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.

Comprehensive Attention Self-Distillation (CASD) is a new training approach for Weakly Supervised Object Detection (WSOD) that enables consistent object detection across different transformations of the same images by computing comprehensive attention and conducting self-distillation on the WSOD networks.