most citedSemi-supervised Models are Strong Unsupervised Domain Adaptation Learners

15 citations · 42 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV202212 cited

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

Chenhang He, Ruihuang Li, Shuai Li +1

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cl…

cs.CV20221 cited

Towards Robust 2D Convolution for Reliable Visual Recognition

Lida Li, Shuai Li, Kun Wang +2

2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN). However, Conv2d is vu…

cs.CV20221 cited

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

Ruihuang Li, Shuai Li, Chenhang He +3

Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One p…

cs.CV20225 cited

A Dual Weighting Label Assignment Scheme for Object Detection

Shuai Li, Chenhang He, Ruihuang Li +1

Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods…

cs.LG202115 cited

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners

Yabin Zhang, Haojian Zhang, Bin Deng +3

Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn eff…

cs.CV20218 cited

Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation

Minghan Li, Shuai Li, Lida Li +1

Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth boundin…