VALSE 论文速览 第178期：Imitation Learning for Small Object Detection

论文题目：

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

作者列表：

袁翔 (西北工业大学)、程塨 (西北工业大学)、延可冰 (西北工业大学)、曾庆华 (西北工业大学)、韩军伟 (西北工业大学)

B站观看网址：

https://www.bilibili.com/video/BV14J4m1G77W/

论文摘要：

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.

论文信息：

[1] Xiang Yuan, Gong Cheng, Kebing Yan, Qinghua Zeng, and Junwei Han. Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 6317-6327.

论文链接：

[https://openaccess.thecvf.com/content/ICCV2023/html/Yuan_Small_Object_Detection_via_Coarse-to-fine_Proposal_Generation_and_Imitation_Learning_ICCV_2023_paper.html]

代码链接：

[https://github.com/shaunyuan22/CFINet]

视频讲者简介：

袁翔，西北工业大学自动化学院博士生，导师为程塨教授。主要研究方向为计算机视觉和目标检测。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：李爽 (北京理工大学)