Weakly supervised object detection using pseudo-strong labels

TL;DR

This paper introduces a framework that enhances weakly supervised object detection by generating pseudo-strong labels from weak labels, leading to improved detection accuracy on PASCAL VOC 2007.

Contribution

It proposes a novel framework that uses weakly supervised outputs as pseudo-strong labels to train a more accurate object detection model.

Findings

Achieved 43.4% mAP on PASCAL VOC 2007, surpassing previous best of 39.5%.

Demonstrated the effectiveness of pseudo-strong labels in improving detection accuracy.

Framework is simple, distinct, and adaptable to other methods.

Abstract

Object detection is an import task of computer vision.A variety of methods have been proposed,but methods using the weak labels still do not have a satisfactory result.In this paper,we propose a new framework that using the weakly supervised method's output as the pseudo-strong labels to train a strongly supervised model.One weakly supervised method is treated as black-box to generate class-specific bounding boxes on train dataset.A de-noise method is then applied to the noisy bounding boxes.Then the de-noised pseudo-strong labels are used to train a strongly object detection network.The whole framework is still weakly supervised because the entire process only uses the image-level labels.The experiment results on PASCAL VOC 2007 prove the validity of our framework, and we get result 43.4% on mean average precision compared to 39.5% of the previous best result and 34.5% of the initial method,respectively.And this frame work is simple and distinct,and is promising to be applied to other method easily.