38 citations · 112 across the 14 of their papers we have counts for
14 papers
A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning
Yinmin Zhang, Jie Liu, Chuming Li +4
Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most…
MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning
Jie Liu, Yinmin Zhang, Chuming Li +4
Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making…
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
Chuming Li, Jie Liu, Yinmin Zhang +5
Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policie…
Residual Relaxation for Multi-view Representation Learning
Yifei Wang, Zhengyang Geng, Feng Jiang +4
Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we no…
GLiT: Neural Architecture Search for Global and Local Image Transformer
Boyu Chen, Peixia Li, Chuming Li +6
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones a…
BN-NAS: Neural Architecture Search with Batch Normalization
Boyu Chen, Peixia Li, Baopu Li +5
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required b…
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Boyu Chen, Peixia Li, Baopu Li +6
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network pro…
Inception Convolution with Efficient Dilation Search
Jie Liu, Chuming Li, Feng Liang +5
As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computa…
DETR for Crowd Pedestrian Detection
Matthieu Lin, Chuming Li, Xingyuan Bu +5
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…
Adaptive Gradient Method with Resilience and Momentum
Jie Liu, Chen Lin, Chuming Li +4
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some r…
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Ronghao Guo, Chen Lin, Chuming Li +4
One-shot NAS method has attracted much interest from the research community due to its remarkable training efficiency and capacity to discover high performance models. However, the…
Improving One-shot NAS by Suppressing the Posterior Fading
Xiang Li, Chen Lin, Chuming Li +4
There is a growing interest in automated neural architecture search (NAS). To improve the efficiency of NAS, previous approaches adopt weight sharing method to force all models sha…
AM-LFS: AutoML for Loss Function Search
Chuming Li, Yuan Xin, Chen Lin +4
Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to…
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Chen Lin, Minghao Guo, Chuming Li +5
Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an…