Search Results for author: Junge Zhang

Found 24 papers, 14 papers with code

Counter-Contrastive Learning for Language GANs

no code implementations Findings (EMNLP) 2021 Yekun Chai, Haidong Zhang, Qiyue Yin, Junge Zhang

Generative Adversarial Networks (GANs) have achieved great success in image synthesis, but have proven to be difficult to generate natural language.

Contrastive Learning Image Generation

Delving into Transformer for Incremental Semantic Segmentation

no code implementations18 Nov 2022 Zekai Xu, Mingyi Zhang, Jiayue Hou, Xing Gong, Chuan Wen, Chengjie Wang, Junge Zhang

In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks.

Semantic Segmentation

Softmax-free Linear Transformers

1 code implementation5 Jul 2022 Jiachen Lu, Li Zhang, Junge Zhang, Xiatian Zhu, Hang Xu, Jianfeng Feng

Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning

no code implementations2 Jun 2022 Hao Chen, Guangkai Yang, Junge Zhang, Qiyue Yin, Kaiqi Huang

Specifically, these methods do not explicitly utilize the relationship between agents and cannot adapt to different sizes of inputs.

reinforcement-learning

Coordinated Proximal Policy Optimization

1 code implementation NeurIPS 2021 Zifan Wu, Chao Yu, Deheng Ye, Junge Zhang, Haiyin Piao, Hankz Hankui Zhuo

We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting.

Starcraft Starcraft II

SOFT: Softmax-free Transformer with Linear Complexity

2 code implementations NeurIPS 2021 Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, Li Zhang

Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

no code implementations9 Apr 2021 Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang

More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when we use the transition to train the action-value and policy functions.

Model-based Reinforcement Learning reinforcement-learning

Improving Sequence Generative Adversarial Networks with Feature Statistics Alignment

no code implementations1 Jan 2021 Yekun Chai, Qiyue Yin, Junge Zhang

Generative Adversarial Networks (GAN) are facing great challenges in synthesizing sequences of discrete elements, such as mode dropping and unstable training.

Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning

no code implementations24 Oct 2020 Xiyao Wang, Junge Zhang, Wenzhen Huang, Qiyue Yin

We give an upper bound of the trajectory reward estimation error and point out that increasing the agent's exploration ability is the key to reduce trajectory reward estimation error, thereby alleviating dynamics bottleneck dilemma.

Continuous Control Decision Making +2

Point Cloud Super Resolution with Adversarial Residual Graph Networks

1 code implementation arXiv:1908.02111 2019 Huikai Wu, Junge Zhang, Kaiqi Huang

The key idea of the proposed network is to exploit the local similarity of point cloud and the analogy between LR input and HR output.

Graphics Image and Video Processing

SparseMask: Differentiable Connectivity Learning for Dense Image Prediction

1 code implementation ICCV 2019 Huikai Wu, Junge Zhang, Kaiqi Huang

In this paper, we aim at automatically searching an efficient network architecture for dense image prediction.

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

12 code implementations28 Mar 2019 Huikai Wu, Junge Zhang, Kaiqi Huang, Kongming Liang, Yizhou Yu

Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint.

Semantic Segmentation

Transductive Zero-Shot Learning with Visual Structure Constraint

1 code implementation NeurIPS 2019 Zi-Yu Wan, Dong-Dong Chen, Yan Li, Xingguang Yan, Junge Zhang, Yizhou Yu, Jing Liao

Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i. e. alleviate the above domain shift problem).

Zero-Shot Learning

Discriminative Learning of Latent Features for Zero-Shot Recognition

1 code implementation CVPR 2018 Yan Li, Junge Zhang, Jian-Guo Zhang, Kaiqi Huang

In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL.

Zero-Shot Learning

Fast End-to-End Trainable Guided Filter

1 code implementation CVPR 2018 Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map.

Mixed Supervised Object Detection with Robust Objectness Transfer

no code implementations27 Feb 2018 Yan Li, Junge Zhang, Kaiqi Huang, Jian-Guo Zhang

Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD.

Multiple Instance Learning object-detection +1

MSC: A Dataset for Macro-Management in StarCraft II

2 code implementations9 Oct 2017 Huikai Wu, Junge Zhang, Kaiqi Huang

We also split MSC into training, validation and test set for the convenience of evaluation and comparison.

Management Starcraft +1

GP-GAN: Towards Realistic High-Resolution Image Blending

2 code implementations21 Mar 2017 Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.

Conditional Image Generation

Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation

no code implementations ICCV 2015 Lianrui Fu, Junge Zhang, Kaiqi Huang

Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structure models.

Pose Estimation

GRSA: Generalized Range Swap Algorithm for the Efficient Optimization of MRFs

no code implementations CVPR 2015 Kangwei Liu, Junge Zhang, Peipei Yang, Kaiqi Huang

al propose the range move algorithms, which are one of the most successful solvers to this problem.

Cannot find the paper you are looking for? You can Submit a new open access paper.