.png){kind=icon}
返回
Dynamic Semantic Complementary Network for Zero-Shot Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TETCI.2025.3573239.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Zero-Shot Learning (ZSL) transfers knowledge from seen to unseen classes by associating visual features with shared semantic information. However, semantic information consists of high-level attributes with complex visual characteristics and the contrasting low-level attributes. Existing ZSL methods tend to oversimplify visual-semantic associations by ignoring high-level attributes, resulting in incomplete utilization of semantic information and limited knowledge transfer. To address this issue, we propose a novel Dynamic Semantic Complementary Network (DSCN). Based on training a main subnet that obtains complete semantic information, DSCN dynamically calculates and selects the ignored semantic information with a novel semantic utilization metric. An auxiliary subnet is then used to learn the ignored semantic information. Finally, we deploy complementary knowledge distillation to conduct effective knowledge interactions between the two subnets. DSCN makes full use of semantic information through the mutual complementarity between two subnets. Extensive experiments on three benchmark datasets (CUB, SUN and AWA2) demonstrate that DSCN achieves superior performance by maximizing semantic utilization, surpassing existing state-of-the-art methods.
Keyword:
Zero-shot learning
image classification
semantic utilization metric
knowledge distillation
期刊
I
IF:
6.5
论文数:
1.4K
被引数:
4.5K
机构
引用论文
.png){kind=icon}
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly零拍学习 -- 综合评价好、坏、丑
OAAI
OAAI分享收藏分享收藏Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks视觉智能的知识蒸馏和师生学习: 回顾和新观点OAAI
OAAI分享收藏
查看更多内容