Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

Abstract

Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on salient objects, clustered objects and discriminative object parts. Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images. To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. To balance feature learning among all object instances, CASD computes the comprehensive attention aggregated from multiple transformations and feature layers of the same images. To enforce consistent spatial supervision on objects, CASD conducts self-distillation on the WSOD networks, such that the comprehensive attention is approximated simultaneously by multiple transformations and feature layers of the same images. CASD produces new state-of-the-art WSOD results on standard benchmarks such as PASCAL VOC 2007/2012 and MS-COCO.

arXiv commentNeural Information Processing Systems (NeurIPS 2020)

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• Dual Attention Network for Scene Segmentation
• Self-Challenging Improves Cross-Domain Generalization
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• Multi-Task Incremental Learning for Object Detection
• Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
• Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer

Cited by in corpus (5)

• Knowledge Distillation: A Survey
• Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
• Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
• Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
• Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection