Search Results for author: Heng-Tao Shen

Found 8 papers, 6 papers with code

Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric

1 code implementation3 Jul 2024 Xiruo Jiang, Yazhou Yao, Xili Dai, Fumin Shen, Xian-Sheng Hua, Heng-Tao Shen

Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval.

Diversity Metric Learning

Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

no code implementations17 Feb 2024 Huafeng Liu, Mengmeng Sheng, Zeren Sun, Yazhou Yao, Xian-Sheng Hua, Heng-Tao Shen

Specifically, we propose Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training.

Learning with noisy labels

Hierarchical Graph Pattern Understanding for Zero-Shot VOS

1 code implementation15 Dec 2023 Gensheng Pei, Fumin Shen, Yazhou Yao, Tao Chen, Xian-Sheng Hua, Heng-Tao Shen

However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene.

Decoder Graph Neural Network +6

Holistic Prototype Attention Network for Few-Shot VOS

1 code implementation16 Jul 2023 Yin Tang, Tao Chen, Xiruo Jiang, Yazhou Yao, Guo-Sen Xie, Heng-Tao Shen

Existing methods have demonstrated that the domain agent-based attention mechanism is effective in FSVOS by learning the correlation between support images and query frames.

Graph Attention Semantic Segmentation +2

Co-attention Propagation Network for Zero-Shot Video Object Segmentation

1 code implementation8 Apr 2023 Gensheng Pei, Yazhou Yao, Fumin Shen, Dan Huang, Xingguo Huang, Heng-Tao Shen

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects.

Decoder Optical Flow Estimation +4

Attention Map Guided Transformer Pruning for Edge Device

1 code implementation4 Apr 2023 Junzhu Mao, Yazhou Yao, Zeren Sun, Xingguo Huang, Fumin Shen, Heng-Tao Shen

Then we combine the similarity and first-order gradients of key tokens along the query dimension for token importance estimation and remove redundant key and value tokens to further reduce the inference complexity.

Person Re-Identification

Towards Automatic Construction of Diverse, High-quality Image Dataset

no code implementations22 Aug 2017 Yazhou Yao, Jian Zhang, Fumin Shen, Li Liu, Fan Zhu, Dongxiang Zhang, Heng-Tao Shen

To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries.

Diversity Image Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.