Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

2020-10-22 · NeurIPS 2020 12 · Zeyi Huang, Yang Zou, Vijayakumar Bhagavatula, Dong Huang

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.

📄 PDF Abstract BibTeX arXiv:2010.12023

Code (1)

DeLightCMU/CASD 공식 구현 pytorch

Tasks

Objectobject-detection Object Detection Weakly Supervised Object Detection

Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation

2023-02-27 · Rongtao Xu, Changwei Wang, Jiaxi Sun, Shibiao Xu 외

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due t…

Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Self-supervised Attention Model for Weakly Labeled Audio Event Classification

2019-08-07 · Bongjun Kim, Shabnam Ghaffarzadegan

We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self…

Classification General Classification

A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation

2021-08-14 · Qi Zhao, Binghao Liu, Shuchang Lyu, Huojin Chen

Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between …

Few-Shot Semantic Segmentation Segmentation Semantic Segmentation

Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection

2022-07-12 · Jiashuo Yu, Jinyu Liu, Ying Cheng, Rui Feng 외

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early …

Anomaly Detection In Surveillance Videos audio-visual learning Multiple Instance Learning

Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching

2021-12-17 · Dingwen Zhang, Wenyuan Zeng, Guangyu Guo, Chaowei Fang 외

Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches would contain redundant feature extraction…

Knowledge Distillation Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation