no code implementations • 22 Apr 2025 • Wei Zhuo, Zhiyue Tang, Wufeng Xue, Hao Ding, Linlin Shen
Few-shot semantic segmentation has gained increasing interest due to its generalization capability, i. e., segmenting pixels of novel classes requiring only a few annotated images.
1 code implementation • 4 Dec 2024 • Jiongtong Hu, Wei Zhuo, Jun Cheng, Yingying Liu, Wufeng Xue, Dong Ni
Effective solution for such a multi-plane segmentation (MPS) problem is highly demanded for medical images, yet has not been well investigated.
no code implementations • 16 Nov 2024 • Wei Zhuo, Zemin Liu, Bryan Hooi, Bingsheng He, Guang Tan, Rizal Fathony, Jia Chen
Label imbalance and homophily-heterophily mixture are the fundamental problems encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection (GFD) tasks.
1 code implementation • 20 Jul 2024 • Beibei Li, Beihong Jin, Yisong Yu, Yiyuan Zheng, Jiageng Song, Wei Zhuo, Tao Xiang
Moreover, OPAL employs a two-stage training strategy, in which the pre-train is to generate soft interests from historical interactions under the guidance of orthogonal hyper-categories of micro-videos and the fine-tune is to reinforce the degree of disentanglement among the interests and learn the temporal evolution of each interest of each user.
no code implementations • 30 Jun 2024 • Wei Zhuo, Han Yu, Guang Tan, Xiaoxiao Li
However, their application to directed graphs (digraphs) presents unique challenges, primarily due to the inherent asymmetry in node relationships.
1 code implementation • 21 Jun 2024 • Wei Zhuo, Guang Tan
In the inference stage, the graph-level representations learned by the GNN encoder are directly used to compute the similarity score without using AReg again to speed up inference.
no code implementations • CVPR 2024 • Weizhao He, Yang Zhang, Wei Zhuo, Linlin Shen, Jiaqi Yang, Songhe Deng, Liang Sun
Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples.
1 code implementation • 18 Jan 2024 • Songhe Deng, Wei Zhuo, Jinheng Xie, Linlin Shen
Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels.
Ranked #7 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
no code implementations • 2 Dec 2022 • Dianwen Mei, Wei Zhuo, Jiandong Tian, Guangming Lu, Wenjie Pei
To circumvent these two challenges, we propose to activate the discriminability of novel classes explicitly in both the feature encoding stage and the prediction stage for segmentation.
1 code implementation • 19 May 2022 • Beibei Li, Beihong Jin, Jiageng Song, Yisong Yu, Yiyuan Zheng, Wei Zhuo
With the rapid increase of micro-video creators and viewers, how to make personalized recommendations from a large number of candidates to viewers begins to attract more and more attention.
no code implementations • 24 Feb 2022 • YuAn Wang, Wei Zhuo, Yucong Li, Zhi Wang, Qi Ju, Wenwu Zhu
To solve this problem, we proposed a bootstrapped training scheme for semantic segmentation, which fully leveraged the global semantic knowledge for self-supervision with our proposed PGG strategy and CAE module.
Ranked #21 on
Unsupervised Semantic Segmentation
on COCO-Stuff-27
no code implementations • 19 Nov 2021 • Wei Zhuo, Guang Tan
Graph Neural Networks (GNNs) have received increasing attention for representation learning in various machine learning tasks.
1 code implementation • ICCV 2021 • Haoxi Ran, Wei Zhuo, Jun Liu, Li Lu
We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation.
Ranked #21 on
3D Point Cloud Classification
on ModelNet40
no code implementations • 27 Jun 2021 • Wei Zhuo, Kunchi Liu, Taofeng Xue, Beihong Jin, Beibei Li, Xinzhou Dong, He Chen, Wenhai Pan, Xuejian Zhang, Shuo Zhou
Interactions between users and videos are the major data source of performing video recommendation.
no code implementations • 23 Jun 2021 • Zejian Chen, Wei Zhuo, Tianfu Wang, Wufeng Xue, Dong Ni
Based on the continuity between slices/frames and the common spatial layout of organs across volumes/sequences, we introduced a novel bootstrap self-supervised representation learning method by leveraging the predictable possibility of neighboring slices.
1 code implementation • CVPR 2022 • Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao
In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student.
no code implementations • 7 Jun 2021 • Wei Zhuo, Guang Tan
Not restricted by connectivity in the original graph, the generated views allow the model to enhance its expressive power with new and complementary perspectives from which to look at the relationship between nodes.
1 code implementation • ICCV 2021 • Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao
Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes.
Ranked #47 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
no code implementations • 10 Mar 2021 • Xinzhou Dong, Beihong Jin, Wei Zhuo, Beibei Li, Taofeng Xue
Many practical recommender systems provide item recommendation for different users only via mining user-item interactions but totally ignoring the rich attribute information of items that users interact with.
3 code implementations • CVPR 2020 • Qi Fan, Wei Zhuo, Chi-Keung Tang, Yu-Wing Tai
To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations.
Ranked #23 on
Few-Shot Object Detection
on MS-COCO (10-shot)
no code implementations • CVPR 2017 • Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu
In particular, while some of them aim at segmenting the image into regions, such as object or surface instances, others aim at inferring the semantic labels of given regions, or their support relationships.
no code implementations • CVPR 2015 • Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu
We tackle the problem of single image depth estimation, which, without additional knowledge, suffers from many ambiguities.