128 citations · 411 across the 16 of their papers we have counts for
14 papers · 1 filter
A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
Minghao Chen, Zepeng Gao, Shuai Zhao +4
Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set…
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Shuai Zhao, Xiaohan Wang, Linchao Zhu +1
One fascinating aspect of pre-trained vision-language models~(VLMs) learning under language supervision is their impressive zero-shot generalization capability. However, this abili…
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
Shuai Zhao, Ruijie Quan, Linchao Zhu +1
Pre-trained vision-language models~(VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre-traine…
Slimmable Networks for Contrastive Self-supervised Learning
Shuai Zhao, Linchao Zhu, Xiaohan Wang +1
Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge dis…
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
Shuai Zhao, Linchao Zhu, Xiaohan Wang +1
Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling com…
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
Tu Zheng, Shuai Zhao, Yang Liu +2
Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-base…
ES-Net: Erasing Salient Parts to Learn More in Re-Identification
Dong Shen, Shuai Zhao, Jinming Hu +3
As an instance-level recognition problem, re-identification (re-ID) requires models to capture diverse features. However, with continuous training, re-ID models pay more and more a…
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Shuai Zhao, Liguang Zhou, Wenxiao Wang +3
The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with…
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Wenxiao Wang, Minghao Chen, Shuai Zhao +6
Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a compu…
Adversarial-Learned Loss for Domain Adaptation
Minghao Chen, Shuai Zhao, Haifeng Liu +1
Recently, remarkable progress has been made in learning transferable representation across domains. Previous works in domain adaptation are majorly based on two techniques: domain-…
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
Wenxiao Wang, Shuai Zhao, Minghao Chen +3
Neural network pruning is one of the most popular methods of accelerating the inference of deep convolutional neural networks (CNNs). The dominant pruning methods, filter-level pru…
Region Mutual Information Loss for Semantic Segmentation
Shuai Zhao, Yang Wang, Zheng Yang +1
Semantic segmentation is a fundamental problem in computer vision. It is considered as a pixel-wise classification problem in practice, and most segmentation models use a pixel-wis…
Correlation Maximized Structural Similarity Loss for Semantic Segmentation
Shuai Zhao, Boxi Wu, Wenqing Chu +2
Most semantic segmentation models treat semantic segmentation as a pixel-wise classification task and use a pixel-wise classification error as their optimization criterions. Howeve…
Improving Semantic Segmentation via Dilated Affinity
Boxi Wu, Shuai Zhao, Wenqing Chu +2
Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly bas…