Co-Paced Learning Strategy Based on Confidence for Flying Bird Object Detection Model Training

TL;DR

This paper introduces a co-paced learning strategy based on confidence that improves flying bird object detection by gradually training models from easy to hard samples, enhancing accuracy in surveillance videos.

Contribution

It proposes a novel co-paced learning method that uses two collaborating models to adaptively select training samples based on confidence, improving detection performance.

Findings

Significant accuracy improvement over existing strategies

Effective in handling varying difficulty of flying bird samples

Validated on multiple surveillance datasets

Abstract

The flying bird objects captured by surveillance cameras exhibit varying levels of recognition difficulty due to factors such as their varying sizes or degrees of similarity to the background. To alleviate the negative impact of hard samples on training the Flying Bird Object Detection (FBOD) model for surveillance videos, we propose the Co-Paced Learning strategy Based on Confidence (CPL-BC) and apply it to the training process of the FBOD model. This strategy involves maintaining two models with identical structures but different initial parameter configurations that collaborate with each other to select easy samples for training, where the prediction confidence exceeds a set threshold. As training progresses, the strategy gradually lowers the threshold, thereby gradually enhancing the model's ability to recognize objects, from easier to more hard ones. Prior to applying CPL-BC, we pre-trained the two FBOD models to equip them with the capability to assess the difficulty of flying bird object samples. Experimental results on two different datasets of flying bird objects in surveillance videos demonstrate that, compared to other model learning strategies, CPL-BC significantly improves detection accuracy, thereby verifying the method's effectiveness and advancement.