Search Results for author: Peixi Peng

Found 25 papers, 9 papers with code

Sensitivity Decouple Learning for Image Compression Artifacts Reduction

no code implementations15 May 2024 Li Ma, Yifan Zhao, Peixi Peng, Yonghong Tian

Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, ie, the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree.

Image Compression

Noisy Spiking Actor Network for Exploration

no code implementations7 Mar 2024 Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian

As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies.

Continuous Control Efficient Exploration +2

Adaptive Discovering and Merging for Incremental Novel Class Discovery

no code implementations6 Mar 2024 Guangyao Chen, Peixi Peng, Yangru Huang, Mengyue Geng, Yonghong Tian

One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner.

Class Incremental Learning Diversity +3

Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning

no code implementations9 Jan 2024 Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian

Recently, the surrogate gradient method has been utilized for training multi-layer SNNs, which allows SNNs to achieve comparable performance with the corresponding deep networks in this task.


DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning

1 code implementation CVPR 2024 Haoran Xu, Peixi Peng, Guang Tan, Yuan Li, Xinhai Xu, Yonghong Tian

We explore visual reinforcement learning (RL) using two complementary visual modalities: frame-based RGB camera and event-based Dynamic Vision Sensor (DVS).

Reinforcement Learning (RL)

Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction

no code implementations CVPR 2024 Di Wen, Haoran Xu, Zhaocheng He, Zhe Wu, Guang Tan, Peixi Peng

In temporal dimension we extract the temporal interaction features and adapt a pyramidal pooling layer to generate the interaction probability for each agent.

Autonomous Driving Trajectory Prediction

Learning Sparse Neural Networks with Identity Layers

no code implementations14 Jul 2023 Mingjian Ni, Guangyao Chen, Xiawu Zheng, Peixi Peng, Li Yuan, Yonghong Tian

Applying such theory, we propose a plug-and-play CKA-based Sparsity Regularization for sparse network training, dubbed CKA-SR, which utilizes CKA to reduce feature similarity between layers and increase network sparsity.

Population-Based Evolutionary Gaming for Unsupervised Person Re-identification

no code implementations8 Jun 2023 Yunpeng Zhai, Peixi Peng, Mengxi Jia, Shiyong Li, Weiqiang Chen, Xuesong Gao, Yonghong Tian

Extensive experiments demonstrate that (1) CRS approximately measures the performance of models without labeled samples; (2) and PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning.

Diversity Knowledge Distillation +1

Picking Up Quantization Steps for Compressed Image Classification

1 code implementation21 Apr 2023 Li Ma, Peixi Peng, Guangyao Chen, Yifan Zhao, Siwei Dong, Yonghong Tian

The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file.

Classification Image Classification +1

Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning

1 code implementation CVPR 2023 Zeyin Song, Yifan Zhao, Yujun Shi, Peixi Peng, Li Yuan, Yonghong Tian

However, in this work, we find that the CE loss is not ideal for the base session training as it suffers poor class separation in terms of representations, which further degrades generalization to novel classes.

Contrastive Learning Few-Shot Class-Incremental Learning +1

Training Full Spike Neural Networks via Auxiliary Accumulation Pathway

2 code implementations27 Jan 2023 Guangyao Chen, Peixi Peng, Guoqi Li, Yonghong Tian

The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN.

Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection

no code implementations10 Mar 2022 Lantian Xue, Yixiong Zou, Peixi Peng, Yonghong Tian, Tiejun Huang

To solve this problem, we propose the Annotation Efficient Person Re-Identification method to select image pairs from an alternative pair set according to the fallibility and diversity of pairs, and train the Re-ID model based on the annotation.

Clustering Diversity +1

Deep Reinforcement Learning with Spiking Q-learning

no code implementations21 Jan 2022 Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian

With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption.

Atari Games Q-Learning +2

Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain

1 code implementation ICCV 2021 Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, Yonghong Tian

This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.

Adversarial Attack Data Augmentation +2

Adversarial Reciprocal Points Learning for Open Set Recognition

1 code implementation1 Mar 2021 Guangyao Chen, Peixi Peng, Xiangqian Wang, Yonghong Tian

Then, an adversarial margin constraint is proposed to reduce the open space risk by limiting the latent open space constructed by reciprocal points.

General Classification Open Set Learning

MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control

3 code implementations4 Jan 2021 Liwen Zhu, Peixi Peng, Zongqing Lu, Xiangqian Wang, Yonghong Tian

To make the policy learned from a training scenario generalizable to new unseen scenarios, a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method is proposed to learn the decentralized policy for each intersection that considers neighbor information in a latent way.

Meta-Learning Multi-agent Reinforcement Learning +2

Learning Open Set Network with Discriminative Reciprocal Points

1 code implementation ECCV 2020 Guangyao Chen, Limeng Qiao, Yemin Shi, Peixi Peng, Jia Li, Tiejun Huang, ShiLiang Pu, Yonghong Tian

In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data.

Open Set Learning

Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

no code implementations25 May 2019 Yangru Huang, Peixi Peng, Yi Jin, Yidong Li, Junliang Xing, Shiming Ge

In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part.

Diversity Domain Adaptation +3

Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration

no code implementations5 Dec 2018 Peixi Peng, Junliang Xing

To learn the multi-agent cooperation effectively and tackle the sub-optimality of demonstration, a self-improving learning method is proposed: On the one hand, the centralized state-action values are initialized by the demonstration and updated by the learned decentralized policy to improve the sub-optimality.

Visual Tracking via Spatially Aligned Correlation Filters Network

no code implementations ECCV 2018 Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background.

Visual Tracking

Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification

no code implementations CVPR 2016 Peixi Peng, Tao Xiang, Yao-Wei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, Yonghong Tian

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training.

Dictionary Learning Person Re-Identification +1

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