# Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

arXiv: https://arxiv.org/abs/2010.12023 · HTML: https://mlsanity.com/paper/2010.12023/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 30 of 50)

- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection](https://mlsanity.com/paper/2207.03482/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Open-Vocabulary Point-Cloud Object Detection without 3D Annotation](https://mlsanity.com/paper/2304.00788/) (2023)
- [Point-to-Box Network for Accurate Object Detection via Single Point Supervision](https://mlsanity.com/paper/2207.06827/) (2022)
- [Distilling a Powerful Student Model via Online Knowledge Distillation](https://mlsanity.com/paper/2103.14473/) (2021)
- [Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters](https://mlsanity.com/paper/2108.01499/) (2021)
- [LGD: Label-guided Self-distillation for Object Detection](https://mlsanity.com/paper/2109.11496/) (2021)
- [Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching](https://mlsanity.com/paper/2112.09459/) (2021)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Object Discovery via Contrastive Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2208.07576/) (2022)
- [Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations](https://mlsanity.com/paper/2303.16891/) (2023)
- [Semantic-aware SAM for Point-Prompted Instance Segmentation](https://mlsanity.com/paper/2312.15895/) (2023)
- [Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity](https://mlsanity.com/paper/2110.14191/) (2021)
- [A Novel Plug-in Module for Fine-Grained Visual Classification](https://mlsanity.com/paper/2202.03822/) (2022)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection](https://mlsanity.com/paper/2207.12104/) (2022)
- [Salvage of Supervision in Weakly Supervised Object Detection](https://mlsanity.com/paper/2106.04073/) (2021)
- [ALWOD: Active Learning for Weakly-Supervised Object Detection](https://mlsanity.com/paper/2309.07914/) (2023)
- [GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization](https://mlsanity.com/paper/2507.10935/) (2025)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening](https://mlsanity.com/paper/2412.06243/) (2024)
- [CaT: Weakly Supervised Object Detection with Category Transfer](https://mlsanity.com/paper/2108.07487/) (2021)
- [Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information](https://mlsanity.com/paper/2204.10068/) (2022)
- [EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2212.07629/) (2022)
- [Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2304.12161/) (2023)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning](https://mlsanity.com/paper/2108.03704/) (2021)
- [Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors](https://mlsanity.com/paper/2209.11795/) (2022)

## Abstract (arXiv)

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.