Hybrid Classification-Regression Adaptive Loss for Dense Object Detection

TL;DR

This paper introduces a novel hybrid loss function, HCRAL, for dense object detection that improves performance by addressing task inconsistencies and focusing on difficult samples through innovative modules and sample selection strategies.

Contribution

The paper proposes the HCRAL method with RCI and CF modules, along with EATSS strategy, to enhance dense object detection by better handling task inconsistencies and training sample difficulty.

Findings

Outperforms existing methods on COCO test-dev

Improves detection accuracy in one-stage models

Effectively addresses task inconsistencies and difficult samples

Abstract

For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples. Achieving this necessitates incorporating information from both the classification and regression tasks. However, prior work tends to either emphasize difficult-to-train samples within their respective tasks or simply compute classification scores with IoU, often leading to suboptimal model performance. In this paper, we propose a Hybrid Classification-Regression Adaptive Loss, termed as HCRAL. Specifically, we introduce the Residual of Classification and IoU (RCI) module for cross-task supervision, addressing task inconsistencies, and the Conditioning Factor (CF) to focus on difficult-to-train samples within each task. Furthermore, we introduce a new strategy named Expanded Adaptive Training Sample Selection (EATSS) to provide additional samples that exhibit classification and regression inconsistencies. To validate the effectiveness of the proposed method, we conduct extensive experiments on COCO test-dev. Experimental evaluations demonstrate the superiority of our approachs. Additionally, we designed experiments by separately combining the classification and regression loss with regular loss functions in popular one-stage models, demonstrating improved performance.