Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

By Zeyi Huang, Yang Zou, V. Bhagavatula, Dong Huang. 2020

146 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Ishan Misra
3. Rohit Girdhar
4. Armand Joulin
5. Jianping Gou
6. S. Maybank
7. Baosheng Yu
8. Xingyi Zhou

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Trevor Darrell
4. Xiaogang Wang
5. Ming-Hsuan Yang
6. Jitendra Malik
7. Cordelia Schmid
8. Andrew Zisserman

Citations in the corpus

• Knowledge Distillation: A Survey (2020, background): “…Wu et al. 2019b; Zhang et al. 2020c; Cui et al. 2020), object detection (Li et al. 2017; Shmelkov et al. 2017; Cun and Pun 2020; Wang et al. 2019d; Huang et al. 2020; Wei et al. 2018; Hong and Yu 2019; Chawla et al. 2021), lane detection (Hou et al. 2019), person re-identification (Wu et al.…”
• Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “Huang-NIPS-2020 [67] Faster RCNN CNN None ImageNet(tag label) Faster RCNN*(VGG16/ResNet50) Proposal attention aggregation and distillation General objects”
• Detecting Twenty-thousand Classes using Image-level Supervision (2022, methodology): “CASD [20] further introduces feature-level attention and self-distillation.”