针对少样本检测中提案分布不均问题，提出动态优化方案提升新类识别能力。
Proposal Refinement for Few-Shot Object Detection
- 分阶段设计精修损失与辅助分支，平衡基类与新类提案分布。
- 在基准测试上性能提升1%~6%，且推理时间不变。
- 适合需要高效少样本检测的工业应用或资源受限场景。
少样本目标检测近年来受到广泛关注。尽管已有优秀算法提出，但多数方法依赖少样本分类性能。不同于以往工作，本文关注基类与新类之间区域提案分布不均的问题。为缓解该问题，我们提出一种针对不同训练阶段的提案精修方法：在基础训练阶段引入精修损失以增强模型对新类的敏感性；在微调阶段引入作为RPN辅助分支的精修分支，生成更多新类提案。通过重新平衡提案分布，所提方法在现有基准上相比基线模型性能提升约1%~6%，且不增加任何推理时间。大量实验表明，本方法建立了少样本目标检测任务的新标杆。
原文摘要 · Abstract (English)
Few-shot object detection has gained widely attention in recent years. Some excellent algorithms have been proposed to handle this task. However, most of these algorithms rely on the performance of few-shot classification. Unlike previous attempts, our work focuses on the problem of unbalanced distribution of region proposals between the novel classes and the base classes. In order to alleviate this unbalanced distribution, we propose the proposal refinement approach for different training phases. Specifically, refinement loss is designed for the base training phase to enhance sensitivity of the model to novel classes, and refinement branch is introduced as an auxiliary branch for RPN (Region Proposal Networks) to generate more novel proposals in the fine-tuning phase. By rebalancing the proposal distribution, the proposed approach outperforms the baselines methods by roughly 1\%$\sim$6\% on current benchmarks without increasing any inference time. Through extensive experiments, we prove that we establish a new state-of-the-art method for the few-shot object detection task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。