Category Disentangled Context: Turning Category-irrelevant Features Into Treasures
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.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Attending Category Disentangled Global Context for Image Classification
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 ClassificationA Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection
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 CloudsDAFD: Domain Adaptation via Feature Disentanglement for Image Classification
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+3Attribute Group Editing for Reliable Few-shot Image Generation
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 GenerationDeep Image Clustering with Category-Style Representation
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