20 citations · 29 across the 14 of their papers we have counts for
14 papers
BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning
Hongwei Zheng, Linyuan Zhou, Han Li +3
Data mixing methods play a crucial role in semi-supervised learning (SSL), but their application is unexplored in long-tailed semi-supervised learning (LTSSL). The primary reason i…
Text2Street: Controllable Text-to-image Generation for Street Views
Jinming Su, Songen Gu, Yiting Duan +2
Text-to-image generation has made remarkable progress with the emergence of diffusion models. However, it is still a difficult task to generate images for street views based on tex…
3rd Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
Jinming Su, Wangwang Yang, Junfeng Luo +1
In order to deal with the task of video panoptic segmentation in the wild, we propose a robust integrated video panoptic segmentation solution. In our solution, we regard the video…
Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation
Jinming Su, Ruihong Yin, Xingyue Chen +1
Recently, instance segmentation has made great progress with the rapid development of deep neural networks. However, there still exist two main challenges including discovering ind…
Motion-state Alignment for Video Semantic Segmentation
Jinming Su, Ruihong Yin, Shuaibin Zhang +1
In recent years, video semantic segmentation has made great progress with advanced deep neural networks. However, there still exist two main challenges \ie, information inconsisten…
5th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentation
Wangwang Yang, Jinming Su, Yiting Duan +2
Video object segmentation (VOS) has made significant progress with the rise of deep learning. However, there still exist some thorny problems, for example, similar objects are easi…