no code implementations • ICML 2020 • Liu Liu, Lei Deng, Zhaodong Chen, yuke wang, Shuangchen Li, Jingwei Zhang, Yihua Yang, Zhenyu Gu, Yufei Ding, Yuan Xie
Using Deep Neural Networks (DNNs) in machine learning tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements and energy constraints because of the memory-bound and the compute-bound execution pattern of DNNs.
no code implementations • 26 Mar 2024 • Zhan Shi, Jingwei Zhang, Jun Kong, Fusheng Wang
In digital pathology, the multiple instance learning (MIL) strategy is widely used in the weakly supervised histopathology whole slide image (WSI) classification task where giga-pixel WSIs are only labeled at the slide level.
no code implementations • 19 Mar 2024 • Jingwei Zhang, Lauren Swinnen, Christos Chatzichristos, Victoria Broux, Renee Proost, Katrien Jansen, Benno Mahler, Nicolas Zabler, Nino Epitashvilli, Matthias Dümpelmann, Andreas Schulze-Bonhage, Elisabeth Schriewer, Ummahan Ermis, Stefan Wolking, Florian Linke, Yvonne Weber, Mkael Symmonds, Arjune Sen, Andrea Biondi, Mark P. Richardson, Abuhaiba Sulaiman I, Ana Isabel Silva, Francisco Sales, Gergely Vértes, Wim Van Paesschen, Maarten De Vos
The combination of wearable EEG and EMG achieved overall the most clinically useful performance in offline TCS detection with a sensitivity of 97. 7%, a FPR of 0. 4/24 h, a precision of 43. 0%, and a F1-score of 59. 7%.
no code implementations • 27 Feb 2024 • Jingwei Zhang, Cheuk Ting Li, Farzan Farnia
The massive developments of generative model frameworks and architectures require principled methods for the evaluation of a model's novelty compared to a reference dataset or baseline generative models.
no code implementations • 23 Feb 2024 • Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, Nando de Freitas, Satinder Singh, Tim Rocktäschel
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos.
no code implementations • 8 Feb 2024 • Jost Tobias Springenberg, Abbas Abdolmaleki, Jingwei Zhang, Oliver Groth, Michael Bloesch, Thomas Lampe, Philemon Brakel, Sarah Bechtle, Steven Kapturowski, Roland Hafner, Nicolas Heess, Martin Riedmiller
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning.
1 code implementation • 22 Dec 2023 • Saarthak Kapse, Pushpak Pati, Srijan Das, Jingwei Zhang, Chao Chen, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras, Rajarsi R. Gupta, Prateek Prasanna
Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides.
no code implementations • 14 Sep 2023 • Cristina Pinneri, Sarah Bechtle, Markus Wulfmeier, Arunkumar Byravan, Jingwei Zhang, William F. Whitney, Martin Riedmiller
We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment.
no code implementations • 12 Sep 2023 • Saarthak Kapse, Srijan Das, Jingwei Zhang, Rajarsi R. Gupta, Joel Saltz, Dimitris Samaras, Prateek Prasanna
We propose DiRL, a Diversity-inducing Representation Learning technique for histopathology imaging.
no code implementations • 12 Jul 2023 • Jingwei Zhang, Ke Ma, Saarthak Kapse, Joel Saltz, Maria Vakalopoulou, Prateek Prasanna, Dimitris Samaras
On these two datasets, the proposed additional pathology foundation model further achieves a relative improvement of 5. 07% to 5. 12% in Dice score and 4. 50% to 8. 48% in IOU.
no code implementations • 5 Jul 2023 • Jingwei Zhang, Han Shi, Jincheng Yu, Enze Xie, Zhenguo Li
Generative models can be categorized into two types: explicit generative models that define explicit density forms and allow exact likelihood inference, such as score-based diffusion models (SDMs) and normalizing flows; implicit generative models that directly learn a transformation from the prior to the data distribution, such as generative adversarial nets (GANs).
no code implementations • 22 May 2023 • Jinglin Zhan, Tiejun Liu, RenGang Li, Jingwei Zhang, Zhaoxiang Zhang, Yuntao Chen
Data and model are the undoubtable two supporting pillars for LiDAR object detection.
no code implementations • 18 May 2023 • Ingmar Schubert, Jingwei Zhang, Jake Bruce, Sarah Bechtle, Emilio Parisotto, Martin Riedmiller, Jost Tobias Springenberg, Arunkumar Byravan, Leonard Hasenclever, Nicolas Heess
We investigate the use of transformer sequence models as dynamics models (TDMs) for control.
1 code implementation • 21 Mar 2023 • Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras
Compared to conventional full fine-tuning approaches, we fine-tune less than 1. 3% of the parameters, yet achieve a relative improvement of 1. 29%-13. 61% in accuracy and 3. 22%-27. 18% in AUROC and reduce GPU memory consumption by 38%-45% while training 21%-27% faster.
no code implementations • 24 Feb 2023 • Jingwei Zhang, Jost Tobias Springenberg, Arunkumar Byravan, Leonard Hasenclever, Abbas Abdolmaleki, Dushyant Rao, Nicolas Heess, Martin Riedmiller
We conduct a set of experiments in the RGB-stacking environment, showing that planning with the learned skills and the associated model can enable zero-shot generalization to new tasks, and can further speed up training of policies via reinforcement learning.
1 code implementation • ICCV 2023 • Jingwei Zhang, Farzan Farnia
Explaining the predictions of deep neural nets has been a topic of great interest in the computer vision literature.
no code implementations • ICCV 2023 • Yu Pei, Xian Zhao, Hao Li, Jingyuan Ma, Jingwei Zhang, ShiLiang Pu
Attributed to the unstructured and sparse nature of point clouds, the transformer shows greater potential in point clouds data processing.
no code implementations • 29 Dec 2022 • Priyank Pathak, Jingwei Zhang, Dimitris Samaras
In this paper, we propose a new mechanism for each local module, where instead of reconstructing the entire image, we reconstruct its input features, generated from previous modules.
1 code implementation • 23 Dec 2022 • Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras
Our method outperforms previous dense matching methods by up to 7. 2% in average precision for detection and 5. 6% in average precision for instance segmentation tasks.
no code implementations • 7 Nov 2022 • Zhongdao Wang, Zhaopeng Dou, Jingwei Zhang, Liang Zheng, Yifan Sun, YaLi Li, Shengjin Wang
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos.
Domain Generalization Generalizable Person Re-identification +1
1 code implementation • 17 Jul 2022 • Jingwei Zhang, Xin Zhang, Ke Ma, Rajarsi Gupta, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras
Histopathology whole slide images (WSIs) play a very important role in clinical studies and serve as the gold standard for many cancer diagnoses.
no code implementations • 19 May 2022 • Jingwei Zhang, Xunpeng Huang
We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with the neurons.
no code implementations • 9 Jul 2021 • Jingwei Zhang, Bin Zi, Xiaoyu Ge
This paper seeks to tackle the bin packing problem (BPP) through a learning perspective.
no code implementations • CVPR 2021 • Jingwei Zhang, Ke Ma, John Van Arnam, Rajarsi Gupta, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras
To tackle these problems, we propose a novel spatial and magnification based attention sampling strategy.
no code implementations • 22 Aug 2020 • Jialun Liu, Jingwei Zhang, Yi Yang, Wenhui Li, Chi Zhang, Yifan Sun
With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i. e.}, deep image classification and deep metric learning (on long-tailed data).
Ranked #44 on Long-tail Learning on CIFAR-100-LT (ρ=100)
no code implementations • ECCV 2020 • Zhongdao Wang, Jingwei Zhang, Liang Zheng, Yixuan Liu, Yifan Sun, Ya-Li Li, Shengjin Wang
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
no code implementations • 9 Mar 2020 • Shengchao Yan, Jingwei Zhang, Daniel Büscher, Wolfram Burgard
In this paper we present an approach to learning policies for signal controllers using deep reinforcement learning aiming for optimized traffic flow.
no code implementations • 8 Feb 2020 • Hongwu Kuang, Xiaodong Liu, Jingwei Zhang, Zicheng Fang
Multi-modality fusion is the guarantee of the stability of autonomous driving systems.
no code implementations • 3 Oct 2019 • Shan Lin, Jingwei Zhang
Convolutional neural networks (CNNs) have achieved breakthrough performances in a wide range of applications including image classification, semantic segmentation, and object detection.
no code implementations • 25 Sep 2019 • Liu Liu, Lei Deng, Shuangchen Li, Jingwei Zhang, Yihua Yang, Zhenyu Gu, Yufei Ding, Yuan Xie
Using Recurrent Neural Networks (RNNs) in sequence modeling tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements because of the memory-bound execution pattern of RNNs.
no code implementations • 18 Mar 2019 • Jingwei Zhang, Niklas Wetzel, Nicolai Dorka, Joschka Boedecker, Wolfram Burgard
Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration.
no code implementations • NeurIPS 2019 • Zhuozhuo Tu, Jingwei Zhang, DaCheng Tao
Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries.
no code implementations • 8 Nov 2018 • Jingwei Zhang, Tongliang Liu, DaCheng Tao
We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hypothesis and the output hypothesis conditioned on an input example.
no code implementations • 24 Apr 2018 • Jingwei Zhang, Tongliang Liu, DaCheng Tao
This upper bound shows that as the number of convolutional and pooling layers $L$ increases in the network, the expected generalization error will decrease exponentially to zero.
no code implementations • 2 Apr 2018 • Oleksii Zhelo, Jingwei Zhang, Lei Tai, Ming Liu, Wolfram Burgard
A video of our experimental results can be found at https://goo. gl/pWbpcF.
no code implementations • 11 Feb 2018 • Jingwei Zhang, Tongliang Liu, DaCheng Tao
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier.
no code implementations • 1 Feb 2018 • Jingwei Zhang, Lei Tai, Peng Yun, Yufeng Xiong, Ming Liu, Joschka Boedecker, Wolfram Burgard
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks.
1 code implementation • 6 Oct 2017 • Lei Tai, Jingwei Zhang, Ming Liu, Wolfram Burgard
Experiments show that our GAIL-based approach greatly improves the safety and efficiency of the behavior of mobile robots from pure behavior cloning.
1 code implementation • 29 Jun 2017 • Jingwei Zhang, Lei Tai, Ming Liu, Joschka Boedecker, Wolfram Burgard
We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments.
Reinforcement Learning (RL) Simultaneous Localization and Mapping
1 code implementation • 21 Dec 2016 • Lei Tai, Jingwei Zhang, Ming Liu, Joschka Boedecker, Wolfram Burgard
We carry out our discussions on the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning.
no code implementations • 16 Dec 2016 • Jingwei Zhang, Jost Tobias Springenberg, Joschka Boedecker, Wolfram Burgard
We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances.
1 code implementation • EMNLP 2015 • Jingwei Zhang, Aaron Gerow, Jaan Altosaar, James Evans, Richard Jean So
Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models.