no code implementations • 15 Sep 2023 • Xiaonan Lu, Jianlong Yuan, Ruigang Niu, Yuan Hu, Fan Wang
Therefore, they cannot be directly applied to cope with image change understanding (ICU), which requires models to capture actual changes between multiple images and describe them in language.
1 code implementation • 28 Jul 2023 • Yuan Hu, Jianlong Yuan, Congcong Wen, Xiaonan Lu, Xiang Li
This dataset consists of human-annotated captions and visual question-answer pairs, allowing for a comprehensive assessment of VLMs in the context of RS.
1 code implementation • 26 Apr 2023 • Fangjian Lin, Jianlong Yuan, Sitong Wu, Fan Wang, Zhibin Wang
Interestingly, the ranking of these spatial token mixers also changes under our UniNeXt, suggesting that an excellent spatial token mixer may be stifled due to a suboptimal general architecture, which further shows the importance of the study on the general architecture of vision backbone.
no code implementations • CVPR 2023 • Chaohui Yu, Qiang Zhou, Jingliang Li, Jianlong Yuan, Zhibin Wang, Fan Wang
In this work, we propose a novel and data-efficient framework for WILSS, named FMWISS.
1 code implementation • CVPR 2023 • Fei Du, Jianlong Yuan, Zhibin Wang, Fan Wang
To this end, we propose an efficient method to correct the mask with a lightweight mask correction network.
1 code implementation • 30 Aug 2022 • Jianlong Yuan, Qian Qi, Fei Du, Zhibin Wang, Fan Wang, Yifan Liu
Inspired by the recent progress on semantic directions on feature-space, we propose to include augmentations in feature space for efficient distillation.
1 code implementation • 24 Aug 2022 • Jianlong Yuan, Jinchao Ge, Zhibin Wang, Yifan Liu
More specifically, we use the pseudo-labels generated by a mean teacher to supervise the student network to achieve a mutual knowledge distillation between the two branches.
no code implementations • 2 Aug 2022 • Mengzhu Wang, Jianlong Yuan, Qi Qian, Zhibin Wang, Hao Li
Further, we provide an in-depth analysis of the mechanism and rational behind our approach, which gives us a better understanding of why leverage logits in lieu of features can help domain generalization.
1 code implementation • ICCV 2021 • Jianlong Yuan, Yifan Liu, Chunhua Shen, Zhibin Wang, Hao Li
Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics.
no code implementations • 17 Nov 2020 • Jianlong Yuan, Zelu Deng, Shu Wang, Zhenbo Luo
Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image.
Ranked #20 on Semantic Segmentation on Cityscapes test (using extra training data)