219 citations · 297 across the 14 of their papers we have counts for
14 papers
Balancing Logit Variation for Long-tailed Semantic Segmentation
Yuchao Wang, Jingjing Fei, Haochen Wang +5
Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get sque…
Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation
Haochen Wang, Yujun Shen, Jingjing Fei +4
Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly l…
SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers
Guoqiang Jin, Fan Yang, Mingshan Sun +7
Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object det…
Efficient Masked Autoencoders with Self-Consistency
Zhaowen Li, Yousong Zhu, Zhiyang Chen +5
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training me…
Exploring Stochastic Autoregressive Image Modeling for Visual Representation
Yu Qi, Fan Yang, Yousong Zhu +4
Autoregressive language modeling (ALM) have been successfully used in self-supervised pre-training in Natural language processing (NLP). However, this paradigm has not achieved com…
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Zhiyang Chen, Yousong Zhu, Zhaowen Li +8
Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensi…
Learning from Future: A Novel Self-Training Framework for Semantic Segmentation
Ye Du, Yujun Shen, Haochen Wang +6
Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and…
Uni6Dv2: Noise Elimination for 6D Pose Estimation
Mingshan Sun, Ye Zheng, Tianpeng Bao +5
Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images. We discover that the principal reasons of Un…
Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation
Xiaoke Jiang, Donghai Li, Hao Chen +3
As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use di…
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Zhaowen Li, Yousong Zhu, Fan Yang +9
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images…
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
Yuchao Wang, Haochen Wang, Yujun Shen +6
The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predict…
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
Jiawei Yu, Ye Zheng, Xiang Wang +4
Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representa…
Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization
Ye Zheng, Xiang Wang, Rui Deng +3
The essence of unsupervised anomaly detection is to learn the compact distribution of normal samples and detect outliers as anomalies in testing. Meanwhile, the anomalies in real-w…
MST: Masked Self-Supervised Transformer for Visual Representation
Zhaowen Li, Zhiyang Chen, Fan Yang +8
Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual…