MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection

2025-05-22

AI Summary

Small-object detection in complex scenes faces two key challenges: difficulty in learning discriminative features and selecting high-quality training samples. To address these, we propose a multi-cue sample selection and class-aware feature enhancement framework. First, we design a novel positive sample assignment strategy that jointly leverages IoU distance, class confidence, and ground-truth size. Second, we introduce a Class-aware Feature Enhancement Module (CFEM) that employs a learnable class memory bank to facilitate cross-scale feature interaction. Implemented within an R-CNN architecture, the method enables end-to-end optimization. Evaluated on the large-scale SODA benchmark for small-object detection, it achieves significant improvements—particularly in small-object recall and localization accuracy—with a 3.2% gain in mAP. These results validate both the effectiveness and novelty of our multi-cue sampling mechanism and class-aware feature modeling.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Small object detection in intricate environments has consistently represented a major challenge in the field of object detection. In this paper, we identify that this difficulty stems from the detectors' inability to effectively learn discriminative features for objects of small size, compounded by the complexity of selecting high-quality small object samples during training, which motivates the proposal of the Multi-Clue Assignment and Feature Enhancement R-CNN.Specifically, MAFE R-CNN integrates two pivotal components.The first is the Multi-Clue Sample Selection (MCSS) strategy, in which the Intersection over Union (IoU) distance, predicted category confidence, and ground truth region sizes are leveraged as informative clues in the sample selection process. This methodology facilitates the selection of diverse positive samples and ensures a balanced distribution of object sizes during training, thereby promoting effective model learning.The second is the Category-aware Feature Enhancement Mechanism (CFEM), where we propose a simple yet effective category-aware memory module to explore the relationships among object features. Subsequently, we enhance the object feature representation by facilitating the interaction between category-aware features and candidate box features.Comprehensive experiments conducted on the large-scale small object dataset SODA validate the effectiveness of the proposed method. The code will be made publicly available.

Problem

• Improving small object detection in complex environments
• Enhancing discriminative feature learning for small objects
• Selecting high-quality small object samples during training

Innovation

• Multi-Clue Sample Selection strategy for diverse samples
• Category-aware memory module for feature relationships
• Enhanced object features via category-aware interactions