Object-Aware Instance Labeling for Weakly Supervised Object Detection

TL;DR

This paper introduces improved instance labeling techniques for weakly supervised object detection, enhancing the iterative training process by focusing on whole-object coverage and spatial restrictions, leading to better detection accuracy.

Contribution

It proposes novel instance labeling methods that address partial object coverage and inter-object negative labeling, improving weakly supervised detection performance.

Findings

Significant accuracy improvements on PASCAL VOC datasets

Effective handling of partial object regions

Enhanced negative region selection

Abstract

Weakly supervised object detection (WSOD), where a detector is trained with only image-level annotations, is attracting more and more attention. As a method to obtain a well-performing detector, the detector and the instance labels are updated iteratively. In this study, for more efficient iterative updating, we focus on the instance labeling problem, a problem of which label should be annotated to each region based on the last localization result. Instead of simply labeling the top-scoring region and its highly overlapping regions as positive and others as negative, we propose more effective instance labeling methods as follows. First, to solve the problem that regions covering only some parts of the object tend to be labeled as positive, we find regions covering the whole object focusing on the context classification loss. Second, considering the situation where the other objects contained in the image can be labeled as negative, we impose a spatial restriction on regions labeled as negative. Using these instance labeling methods, we train the detector on the PASCAL VOC 2007 and 2012 and obtain significantly improved results compared with other state-of-the-art approaches.