TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

TL;DR

This paper introduces TS2C, a method that improves weakly supervised object detection by mining tighter bounding boxes using surrounding segmentation context, leading to state-of-the-art results on VOC benchmarks.

Contribution

TS2C leverages surrounding segmentation context to suppress low-quality candidates and discover more accurate bounding boxes in weakly supervised object detection.

Findings

Achieved 48.0% mAP on VOC 2007

Achieved 44.4% mAP on VOC 2012

State-of-the-art performance on benchmarks

Abstract

This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C). We observe that object candidates mined through current multiple instance learning methods are usually trapped to discriminative object parts, rather than the entire object. TS2C leverages surrounding segmentation context derived from weakly-supervised segmentation to suppress such low-quality distracting candidates and boost the high-quality ones. Specifically, TS2C is developed based on two key properties of desirable bounding boxes: 1) high purity, meaning most pixels in the box are with high object response, and 2) high completeness, meaning the box covers high object response pixels comprehensively. With such novel and computable criteria, more tight candidates can be discovered for learning a better object detector. With TS2C, we obtain 48.0% and 44.4% mAP scores on VOC 2007 and 2012 benchmarks, which are the new state-of-the-arts.