Self-Classification Enhancement and Correction for Weakly Supervised Object Detection

TL;DR

This paper introduces a novel weakly supervised object detection framework that enhances classification accuracy by integrating intra-class binary classification and a correction algorithm, leading to improved detection performance.

Contribution

It proposes a self-classification enhancement module with intra-class binary classification and a correction algorithm to address classification ambiguities in WSOD.

Findings

Superior performance on VOC 2007 & 2012 datasets

Effective reduction of misclassified predictions

Enhanced discrimination between positive and mis-located samples

Abstract

In recent years, weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost. The success of recent WSOD models is often ascribed to the two-stage multi-class classification (MCC) task, i.e., multiple instance learning and online classification refinement. Despite achieving non-trivial progresses, these methods overlook potential classification ambiguities between these two MCC tasks and fail to leverage their unique strengths. In this work, we introduce a novel WSOD framework to ameliorate these two issues. For one thing, we propose a self-classification enhancement module that integrates intra-class binary classification (ICBC) to bridge the gap between the two distinct MCC tasks. The ICBC task enhances the network's discrimination between positive and mis-located samples in a class-wise manner and forges a mutually reinforcing relationship with the MCC task. For another, we propose a self-classification correction algorithm during inference, which combines the results of both MCC tasks to effectively reduce the mis-classified predictions. Extensive experiments on the prevalent VOC 2007 & 2012 datasets demonstrate the superior performance of our framework.