345 citations · 659 across the 21 of their papers we have counts for
23 papers
DeGuNet: Depth-Guided Ultra-Compact Backbones for Efficient LiDAR-Camera 3D Detection
Haifa Zhang, Yijing Wang, Peixi Peng +1
In autonomous driving perception, the fusion of LiDAR and camera modalities has become the dominant paradigm for 3D object detection. However, current multi-modal frameworks heavil…
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
Dong Xiao, Guangyao Chen, Peixi Peng +4
Anomaly detection is essential for the safety and reliability of autonomous driving systems. Current methods often focus on detection accuracy but neglect response time, which is c…
Delta-Triplane Transformers as Occupancy World Models
Haoran Xu, Peixi Peng, Guang Tan +3
Occupancy World Models (OWMs) aim to predict future scenes via 3D voxelized representations of the environment to support intelligent motion planning. Existing approaches typically…
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection
Mingyi Guo, Yuyang Liu, Zhiyuan Yan +3
Incremental object detection is fundamentally challenged by catastrophic forgetting. A major factor contributing to this issue is background shift, where background categories in s…
Sensitivity Decouple Learning for Image Compression Artifacts Reduction
Li Ma, Yifan Zhao, Peixi Peng +1
With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevai…
MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control
Liwen Zhu, Peixi Peng, Zongqing Lu +1
Traffic signal control has a great impact on alleviating traffic congestion in modern cities. Deep reinforcement learning (RL) has been widely used for this task in recent years, d…
Adaptive Discovering and Merging for Incremental Novel Class Discovery
Guangyao Chen, Peixi Peng, Yangru Huang +2
One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner. The central challenge is twofold: discovering and learnin…
Noisy Spiking Actor Network for Exploration
Ding Chen, Peixi Peng, Tiejun Huang +1
As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies. Spiking neural networks (SNNs), due to their…
Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning
Ding Chen, Peixi Peng, Tiejun Huang +1
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a prom…
Learning Sparse Neural Networks with Identity Layers
Mingjian Ni, Guangyao Chen, Xiawu Zheng +3
The sparsity of Deep Neural Networks is well investigated to maximize the performance and reduce the size of overparameterized networks as possible. Existing methods focus on pruni…
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification
Yunpeng Zhai, Peixi Peng, Mengxi Jia +4
Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discrimina…
Picking Up Quantization Steps for Compressed Image Classification
Li Ma, Peixi Peng, Guangyao Chen +3
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 screens…
Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning
Zeyin Song, Yifan Zhao, Yujun Shi +3
Few-shot class-incremental learning (FSCIL) aims at learning to classify new classes continually from limited samples without forgetting the old classes. The mainstream framework t…
Training Full Spike Neural Networks via Auxiliary Accumulation Pathway
Guangyao Chen, Peixi Peng, Guoqi Li +1
Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Ne…
Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection
Lantian Xue, Yixiong Zou, Peixi Peng +2
Person Re-identification (Re-ID) has attracted great attention due to its promising real-world applications. However, in practice, it is always costly to annotate the training data…
Deep Reinforcement Learning with Spiking Q-learning
Ding Chen, Peixi Peng, Tiejun Huang +1
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a prom…
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
Guangyao Chen, Peixi Peng, Li Ma +3
Recently, the generalization behavior of Convolutional Neural Networks (CNN) is gradually transparent through explanation techniques with the frequency components decomposition. Ho…
Adversarial Reciprocal Points Learning for Open Set Recognition
Guangyao Chen, Peixi Peng, Xiangqian Wang +1
Open set recognition (OSR), aiming to simultaneously classify the seen classes and identify the unseen classes as 'unknown', is essential for reliable machine learning.The key chal…
MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control
Liwen Zhu, Peixi Peng, Zongqing Lu +2
Traffic signal control aims to coordinate traffic signals across intersections to improve the traffic efficiency of a district or a city. Deep reinforcement learning (RL) has been…
Learning Open Set Network with Discriminative Reciprocal Points
Guangyao Chen, Limeng Qiao, Yemin Shi +5
Open set recognition is an emerging research area that aims to simultaneously classify samples from predefined classes and identify the rest as 'unknown'. In this process, one of t…
Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
Zongxian Li, Qixiang Ye, Chong Zhang +3
Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely i…
Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
Yangru Huang, Peixi Peng, Yi Jin +3
Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotat…
Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration
Peixi Peng, Junliang Xing
Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized…