Search Results for author: Yang Gao

Found 214 papers, 90 papers with code

Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning

no code implementations29 Nov 2023 Yingdong Hu, Fanqi Lin, Tong Zhang, Li Yi, Yang Gao

In this study, we are interested in imbuing robots with the capability of physically-grounded task planning.

Plug-and-Play Latent Feature Editing for Orientation-Adaptive Quantitative Susceptibility Mapping Neural Networks

1 code implementation14 Nov 2023 Yang Gao, Zhuang Xiong, Shanshan Shan, Yin Liu, Pengfei Rong, Min Li, Alan H Wilman, G. Bruce Pike, Feng Liu, Hongfu Sun

The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a self-supervised manner on a specially-designed simulation brain dataset.

TSST: A Benchmark and Evaluation Models for Text Speech-Style Transfer

no code implementations14 Nov 2023 Huashan Sun, Yixiao Wu, Yinghao Li, Jiawei Li, Yizhe Yang, Yang Gao

In summary, we present the TSST task, a new benchmark for style transfer and emphasizing human-oriented evaluation, exploring and advancing the performance of current LLMs.

Style Transfer Text Style Transfer

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

no code implementations6 Nov 2023 Kun Lei, Zhengmao He, Chenhao Lu, Kaizhe Hu, Yang Gao, Huazhe Xu

Owning to the alignment of objectives in two phases, the RL agent can transfer between offline and online learning seamlessly.

Reinforcement Learning (RL)

JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds

1 code implementation5 Nov 2023 Saeed Saadatnejad, Yang Gao, Hamid Rezatofighi, Alexandre Alahi

To address this, we introduce a novel dataset for end-to-end trajectory forecasting, facilitating the evaluation of models in scenarios involving less-than-ideal preceding modules such as tracking.

Autonomous Navigation Benchmarking +1

The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics

1 code implementation30 Oct 2023 Christoph Leiter, Juri Opitz, Daniel Deutsch, Yang Gao, Rotem Dror, Steffen Eger

Specifically, we propose a novel competition setting in which we select a list of allowed LLMs and disallow fine-tuning to ensure a focus on prompting.

Machine Translation Text Generation

MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications

no code implementations24 Oct 2023 Yizhe Yang, Huashan Sun, Jiawei Li, Runheng Liu, Yinghao Li, Yuhang Liu, Heyan Huang, Yang Gao

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence.

Language Modelling Large Language Model

DexCatch: Learning to Catch Arbitrary Objects with Dexterous Hands

no code implementations13 Oct 2023 Fengbo Lan, Shengjie Wang, Yunzhe Zhang, Haotian Xu, Oluwatosin Oseni, Yang Gao, Tao Zhang

Achieving human-like dexterous manipulation remains a crucial area of research in robotics.

Imitation Learning from Observation with Automatic Discount Scheduling

no code implementations11 Oct 2023 Yuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao

Nonetheless, we identify that tasks characterized by a progress dependency property pose significant challenges for such approaches; in these tasks, the agent needs to initially learn the expert's preceding behaviors before mastering the subsequent ones.

Imitation Learning reinforcement-learning +1

Rethink Baseline of Integrated Gradients from the Perspective of Shapley Value

no code implementations7 Oct 2023 Shuyang Liu, Zixuan Chen, Ge Shi, Ji Wang, Changjie Fan, Yu Xiong, Runze Wu Yujing Hu, Ze Ji, Yang Gao

Thus, we propose a novel baseline construction method called Shapley Integrated Gradients (SIG) that searches for a set of baselines by proportional sampling to partly simulate the computation path of Shapley Value.

Graph Neural Architecture Search with GPT-4

no code implementations30 Sep 2023 Haishuai Wang, Yang Gao, Xin Zheng, Peng Zhang, Hongyang Chen, Jiajun Bu

In this paper, we integrate GPT-4 into GNAS and propose a new GPT-4 based Graph Neural Architecture Search method (GPT4GNAS for short).

Neural Architecture Search

CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture

no code implementations28 Sep 2023 Zixuan Chen, Ze Ji, Shuyang Liu, Jing Huo, Yiyu Chen, Yang Gao

Heuristically, we extend the usual notion of action to a dual Cognition (high-level)-Action (low-level) architecture by introducing intuitive human cognitive priors, and propose a novel skill IL framework through human-robot interaction, called Cognition-Action-based Skill Imitation Learning (CasIL), for the robotic agent to effectively cognize and imitate the critical skills from raw visual demonstrations.

Imitation Learning

OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement

1 code implementation19 Sep 2023 Yang Gao, Ji Ma, Ivan Korotkov, Keith Hall, Dana Alon, Don Metzler

We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs.

Exploring Flat Minima for Domain Generalization with Large Learning Rates

no code implementations12 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.

Domain Generalization Semantic Segmentation

A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness

no code implementations6 Sep 2023 Ze Peng, Lei Qi, Yinghuan Shi, Yang Gao

Although having attributed it to training dynamics, existing theoretical explanations of activation sparsity are restricted to shallow networks, small training steps and special training, despite its emergence in deep models standardly trained for a large number of steps.

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

1 code implementation26 Aug 2023 Yanqi Bao, Tianyu Ding, Jing Huo, Wenbin Li, Yuxin Li, Yang Gao

By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations.

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

1 code implementation ICCV 2023 Zekun Li, Lei Qi, Yinghuan Shi, Yang Gao

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain.

Efficient Last-iterate Convergence Algorithms in Solving Games

no code implementations22 Aug 2023 Linjian Meng, Zhenxing Ge, Wenbin Li, Bo An, Yang Gao

Recent works propose a Reward Transformation (RT) framework for MWU, which removes the uniqueness condition and achieves competitive performance with OMWU.


DomainAdaptor: A Novel Approach to Test-time Adaptation

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.

Specificity Test

Quantitative Susceptibility Mapping through Model-based Deep Image Prior (MoDIP)

no code implementations18 Aug 2023 Zhuang Xiong, Yang Gao, Yin Liu, Amir Fazlollahi, Peter Nestor, Feng Liu, Hongfu Sun

The data-driven approach of supervised learning methods has limited applicability in solving dipole inversion in Quantitative Susceptibility Mapping (QSM) with varying scan parameters across different objects.

Image Reconstruction

Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs

1 code implementation5 Aug 2023 Yanqi Bao, Yuxin Li, Jing Huo, Tianyu Ding, Xinyue Liang, Wenbin Li, Yang Gao

Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints.

3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks

1 code implementation30 Jul 2023 Heng Cai, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.

Image Segmentation Medical Image Segmentation +3

Policy Contrastive Imitation Learning

no code implementations6 Jul 2023 Jialei Huang, ZhaoHeng Yin, Yingdong Hu, Yang Gao

However, the performance of AIL is still unsatisfactory on the more challenging tasks.

Binary Classification Imitation Learning +1

Towards Explainable Evaluation Metrics for Machine Translation

no code implementations22 Jun 2023 Christoph Leiter, Piyawat Lertvittayakumjorn, Marina Fomicheva, Wei Zhao, Yang Gao, Steffen Eger

In this context, we also discuss the latest state-of-the-art approaches to explainable metrics based on generative models such as ChatGPT and GPT4.

Machine Translation Translation

A Universal Semantic-Geometric Representation for Robotic Manipulation

no code implementations18 Jun 2023 Tong Zhang, Yingdong Hu, Hanchen Cui, Hang Zhao, Yang Gao

To this end, we present $\textbf{Semantic-Geometric Representation} (\textbf{SGR})$, a universal perception module for robotics that leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning.

Programmatically Grounded, Compositionally Generalizable Robotic Manipulation

no code implementations26 Apr 2023 Renhao Wang, Jiayuan Mao, Joy Hsu, Hang Zhao, Jiajun Wu, Yang Gao

Robots operating in the real world require both rich manipulation skills as well as the ability to semantically reason about when to apply those skills.

Imitation Learning

For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal

no code implementations10 Apr 2023 Yingdong Hu, Renhao Wang, Li Erran Li, Yang Gao

Our study yields a series of intriguing results, including the discovery that the effectiveness of pre-training is highly dependent on the choice of the downstream policy learning algorithm.

Imitation Learning Reinforcement Learning (RL)

Seer: Language Instructed Video Prediction with Latent Diffusion Models

no code implementations27 Mar 2023 Xianfan Gu, Chuan Wen, Jiaming Song, Yang Gao

With the well-designed architecture, Seer makes it possible to generate high-fidelity, coherent, and instruction-aligned video frames by fine-tuning a few layers on a small amount of data.

Denoising Video Prediction

Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation

1 code implementation CVPR 2023 Heng Cai, Shumeng Li, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

Subsequently, by introducing unlabeled volumes, we propose a dual-network paradigm named Dense-Sparse Co-training (DeSCO) that exploits dense pseudo labels in early stage and sparse labels in later stage and meanwhile forces consistent output of two networks.

Image Segmentation Semantic Segmentation +1

Real-time scheduling of renewable power systems through planning-based reinforcement learning

no code implementations9 Mar 2023 Shaohuai Liu, Jinbo Liu, Weirui Ye, Nan Yang, Guanglun Zhang, Haiwang Zhong, Chongqing Kang, Qirong Jiang, Xuri Song, Fangchun Di, Yang Gao

The well-trained scheduling agent significantly reduces renewable curtailment and load shedding, which are issues arising from traditional scheduling's reliance on inaccurate day-ahead forecasts.

reinforcement-learning Reinforcement Learning (RL) +1

Decision Transformer under Random Frame Dropping

1 code implementation3 Mar 2023 Kaizhe Hu, Ray Chen Zheng, Yang Gao, Huazhe Xu

Typical RL methods usually require considerable online interaction data that are costly and unsafe to collect in the real world.

Offline RL

Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization

no code implementations28 Feb 2023 Haotian Xu, Shengjie Wang, Zhaolei Wang, Yunzhe Zhang, Qing Zhuo, Yang Gao, Tao Zhang

In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose.

Efficient Exploration Reinforcement Learning (RL)

Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding

1 code implementation3 Feb 2023 Mingyang Chen, Wen Zhang, Zhen Yao, Yushan Zhu, Yang Gao, Jeff Z. Pan, Huajun Chen

In our proposed model, Entity-Agnostic Representation Learning (EARL), we only learn the embeddings for a small set of entities and refer to them as reserved entities.

Entity Embeddings Knowledge Graph Embedding +3

Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

no code implementations9 Jan 2023 Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, Jan-Jakob Sonke, Efstratios Gavves

However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction.

Few-Shot Semantic Segmentation

A Policy Optimization Method Towards Optimal-time Stability

no code implementations2 Jan 2023 Shengjie Wang, Fengbo Lan, Xiang Zheng, Yuxue Cao, Oluwatosin Oseni, Haotian Xu, Tao Zhang, Yang Gao

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization.

Reinforcement Learning (RL)

PanoViT: Vision Transformer for Room Layout Estimation from a Single Panoramic Image

no code implementations23 Dec 2022 Weichao Shen, Yuan Dong, Zonghao Chen, Zhengyi Zhao, Yang Gao, Zhu Liu

In this paper, we propose PanoViT, a panorama vision transformer to estimate the room layout from a single panoramic image.

Room Layout Estimation

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

no code implementations17 Dec 2022 Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu

Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.

reinforcement-learning Reinforcement Learning (RL)

A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix

no code implementations26 Nov 2022 Wenbin Li, Meihao Kong, Xuesong Yang, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo

In this study, we present a new unified contrastive learning representation framework (named UniCLR) suitable for all the above four kinds of methods from a novel perspective of basic affinity matrix.

Contrastive Learning Representation Learning

Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping

no code implementations25 Nov 2022 Zhuang Xiong, Yang Gao, Feng Liu, Hongfu Sun

We propose an end-to-end AFfine Transformation Edited and Refined (AFTER) deep neural network for QSM, which is robust against arbitrary acquisition orientation and spatial resolution up to 0. 6 mm isotropic at the finest.

Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions

no code implementations23 Oct 2022 Weirui Ye, Pieter Abbeel, Yang Gao

This paper proposes the Virtual MCTS (V-MCTS), a variant of MCTS that spends more search time on harder states and less search time on simpler states adaptively.

Atari Games Board Games

Planning for Sample Efficient Imitation Learning

1 code implementation18 Oct 2022 Zhao-Heng Yin, Weirui Ye, Qifeng Chen, Yang Gao

Inspired by the recent success of EfficientZero in RL, we propose EfficientImitate (EI), a planning-based imitation learning method that can achieve high in-environment sample efficiency and performance simultaneously.

Imitation Learning

Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient

1 code implementation10 Oct 2022 Wubing Chen, Wenbin Li, Xiao Liu, Shangdong Yang, Yang Gao

Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces.

Multi-agent Reinforcement Learning reinforcement-learning +3

Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery

1 code implementation CVPR 2023 Wenbin Li, Zhichen Fan, Jing Huo, Yang Gao

Specifically, we propose an inter-class sKLD constraint to effectively exploit the disjoint relationship between labelled and unlabelled classes, enforcing the separability for different classes in the embedding space.

Novel Class Discovery

PLN: Parasitic-Like Network for Barely Supervised Medical Image Segmentation

1 code implementation IEEE Transactions on Medical Imaging 2022 Shumeng Li, Heng Cai; Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

In this paper, by introducing an extremely sparse annotation way of labeling only one slice per 3D image, we investigate a novel barely-supervised segmentation setting with only a few sparsely-labeled images along with a large amount of unlabeled images.

Image Segmentation Medical Image Segmentation +2

USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation

no code implementations28 Sep 2022 Zhengrong Xue, Zhecheng Yuan, Jiashun Wang, Xueqian Wang, Yang Gao, Huazhe Xu

Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance?

Keypoint Detection

MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees

no code implementations15 Sep 2022 Zichuan Liu, Yuanyang Zhu, Zhi Wang, Yang Gao, Chunlin Chen

Our solution is MIXing Recurrent soft decision Trees (MIXRTs), a novel interpretable architecture that can represent explicit decision processes via the root-to-leaf path of decision trees.

Multi-agent Reinforcement Learning reinforcement-learning +3

Semantic-Aware Fine-Grained Correspondence

1 code implementation21 Jul 2022 Yingdong Hu, Renhao Wang, Kaifeng Zhang, Yang Gao

Establishing visual correspondence across images is a challenging and essential task.

Pose Tracking Self-Supervised Learning +4

EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer

1 code implementation20 Jul 2022 Chenyu Yang, Wanrong He, Yingqing Xu, Yang Gao

Most existing methods view makeup transfer as transferring color distributions of different facial regions and ignore details such as eye shadows and blushes.

Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction

no code implementations20 Jul 2022 Chia-Chi Chuang, Donglin Yang, Chuan Wen, Yang Gao

This is especially the case with image observations, where a single image only includes one view of the scene, and it suffers from a lack of motion information and object occlusions.

Imitation Learning

Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming

no code implementations22 Jun 2022 Chuan Wen, Jianing Qian, Jierui Lin, Jiaye Teng, Dinesh Jayaraman, Yang Gao

Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution.

Autonomous Driving Classification +5

Auto-Encoding Adversarial Imitation Learning

no code implementations22 Jun 2022 Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao

In this work, we propose Auto-Encoding Adversarial Imitation Learning (AEAIL), a robust and scalable AIL framework.

Imitation Learning Reinforcement Learning (RL)

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

1 code implementation9 Jun 2022 Jinkun Cao, Ruiqian Nai, Qing Yang, Jialei Huang, Yang Gao

In this paper, we examine negative-free contrastive learning methods to study the disentanglement property empirically.

Contrastive Learning Disentanglement

$G^2$: Enhance Knowledge Grounded Dialogue via Ground Graph

no code implementations27 Apr 2022 Yizhe Yang, Yang Gao, Jiawei Li, Heyan Huang

Besides, a Ground Graph Aware Transformer ($G^2AT$) is proposed to enhance knowledge grounded response generation.

Response Generation

BFRnet: A deep learning-based MR background field removal method for QSM of the brain containing significant pathological susceptibility sources

1 code implementation6 Apr 2022 Xuanyu Zhu, Yang Gao, Feng Liu, Stuart Crozier, Hongfu Sun

The BFRnet method is compared with three conventional BFR methods and one previous deep learning method using simulated and in vivo brains from 4 healthy and 2 hemorrhagic subjects.

DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder

1 code implementation30 Mar 2022 Jiaao Zhan, Qian Chen, Boxing Chen, Wen Wang, Yu Bai, Yang Gao

We propose a novel and general Dependency-Aware Decoder (DePA) to enhance target dependency modeling in the decoder of fully NAT models from two perspectives: decoder self-attention and decoder input.

Machine Translation Translation

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

2 code implementations27 Mar 2022 Yue Duan, Zhen Zhao, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi, Yang Gao

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.

Semi-Supervised Image Classification

Playing Lottery Tickets in Style Transfer Models

no code implementations25 Mar 2022 Meihao Kong, Jing Huo, Wenbin Li, Jing Wu, Yu-Kun Lai, Yang Gao

(2) Using iterative magnitude pruning, we find the matching subnetworks at 89. 2% sparsity in AdaIN and 73. 7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too.

Style Transfer

TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing

1 code implementation CCL 2022 Mucheng Ren, Heyan Huang, Yuxiang Zhou, Qianwen Cao, Yuan Bu, Yang Gao

Therefore, in this paper, we focus on the core task of the TCM diagnosis and treatment system -- syndrome differentiation (SD) -- and we introduce the first public large-scale dataset for SD, called TCM-SD.

Language Modelling

Towards Explainable Evaluation Metrics for Natural Language Generation

1 code implementation21 Mar 2022 Christoph Leiter, Piyawat Lertvittayakumjorn, Marina Fomicheva, Wei Zhao, Yang Gao, Steffen Eger

We also provide a synthesizing overview over recent approaches for explainable machine translation metrics and discuss how they relate to those goals and properties.

Machine Translation Text Generation +2

CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation

1 code implementation17 Mar 2022 Renhao Wang, Hang Zhao, Yang Gao

Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO.

Contrastive Learning Segmentation

Ask to Understand: Question Generation for Multi-hop Question Answering

no code implementations17 Mar 2022 Jiawei Li, Mucheng Ren, Yang Gao, Yizhe Yang

Specifically, we carefully design an end-to-end QG module on the basis of a classical QA module, which could help the model understand the context by asking inherently logical sub-questions, thus inheriting interpretability from the QD-based method and showing superior performance.

Multi-hop Question Answering Question Answering +2

Generalized Bandit Regret Minimizer Framework in Imperfect Information Extensive-Form Game

no code implementations11 Mar 2022 Linjian Meng, Yang Gao

In this paper, we propose a generalized framework for this learning setting.

Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation

no code implementations2 Mar 2022 Xiao Liu, Shuyang Liu, Wenbin Li, Shangdong Yang, Yang Gao

Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies.

Transformers in Medical Image Analysis: A Review

no code implementations24 Feb 2022 Kelei He, Chen Gan, Zhuoyuan Li, Islem Rekik, Zihao Yin, Wen Ji, Yang Gao, Qian Wang, Junfeng Zhang, Dinggang Shen

Transformers have dominated the field of natural language processing, and recently impacted the computer vision area.

Image Generation

Online Attentive Kernel-Based Temporal Difference Learning

no code implementations22 Jan 2022 Guang Yang, Xingguo Chen, Shangdong Yang, Huihui Wang, Shaokang Dong, Yang Gao

Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA.

Acrobot Reinforcement Learning (RL)

MVDG: A Unified Multi-view Framework for Domain Generalization

1 code implementation23 Dec 2021 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Beyond the training stage, overfitting could also cause unstable prediction in the test stage.

Domain Generalization Meta-Learning +1

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

2 code implementations22 Dec 2021 Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng, Yang Gao, Yi Wu, Zhongqian Sun, Yang Wei

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data.

Reinforcement Learning (RL)

PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization

1 code implementation7 Dec 2021 Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao

Particularly, the proposed method can generate a variety of data variants to better deal with the overfitting issue.

Domain Generalization

Instant tissue field and magnetic susceptibility mapping from MR raw phase using Laplacian enabled deep neural networks

2 code implementations15 Nov 2021 Yang Gao, Zhuang Xiong, Amir Fazlollahi, Peter J Nestor, Viktor Vegh, Fatima Nasrallah, Craig Winter, G. Bruce Pike, Stuart Crozier, Feng Liu, Hongfu Sun

In addition, experiments on patients with intracranial hemorrhage and multiple sclerosis were also performed to test the generalization of the novel neural networks.

Mastering Atari Games with Limited Data

3 code implementations NeurIPS 2021 Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, Yang Gao

Recently, there has been significant progress in sample efficient image-based RL algorithms; however, consistent human-level performance on the Atari game benchmark remains an elusive goal.

Atari Games Atari Games 100k

NAS-FCOS: Efficient Search for Object Detection Architectures

1 code implementation24 Oct 2021 Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang

Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures.

Neural Architecture Search object-detection +1

Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation

1 code implementation17 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.

Image Segmentation Segmentation +2

Unifying Cross-lingual Summarization and Machine Translation with Compression Rate

1 code implementation15 Oct 2021 Yu Bai, Heyan Huang, Kai Fan, Yang Gao, Yiming Zhu, Jiaao Zhan, Zewen Chi, Boxing Chen

Through introducing compression rate, the information ratio between the source and the target text, we regard the MT task as a special CLS task with a compression rate of 100%.

Data Augmentation Machine Translation +1

Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization

no code implementations10 Oct 2021 Ruiqi Wang, Lei Qi, Yinghuan Shi, Yang Gao

Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process.

Domain Generalization Pseudo Label +1

Attention-based Interpretation and Response to The Trade-Off of Adversarial Training

no code implementations29 Sep 2021 Changbin Shao, Wenbin Li, ZhenHua Feng, Jing Huo, Yang Gao

To boost the robustness of a model against adversarial examples, adversarial training has been regarded as a benchmark method.

Disentangling Properties of Contrastive Methods

no code implementations29 Sep 2021 Jinkun Cao, Qing Yang, Jialei Huang, Yang Gao

In this paper, we explored the possibility of using contrastive methods to learn a disentangled representation, a discriminative approach that is drastically different from previous approaches.

Disentanglement Object Recognition

Auto-Encoding Inverse Reinforcement Learning

no code implementations29 Sep 2021 Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao

Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function.

Imitation Learning reinforcement-learning +1

Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts

no code implementations29 Sep 2021 Chuan Wen, Jianing Qian, Jierui Lin, Dinesh Jayaraman, Yang Gao

When operating in partially observed settings, it is important for a control policy to fuse information from a history of observations.

Autonomous Driving Continuous Control +1

LibFewShot: A Comprehensive Library for Few-shot Learning

1 code implementation10 Sep 2021 Wenbin Li, Ziyi, Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.

Data Augmentation Few-Shot Image Classification +2

Supporting Complaints Investigation for Nursing and Midwifery Regulatory Agencies

no code implementations ACL 2021 Piyawat Lertvittayakumjorn, Ivan Petej, Yang Gao, Yamuna Krishnamurthy, Anna Van Der Gaag, Robert Jago, Kostas Stathis

Health professional regulators aim to protect the health and well-being of patients and the public by setting standards for scrutinising and overseeing the training and conduct of health and care professionals.

Decision Making

Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions

1 code implementation24 Jul 2021 Qian Yu, Lei Qi, Luping Zhou, Lei Wang, Yilong Yin, Yinghuan Shi, Wuzhang Wang, Yang Gao

Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.

Image Segmentation Medical Image Segmentation +2

Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings

1 code implementation22 Jul 2021 Wenbin Li, Xuesong Yang, Meihao Kong, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo

However, in small data regimes, we can not obtain a sufficient number of negative pairs or effectively avoid the over-fitting problem when negatives are not used at all.

Representation Learning Self-Supervised Learning +1

Differentiable Architecture Pruning for Transfer Learning

no code implementations7 Jul 2021 Nicolo Colombo, Yang Gao

We propose a new gradient-based approach for extracting sub-architectures from a given large model.

Transfer Learning

Keyframe-Focused Visual Imitation Learning

no code implementations11 Jun 2021 Chuan Wen, Jierui Lin, Jianing Qian, Yang Gao, Dinesh Jayaraman

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations.

Continuous Control Graph Learning +1

ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation

1 code implementation CVPR 2022 Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao

In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student.

Semi-Supervised Semantic Segmentation

Feature-based Style Randomization for Domain Generalization

no code implementations6 Jun 2021 Yue Wang, Lei Qi, Yinghuan Shi, Yang Gao

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption.

Data Augmentation Domain Generalization

Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio

no code implementations4 Jun 2021 Gokce Keskin, Minhua Wu, Brian King, Harish Mallidi, Yang Gao, Jasha Droppo, Ariya Rastrow, Roland Maas

An ASR model that operates on both primary and auxiliary data can achieve better accuracy compared to a primary-only solution; and a model that can serve both primary-only (PO) and primary-plus-auxiliary (PPA) modes is highly desirable.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Prediction or Comparison: Toward Interpretable Qualitative Reasoning

no code implementations Findings (ACL) 2021 Mucheng Ren, Heyan Huang, Yang Gao

Qualitative relationships illustrate how changing one property (e. g., moving velocity) affects another (e. g., kinetic energy) and constitutes a considerable portion of textual knowledge.

Question Answering

Deep grey matter quantitative susceptibility mapping from small spatial coverages using deep learning

no code implementations1 Jun 2021 Xuanyu Zhu, Yang Gao, Feng Liu, Stuart Crozier, Hongfu Sun

Method: A recently proposed deep learning-based QSM method, namely xQSM, is investigated to assess the accuracy of dipole inversion on reduced brain coverages.

Cross-Lingual Abstractive Summarization with Limited Parallel Resources

1 code implementation ACL 2021 Yu Bai, Yang Gao, Heyan Huang

Employing one unified decoder to generate the sequential concatenation of monolingual and cross-lingual summaries, MCLAS makes the monolingual summarization task a prerequisite of the cross-lingual summarization (CLS) task.

Abstractive Text Summarization Cross-Lingual Abstractive Summarization +1

Deep Learning Traversability Estimator for Mobile Robots in Unstructured Environments

1 code implementation23 May 2021 Marco Visca, Sampo Kuutti, Roger Powell, Yang Gao, Saber Fallah

Terrain traversability analysis plays a major role in ensuring safe robotic navigation in unstructured environments.

Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation

1 code implementation17 May 2021 Kelei He, Wen Ji, Tao Zhou, Zhuoyuan Li, Jing Huo, Xin Zhang, Yang Gao, Dinggang Shen, Bing Zhang, Junfeng Zhang

Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network.

Brain Tumor Segmentation Image Generation +3

Adapting by Pruning: A Case Study on BERT

1 code implementation7 May 2021 Yang Gao, Nicolo Colombo, Wei Wang

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models.

CAT: Cross-Attention Transformer for One-Shot Object Detection

no code implementations30 Apr 2021 Weidong Lin, Yuyan Deng, Yang Gao, Ning Wang, Jinghao Zhou, Lingqiao Liu, Lei Zhang, Peng Wang

Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison.

object-detection One-Shot Object Detection +2

Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Environments

no code implementations4 Apr 2021 Marco Visca, Arthur Bouton, Roger Powell, Yang Gao, Saber Fallah

Driving energy consumption plays a major role in the navigation of mobile robots in challenging environments, especially if they are left to operate unattended under limited on-board power.

Self-Supervised Learning

Towards Self-Adaptive Metric Learning On the Fly

no code implementations3 Apr 2021 Yang Gao, Yi-Fan Li, Swarup Chandra, Latifur Khan, Bhavani Thuraisingham

In this paper, we present a new online metric learning framework that attempts to tackle the challenge by learning an ANN-based metric with adaptive model complexity from a stream of constraints.

Image Classification Image Retrieval +2

SetConv: A New Approach for Learning from Imbalanced Data

no code implementations EMNLP 2020 Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, Latifur Khan

For many real-world classification problems, e. g., sentiment classification, most existing machine learning methods are biased towards the majority class when the Imbalance Ratio (IR) is high.

BIG-bench Machine Learning Classification +3

Accelerating Quantitative Susceptibility Mapping using Compressed Sensing and Deep Neural Network

2 code implementations17 Mar 2021 Yang Gao, Martijn Cloos, Feng Liu, Stuart Crozier, G. Bruce Pike, Hongfu Sun

In this study, a learning-based Deep Complex Residual Network (DCRNet) is proposed to recover both the magnitude and phase images from incoherently undersampled data, enabling high acceleration of QSM acquisition.


Mutual Information State Intrinsic Control

2 code implementations ICLR 2021 Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

Reinforcement learning has been shown to be highly successful at many challenging tasks.

Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning

no code implementations10 Mar 2021 Bernie Wang, Simon Xu, Kurt Keutzer, Yang Gao, Bichen Wu

To address this, we propose a novel self-supervised learning task, which we named Trajectory Contrastive Learning (TCL), to improve meta-training.

Contrastive Learning Meta Reinforcement Learning +3

Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation

no code implementations18 Jan 2021 Xiaoting Han, Lei Qi, Qian Yu, Ziqi Zhou, Yefeng Zheng, Yinghuan Shi, Yang Gao

These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images.

Image Segmentation Medical Image Segmentation +4

LoFGAN: Fusing Local Representations for Few-Shot Image Generation

1 code implementation ICCV 2021 Zheng Gu, Wenbin Li, Jing Huo, Lei Wang, Yang Gao

Given only a few available images for a novel unseen category, few-shot image generation aims to generate more data for this category.

Image Generation

Discrete Predictive Representation for Long-horizon Planning

no code implementations1 Jan 2021 Thanard Kurutach, Julia Peng, Yang Gao, Stuart Russell, Pieter Abbeel

Discrete representations have been key in enabling robots to plan at more abstract levels and solve temporally-extended tasks more efficiently for decades.

Reinforcement Learning (RL)

Maximizing absorption in photon trapping ultra-fast silicon photodetectors

no code implementations22 Dec 2020 Cesar Bartolo-Perez, Wayesh Qarony, Soroush Ghandiparsi, Ahmed S. Mayet, Ahasan Ahamed, Hilal Cansizoglu, Yang Gao, Ekaterina Ponizovskaya Devine, Toshishige Yamada, Aly F Elrefaie, Shih-Yuan Wang, M. Saif Islam

Photon trapping structures address this trade-off by enhancing the light-matter interactions, but maximizing their performance remains a challenge due to a multitude of factors influencing their design and fabrication.

Optics Applied Physics

CariMe: Unpaired Caricature Generation with Multiple Exaggerations

2 code implementations1 Oct 2020 Zheng Gu, Chuanqi Dong, Jing Huo, Wenbin Li, Yang Gao

Previous caricature generation methods are obsessed with predicting definite image warping from a given photo while ignoring the intrinsic representation and distribution for exaggerations in caricatures.

Caricature Image-to-Image Translation

Disentangling Neural Architectures and Weights: A Case Study in Supervised Classification

no code implementations11 Sep 2020 Nicolo Colombo, Yang Gao

To find the optimal weight-agnostic network, we use a novel and computationally efficient method that translates the hard architecture-search problem into a feasible optimization problem. More specifically, we look at the optimal task-specific architectures as the optimal configuration of binary networks with {0, 1}-valued weights, which can be found through an approximate gradient descent strategy.

General Classification

ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation

no code implementations7 Sep 2020 Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu, Yang Gao, Pengfei Xu, Trevor Darrell, Kurt Keutzer

They require prior knowledge of real-world statistics and ignore the pixel-level dropout noise gap and the spatial feature gap between different domains.

Autonomous Driving Domain Adaptation +3

Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective

no code implementations31 Jul 2020 Yinghuan Shi, Wanqi Yang, Kim-Han Thung, Hao Wang, Yang Gao, Yang Pan, Li Zhang, Dinggang Shen

Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.

Manifold Alignment for Semantically Aligned Style Transfer

1 code implementation ICCV 2021 Jing Huo, Shiyin Jin, Wenbin Li, Jing Wu, Yu-Kun Lai, Yinghuan Shi, Yang Gao

In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.

Semantic Segmentation Style Transfer

HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation

no code implementations21 May 2020 Kelei He, Chunfeng Lian, Bing Zhang, Xin Zhang, Xiaohuan Cao, Dong Nie, Yang Gao, Junfeng Zhang, Dinggang Shen

In this paper, we tackle the challenging task of prostate segmentation in CT images by a two-stage network with 1) the first stage to fast localize, and 2) the second stage to accurately segment the prostate.

Multi-Task Learning

MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling

no code implementations15 May 2020 Kelei He, Chunfeng Lian, Ehsan Adeli, Jing Huo, Yang Gao, Bing Zhang, Junfeng Zhang, Dinggang Shen

Therefore, the proposed network has a dual-branch architecture that tackles two tasks: 1) a segmentation sub-network aiming to generate the prostate segmentation, and 2) a voxel-metric learning sub-network aiming to improve the quality of the learned feature space supervised by a metric loss.

Metric Learning Multi-Task Learning +2

Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images

no code implementations8 May 2020 Kelei He, Wei Zhao, Xingzhi Xie, Wen Ji, Mingxia Liu, Zhenyu Tang, Feng Shi, Yang Gao, Jun Liu, Junfeng Zhang, Dinggang Shen

Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice).


On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

1 code implementation ACL 2020 Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger

We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER.

Language Modelling Machine Translation +4

xQSM-Quantitative Susceptibility Mapping with Octave Convolutional Neural Networks

1 code implementation14 Apr 2020 Yang Gao, Xuanyu Zhu, Stuart Crozier, Feng Liu, Hongfu Sun

Quantitative susceptibility mapping (QSM) is a valuable magnetic resonance imaging (MRI) contrast mechanism that has demonstrated broad clinical applications.

Image and Video Processing

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

1 code implementation13 Apr 2020 Tiexin Qin, Wenbin Li, Yinghuan Shi, Yang Gao

Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations.

Data Augmentation Unsupervised Few-Shot Image Classification +1

Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation

no code implementations3 Apr 2020 Qian Yu, Yinghuan Shi, Yefeng Zheng, Yang Gao, Jianbing Zhu, Yakang Dai

Robust segmentation for non-elongated tissues in medical images is hard to realize due to the large variation of the shape, size, and appearance of these tissues in different patients.


Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization

1 code implementation27 Mar 2020 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.

Domain Generalization Segmentation +1

Deep Learning on Knowledge Graph for Recommender System: A Survey

no code implementations25 Mar 2020 Yang Gao, Yi-Fan Li, Yu Lin, Hang Gao, Latifur Khan

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS).

Graph Embedding Knowledge Graphs +1

Phylogenetic Study of 2019-nCoV by Using Alignment Free Method (Evolutionary Bifurcation of Novel Coronavirus Mutants)

no code implementations3 Mar 2020 Yang Gao, Tao Li, Liaofu Luo

It is found that there exist three types of virus mutations, namely, the mutation among sub-branches of the same branch, the off-root mutation and the root-oriented mutation between large branches of the tree.

Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation

no code implementations22 Feb 2020 Tiexin Qin, Ziyuan Wang, Kelei He, Yinghuan Shi, Yang Gao, Dinggang Shen

Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation.

Data Augmentation Image Segmentation +5

Asymmetric Distribution Measure for Few-shot Learning

no code implementations1 Feb 2020 Wenbin Li, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao, Jiebo Luo

Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.

Few-Shot Image Classification Few-Shot Learning

MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration

no code implementations7 Jan 2020 Haodi Hou, Jing Huo, Jing Wu, Yu-Kun Lai, Yang Gao

Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo.

Caricature Style Transfer

Multi-Agent Game Abstraction via Graph Attention Neural Network

no code implementations25 Nov 2019 Yong Liu, Weixun Wang, Yujing Hu, Jianye Hao, Xingguo Chen, Yang Gao

Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents.

Graph Attention Multi-agent Reinforcement Learning

Differentiable Meta-learning Model for Few-shot Semantic Segmentation

no code implementations23 Nov 2019 Pinzhuo Tian, Zhangkai Wu, Lei Qi, Lei Wang, Yinghuan Shi, Yang Gao

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.

Few-Shot Semantic Segmentation Segmentation +1

Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation

1 code implementation22 Nov 2019 Edwin Simpson, Yang Gao, Iryna Gurevych

For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs.

Bayesian Optimisation Community Question Answering +1

Defensive Few-shot Learning

1 code implementation16 Nov 2019 Wenbin Li, Lei Wang, Xingxing Zhang, Lei Qi, Jing Huo, Yang Gao, Jiebo Luo

(2) how to narrow the distribution gap between clean and adversarial examples under the few-shot setting?

Adversarial Defense Few-Shot Learning +1

Visual cryptography in single-pixel imaging

no code implementations12 Nov 2019 Shuming Jiao, Jun Feng, Yang Gao, Ting Lei, Xiaocong Yuan

The secret image can be recovered when identical illumination patterns are projected onto multiple visual key images and a single detector is used to record the total light intensities.

Does deep learning always outperform simple linear regression in optical imaging?

no code implementations31 Oct 2019 Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong Yuan

Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated.


Automatic Data Augmentation by Learning the Deterministic Policy

1 code implementation18 Oct 2019 Yinghuan Shi, Tiexin Qin, Yong liu, Jiwen Lu, Yang Gao, Dinggang Shen

By introducing an unified optimization goal, DeepAugNet intends to combine the data augmentation and the deep model training in an end-to-end training manner which is realized by simultaneously training a hybrid architecture of dueling deep Q-learning algorithm and a surrogate deep model.

Data Augmentation Q-Learning

Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation

1 code implementation17 Oct 2019 Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell

The agent is first presented with previous experiences in the training environment, along with task description in the form of trajectory-level sparse rewards.

Continuous Control Zero-Shot Learning

Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

no code implementations25 Sep 2019 Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell

In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn task-agnostic semantics and dynamics priors from arbitrary quality interactions as well as the corresponding sparse rewards and then plan on unseen tasks in zero-shot condition.

From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

no code implementations6 Sep 2019 Weixun Wang, Tianpei Yang, Yong liu, Jianye Hao, Xiaotian Hao, Yujing Hu, Yingfeng Chen, Changjie Fan, Yang Gao

In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents.

Better Rewards Yield Better Summaries: Learning to Summarise Without References

2 code implementations IJCNLP 2019 Florian Böhm, Yang Gao, Christian M. Meyer, Ori Shapira, Ido Dagan, Iryna Gurevych

Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summarieswith higher human ratings.

Reinforcement Learning (RL)

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

no code implementations15 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels.

Semi-Supervised Person Re-Identification

GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification

no code implementations14 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao

Moreover, in the training process, we adopt the joint learning scheme to simultaneously train each branch by the independent loss function, which can enhance the generalization ability of each branch.

Person Re-Identification

Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification

no code implementations2 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Xin Geng, Yang Gao

To achieve the camera alignment, we develop a Multi-Camera Adversarial Learning (MCAL) to map images of different cameras into a shared subspace.

Person Re-Identification

Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation

1 code implementation30 Jul 2019 Yang Gao, Christian M. Meyer, Mohsen Mesgar, Iryna Gurevych

The predominant RL paradigm for summarisation learns a cross-input policy, which requires considerable time, data and parameter tuning due to the huge search spaces and the delayed rewards.

Decision Making Learning-To-Rank +3

Deep Learning for Spacecraft Pose Estimation from Photorealistic Rendering

1 code implementation9 Jul 2019 Pedro F. Proenca, Yang Gao

On-orbit proximity operations in space rendezvous, docking and debris removal require precise and robust 6D pose estimation under a wide range of lighting conditions and against highly textured background, i. e., the Earth.

6D Pose Estimation 6D Pose Estimation using RGB +2