Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning

TL;DR

This paper introduces CFINet, a novel two-stage framework for small object detection that combines a coarse-to-fine proposal generator with feature imitation learning, significantly improving detection accuracy on challenging benchmarks.

Contribution

The paper proposes CFINet, integrating a Coarse-to-fine RPN and feature imitation learning with an auxiliary contrastive loss, advancing small object detection performance.

Findings

Achieves state-of-the-art results on SODA-D and SODA-A benchmarks.

Outperforms baseline detectors and mainstream approaches.

Enhances small object detection accuracy significantly.

Abstract

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the aforementioned issues, we propose CFINet, a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. Firstly, we introduce Coarse-to-fine RPN (CRPN) to ensure sufficient and high-quality proposals for small objects through the dynamic anchor selection strategy and cascade regression. Then, we equip the conventional detection head with a Feature Imitation (FI) branch to facilitate the region representations of size-limited instances that perplex the model in an imitation manner. Moreover, an auxiliary imitation loss following supervised contrastive learning paradigm is devised to optimize this branch. When integrated with Faster RCNN, CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A, underscoring its superiority over baseline detector and other mainstream detection approaches.