paper-with-me

홈 › Papers

Category Disentangled Context: Turning Category-irrelevant Features Into Treasures

2021-01-01 · Keke Tang, Guodong Wei, Jie Zhu, Yuexin Ma, Runnan Chen, Zhaoquan Gu, Wenping Wang

Deep neural networks have achieved great success in computer vision, thanks to their ability in extracting category-relevant semantic features. On the contrary, irrelevant features (e.g., background and confusing parts) are usually considered to be harmful. In this paper, we bring a new perspective on the potential benefits brought by irrelevant features: they could act as references to help identify relevant ones. Therefore, (1) we formulate a novel Category Disentangled Context (CDC) and develop an adversarial deep network to encode it; (2) we investigate utilizing the CDC to improve image classification with the attention mechanism as a bridge. Extensive comparisons on four benchmarks with various backbone networks demonstrate that the CDC could bring remarkable improvements consistently, validating the usefulness of irrelevant features.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Attending Category Disentangled Global Context for Image Classification

2018-12-17 · Keke Tang, Guodong Wei, Runnan Chen, Jie Zhu 외

In this paper, we propose a general framework for image classification using the attention mechanism and global context, which could incorporate with various network architectures to improve their performance. To investi…

ClassificationGeneral Classificationimage-classificationImage Classification

A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection

2026-03-26 · SuYeon Kim, Wongyu Lee, MyeongAh Cho arxiv

3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers…

3D Anomaly DetectionContrastive LearningPoint Clouds

DAFD: Domain Adaptation via Feature Disentanglement for Image Classification

2023-01-30 · Zhize Wu, Changjiang Du, Le Zou, Ming Tan 외

A good feature representation is the key to image classification. In practice, image classifiers may be applied in scenarios different from what they have been trained on. This so-called domain shift leads to a significa…

ClassificationDisentanglementDomain Adaptationfeature selection+3

Attribute Group Editing for Reliable Few-shot Image Generation

2022-03-16 · CVPR 2022 1 · Guanqi Ding, Xinzhe Han, Shuhui Wang, Shuzhe Wu 외

Few-shot image generation is a challenging task even using the state-of-the-art Generative Adversarial Networks (GANs). Due to the unstable GAN training process and the limited training data, the generated images are oft…

AttributeDictionary LearningDiversityImage Generation

Deep Image Clustering with Category-Style Representation

2020-07-20 · ECCV 2020 8 · Junjie Zhao, Donghuan Lu, Kai Ma, Yu Zhang 외

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-s…

ClusteringDeep ClusteringImage Clustering