NV) center in diamond is an ideal candidate for quantum sensors because of its excellent optical and coherence property.
Quantum Physics Mesoscale and Nanoscale Physics
1 code implementation • 22 Feb 2021 • Tao Chen, GuoSen Xie, Yazhou Yao, Qiong Wang, Fumin Shen, Zhenmin Tang, Jian Zhang
Then we utilize the fused prototype to guide the final segmentation of the query image.
no code implementations • 16 Feb 2021 • Yunyi Xie, Jie Jin, Jian Zhang, Shanqing Yu, Qi Xuan
With the wide application of blockchain in the financial field, the rise of various types of cybercrimes has brought great challenges to the security of blockchain.
no code implementations • 1 Feb 2021 • Jian Zhang, Ying Tai, Taiping Yao, Jia Meng, Shouhong Ding, Chengjie Wang, Jilin Li, Feiyue Huang, Rongrong Ji
Face authentication on mobile end has been widely applied in various scenarios.
1 code implementation • 23 Jan 2021 • Huafeng Liu, Chuanyi Zhang, Yazhou Yao, Xiushen Wei, Fumin Shen, Jian Zhang, Zhenmin Tang
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators.
no code implementations • 1 Jan 2021 • Pedram Zamirai, Jian Zhang, Christopher R Aberger, Christopher De Sa
We ask can we do pure 16-bit training which requires only 16-bit compute units, while still matching the model accuracy attained by 32-bit training.
no code implementations • 1 Jan 2021 • Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
no code implementations • 1 Jan 2021 • Qing Chen, Jian Zhang
Deep neural networks (DNNs) compute representations in a layer by layer fashion, producing a final representation at the top layer of the pipeline, and classification or regression is made using the final representation.
no code implementations • ICCV 2021 • Jing Zhao, Jiyu Xie, Ruiqin Xiong, Jian Zhang, Zhaofei Yu, Tiejun Huang
In this paper, we properly exploit the relative motion and derive the relationship between light intensity and each spike, so as to recover the external scene with both high temporal and high spatial resolution.
no code implementations • 28 Dec 2020 • Jian Zhang, Cunjing Ge, Feifei Ma
Compared with constraint satisfaction problems, counting problems have received less attention.
no code implementations • 22 Dec 2020 • Yi Ding, Qiqi Yang, Guozheng Wu, Jian Zhang, Zhiguang Qin
In this paper, a network called Brachial Plexus Multi-instance Segmentation Network (BPMSegNet) is proposed to identify different tissues (nerves, arteries, veins, muscles) in ultrasound images.
no code implementations • 20 Dec 2020 • Huaxi Huang, Junjie Zhang, Jian Zhang, Qiang Wu, Chang Xu
Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning.
2 code implementations • 10 Dec 2020 • Hugues Thomas, Ben Agro, Mona Gridseth, Jian Zhang, Timothy D. Barfoot
We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
no code implementations • 9 Dec 2020 • Radu Horaud, Florence Forbes, Manuel Yguel, Guillaume Dewaele, Jian Zhang
This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration.
1 code implementation • NeurIPS 2020 • Zhibin Li, Jian Zhang, Yongshun Gong, Yazhou Yao, Qiang Wu
We present a model that utilizes linear models with variance and low-rank constraints, to help it generalize better and reduce the number of parameters.
no code implementations • 18 Nov 2020 • Jinyin Chen, Yunyi Xie, Jian Zhang, Xincheng Shu, Qi Xuan
In this paper, we introduce time-series snapshot network (TSSN) which is a mixture network to model the interactions among users and developers.
Social and Information Networks
2 code implementations • 10 Nov 2020 • Jianhui Chang, Zhenghui Zhao, Chuanmin Jia, Shiqi Wang, Lingbo Yang, Qi Mao, Jian Zhang, Siwei Ma
To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks.
no code implementations • 4 Nov 2020 • Litao Yu, Yongsheng Gao, Jun Zhou, Jian Zhang, Qiang Wu
The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information.
Ranked #39 on
Semantic Segmentation
on NYU Depth v2
1 code implementation • 3 Nov 2020 • Litao Yu, Yongsheng Gao, Jun Zhou, Jian Zhang
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.
no code implementations • 3 Nov 2020 • Zhibin Li, Litao Yu, Jian Zhang
In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound.
no code implementations • 2 Nov 2020 • Litao Yu, Jian Zhang, Qiang Wu
In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic correlations and improve the quality of generated sentences.
no code implementations • NeurIPS 2020 • Yikang Zhang, Jian Zhang, Zhao Zhong
Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS).
no code implementations • 20 Oct 2020 • Yunlu Wang, Cheng Yang, Menghan Hu, Jian Zhang, Qingli Li, Guangtao Zhai, Xiao-Ping Zhang
This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.
no code implementations • 13 Oct 2020 • Pedram Zamirai, Jian Zhang, Christopher R. Aberger, Christopher De Sa
State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy.
no code implementations • 9 Oct 2020 • Yuzhen Chen, Menghan Hu, Chunjun Hua, Guangtao Zhai, Jian Zhang, Qingli Li, Simon X. Yang
Aimed at solving the problem that we don't know which service stage of the mask belongs to, we propose a detection system based on the mobile phone.
1 code implementation • 6 Oct 2020 • Jialiang Shen, Yucheng Wang, Jian Zhang
For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels.
1 code implementation • 7 Sep 2020 • Rongzheng Bian, Yumeng Xue, Liang Zhou, Jian Zhang, Baoquan Chen, Daniel Weiskopf, Yunhai Wang
We propose a visualization method to understand the effect of multidimensional projection on local subspaces, using implicit function differentiation.
no code implementations • 7 Sep 2020 • Caiqing Jian, Xinyu Cheng, Jian Zhang, Lihui Wang
The experimental results demonstrate that, compared to the traditional chemical bond structure representations, the rotation and translation invariant structure representations proposed in this work can improve the SCC prediction accuracy; with the graph embedded local self-attention, the mean absolute error (MAE) of the prediction model in the validation set decreases from 0. 1603 Hz to 0. 1067 Hz; using the classification based loss function instead of the scaled regression loss, the MAE of the predicted SCC can be decreased to 0. 0963 HZ, which is close to the quantum chemistry standard on CHAMPS dataset.
no code implementations • 3 Sep 2020 • Bin Huang, Yuanyang Du, Shuai Zhang, Wenfei Li, Jun Wang, Jian Zhang
RNAs play crucial and versatile roles in biological processes.
no code implementations • ECCV 2020 • Ke-Yue Zhang, Taiping Yao, Jian Zhang, Ying Tai, Shouhong Ding, Jilin Li, Feiyue Huang, Haichuan Song, Lizhuang Ma
Face anti-spoofing is crucial to security of face recognition systems.
1 code implementation • 6 Aug 2020 • Zeren Sun, Xian-Sheng Hua, Yazhou Yao, Xiu-Shen Wei, Guosheng Hu, Jian Zhang
To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.
no code implementations • 3 Aug 2020 • Haoqiang Guo, Lu Peng, Jian Zhang, Fang Qi, Lide Duan
Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs.
no code implementations • 28 Jul 2020 • Baoyan Ma, Jian Zhang, Feng Cao, Yongjun He
We design a fixed proposal module to generate fixed-sized feature maps of nuclei, which allows the new information of nucleus is used for classification.
no code implementations • 3 Jul 2020 • Mengxi Jia, Yunpeng Zhai, Shijian Lu, Siwei Ma, Jian Zhang
RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities.
Cross-Modality Person Re-identification
Person Re-Identification
no code implementations • 27 Jun 2020 • Qian Li, Qingyuan Hu, Yong Qi, Saiyu Qi, Jie Ma, Jian Zhang
SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.
no code implementations • 18 Jun 2020 • Shuai Zhang, Xiaoyan Xin, Yang Wang, Yachong Guo, Qiuqiao Hao, Xianfeng Yang, Jun Wang, Jian Zhang, Bing Zhang, Wei Wang
The model provides automated recognition of given scans and generation of reports.
1 code implementation • 8 Jun 2020 • Guoji Fu, Yifan Hou, Jian Zhang, Kaili Ma, Barakeel Fanseu Kamhoua, James Cheng
This paper aims to provide a theoretical framework to understand GNNs, specifically, spectral graph convolutional networks and graph attention networks, from graph signal denoising perspectives.
no code implementations • 28 May 2020 • Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Qiang Wu, Chang Xu
The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i. e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS).
1 code implementation • 20 May 2020 • Yuqing Liu, Shiqi Wang, Jian Zhang, Shanshe Wang, Siwei Ma, Wen Gao
A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
no code implementations • ACL 2020 • Simran Arora, Avner May, Jian Zhang, Christopher Ré
We study the settings for which deep contextual embeddings (e. g., BERT) give large improvements in performance relative to classic pretrained embeddings (e. g., GloVe), and an even simpler baseline---random word embeddings---focusing on the impact of the training set size and the linguistic properties of the task.
no code implementations • 13 May 2020 • Lu Zhang, Jian Zhang, Zhibin Li, Jingsong Xu
Inspired by the fact that spreading and collecting information through the Internet becomes the norm, more and more people choose to post for-profit contents (images and texts) in social networks.
1 code implementation • CVPR 2020 • Xiaoshui Huang, Guofeng Mei, Jian Zhang
We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences.
no code implementations • 22 Apr 2020 • Yikang Zhang, Jian Zhang, Qiang Wang, Zhao Zhong
On one hand, we can reduce the computation cost remarkably while maintaining the performance.
1 code implementation • 27 Mar 2020 • Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao
Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.
no code implementations • 11 Mar 2020 • Dongming Yang, Yuexian Zou, Jian Zhang, Ge Li
GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances.
1 code implementation • 29 Feb 2020 • Megan Leszczynski, Avner May, Jian Zhang, Sen Wu, Christopher R. Aberger, Christopher Ré
To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings.
no code implementations • 18 Jan 2020 • Zhengping Liang, Jian Zhang, Liang Feng, Zexuan Zhu
However, as growing demand for cloud services, the existing EAs fail to implement in large-scale virtual machine placement (LVMP) problem due to the high time complexity and poor scalability.
no code implementations • 30 Dec 2019 • Jie Wu, Ying Peng, Chenghao Zheng, Zongbo Hao, Jian Zhang
Recently, generative adversarial networks (GANs) have shown great advantages in synthesizing images, leading to a boost of explorations of using faked images to augment data.
no code implementations • ICLR 2020 • Xin-Yu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong
The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.
Ranked #552 on
Image Classification
on ImageNet
no code implementations • 18 Dec 2019 • Lionel Blondé, Yichuan Charlie Tang, Jian Zhang, Russ Webb
In this work, we introduce a new method for imitation learning from video demonstrations.
no code implementations • 7 Dec 2019 • Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Jin-Feng Yi
In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.
1 code implementation • 4 Dec 2019 • Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang
In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
no code implementations • 24 Nov 2019 • Jinyin Chen, Jian Zhang, Zhi Chen, Min Du, Qi Xuan
In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).
no code implementations • 9 Nov 2019 • Yichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov
Recent advances in deep reinforcement learning have demonstrated the capability of learning complex control policies from many types of environments.
no code implementations • 17 Oct 2019 • Yijie Mao, Bruno Clerckx, Jian Zhang, Victor O. K. Li, Mohammed Arafah
Cooperative Rate-Splitting (CRS) strategy, relying on linearly precoded rate-splitting at the transmitter and opportunistic transmission of the common message by the relaying user, has recently been shown to outperform typical Non-cooperative Rate-Splitting (NRS), Cooperative Non-Orthogonal Multiple Access (C-NOMA) and Space Division Multiple Access (SDMA) in a two-user Multiple Input Single Output (MISO) Broadcast Channel (BC) with user relaying.
no code implementations • 9 Oct 2019 • Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa
Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization.
no code implementations • ICCV 2019 • Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang
We propose a variational Bayesian framework for enhancing few-shot learning performance.
no code implementations • 25 Sep 2019 • Kane Zhang, Jian Zhang, Qiang Wang, Zhao Zhong
To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduces 69. 3% FLOPs while maintaining the Mean IoU on segmentation task.
1 code implementation • NeurIPS 2019 • Avner May, Jian Zhang, Tri Dao, Christopher Ré
Finally, we show that by using the eigenspace overlap score as a selection criterion between embeddings drawn from a representative set we compressed, we can efficiently identify the better performing embedding with up to $2\times$ lower selection error rates than the next best measure of compression quality, and avoid the cost of training a model for each task of interest.