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 investigate the capability of the global context, we compare four mathematical models and observe the global context encoded in the category disentangled conditional generative model could give more guidance as "know what is task irrelevant will also know what is relevant". Based on this observation, we define a novel Category Disentangled Global Context (CDGC) and devise a deep network to obtain it. By attending CDGC, the baseline networks could identify the objects of interest more accurately, thus improving the performance. We apply the framework to many different network architectures and compare with the state-of-the-art on four publicly available datasets. Extensive results validate the effectiveness and superiority of our approach. Code will be made public upon paper acceptance.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
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) …
image-classificationImage ClassificationGlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction
Attaching attributes (such as color, shape, state, action) to object categories is an important computer vision problem. Attribute prediction has seen exciting recent progress and is often formulated as a multi-label cla…
AttributeMulti-Label ClassificationMUlTI-LABEL-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 CloudsDisentangled Interaction Representation for One-Stage Human-Object Interaction Detection
Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction; h…
DecoderHuman-Object Interaction DetectionPose EstimationReasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object Detection
In this paper, we address the large-scale object detection problem with thousands of categories, which poses severe challenges due to long-tail data distributions, heavy occlusions, and class ambiguities. However, the do…
Objectobject-detectionObject Detection