no code implementations • ECCV 2020 • Junsong Fan, Zhao-Xiang Zhang, Tieniu Tan
Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model's robustness to learn from multiple seeds.
3 code implementations • 18 Mar 2024 • Hongbo Zhao, Bolin Ni, Haochen Wang, Junsong Fan, Fei Zhu, Yuxi Wang, Yuntao Chen, Gaofeng Meng, Zhaoxiang Zhang
(i) For unwanted knowledge, efficient and effective deleting is crucial.
no code implementations • 31 Jan 2024 • Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, Zhaoxiang Zhang
In this paper, we propose a novel approach to achieve object segmentation in 3D Gaussian via an interactive procedure without any training process and learned parameters.
1 code implementation • 21 Dec 2023 • Haochen Wang, Junsong Fan, Yuxi Wang, Kaiyou Song, Tiancai Wang, Xiangyu Zhang, Zhaoxiang Zhang
To empower the model as a teacher, we propose Hard Patches Mining (HPM), predicting patch-wise losses and subsequently determining where to mask.
no code implementations • 30 Sep 2023 • Hongyang Pan, Yanheng Liu, Geng Sun, Junsong Fan, Shuang Liang, Chau Yuen
For UTTOP, we first introduce a pretreatment method, and then use an improved particle swarm optimization with Normal distribution initialization, Genetic mechanism, Differential mechanism and Pursuit operator (PSO-NGDP) to deal with this sub optimization problem.
1 code implementation • NeurIPS 2023 • Haochen Wang, Junsong Fan, Yuxi Wang, Kaiyou Song, Tong Wang, Zhaoxiang Zhang
As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident.
1 code implementation • ICCV 2023 • Xiaojun Tang, Junsong Fan, Chuanchen Luo, Zhaoxiang Zhang, Man Zhang, Zongyuan Yang
Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission of ambiguous information and enhancing the discriminability of snippet-level representations.
Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization
no code implementations • 4 Jun 2023 • Haochen Wang, Yuchao Wang, Yujun Shen, Junsong Fan, Yuxi Wang, Zhaoxiang Zhang
A common practice is to select the highly confident predictions as the pseudo-ground-truths for each pixel, but it leads to a problem that most pixels may be left unused due to their unreliability.
1 code implementation • CVPR 2023 • Haochen Wang, Kaiyou Song, Junsong Fan, Yuxi Wang, Jin Xie, Zhaoxiang Zhang
We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task.
no code implementations • 16 Mar 2023 • Wenjian Wang, Lijuan Duan, Yuxi Wang, Junsong Fan, Zhi Gong, Zhaoxiang Zhang
Research into Cross-Domain Few-Shot (CDFS) has emerged to address this issue, forming a more challenging and realistic setting.
1 code implementation • 25 Oct 2022 • Junsong Fan, Zhaoxiang Zhang, Tieniu Tan
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation.
1 code implementation • CVPR 2022 • Zengjie Song, Yuxi Wang, Junsong Fan, Tieniu Tan, Zhaoxiang Zhang
Sound source localization in visual scenes aims to localize objects emitting the sound in a given image.
no code implementations • CVPR 2022 • Jing Li, Junsong Fan, Zhaoxiang Zhang
Existing methods usually generate pseudo labels from class activation map (CAM) and then train a segmentation model.
no code implementations • CVPR 2022 • Wenjian Wang, Lijuan Duan, Yuxi Wang, Qing En, Junsong Fan, Zhaoxiang Zhang
To remedy this problem, we propose an interesting and challenging cross-domain few-shot semantic segmentation task, where the training and test tasks perform on different domains.
1 code implementation • CVPR 2020 • Junsong Fan, Zhaoxiang Zhang, Chunfeng Song, Tieniu Tan
Image-level weakly-supervised semantic segmentation (WSSS) aims at learning semantic segmentation by adopting only image class labels.
1 code implementation • 27 Nov 2018 • Junsong Fan, Zhao-Xiang Zhang, Tieniu Tan, Chunfeng Song, Jun Xiao
Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels.