提出渐进式主动学习框架，提升红外小目标检测在单点标注下的性能
From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision
- 通过预启动机制先学简单样本，避免初期模型误选难样本
- 双更新策略优化伪标签，使模型持续学习更难样本
- 引入衰减因子控制标签演化，保持训练稳定性和效率
近期，基于单帧红外小目标（SIRST）检测与单点标注的标签演化（LESPS）框架受到广泛关注。然而，现有方法存在训练不稳定、标签演化过度及难以发挥网络性能等问题。受生物体逐步适应环境并积累知识的启发，本文提出一种创新的渐进式主动学习（PAL）框架，使现有SIRST检测网络能逐步、主动地识别并学习更难样本。为避免低性能模型误选难样本，提出模型预启动概念，自动选择部分易样本，帮助模型建立基本任务感知能力；同时设计精细化双更新策略，促进对难样本的合理学习与伪标签的持续优化；此外，引入衰减因子，动态平衡目标标注的扩展与收缩，缓解过度标签演化风险。大量实验表明，采用PAL框架后，现有SIRST检测模型在多个公开数据集上达到当前最优（SOTA）性能。该框架可构建从全监督到单点标注任务的高效稳定桥梁。代码已开源。
原文摘要 · Abstract (English)
Recently, single-frame infrared small target (SIRST) detection with single point supervision has drawn wide-spread attention. However, the latest label evolution with single point supervision (LESPS) framework suffers from instability, excessive label evolution, and difficulty in exerting embedded network performance. Inspired by organisms gradually adapting to their environment and continuously accumulating knowledge, we construct an innovative Progressive Active Learning (PAL) framework, which drives the existing SIRST detection networks progressively and actively recognizes and learns harder samples. Specifically, to avoid the early low-performance model leading to the wrong selection of hard samples, we propose a model pre-start concept, which focuses on automatically selecting a portion of easy samples and helping the model have basic task-specific learning capabilities. Meanwhile, we propose a refined dual-update strategy, which can promote reasonable learning of harder samples and continuous refinement of pseudo-labels. In addition, to alleviate the risk of excessive label evolution, a decay factor is reasonably introduced, which helps to achieve a dynamic balance between the expansion and contraction of target annotations. Extensive experiments show that existing SIRST detection networks equipped with our PAL framework have achieved state-of-the-art (SOTA) results on multiple public datasets. Furthermore, our PAL framework can build an efficient and stable bridge between full supervision and single point supervision tasks. Our code is available at https://github.com/YuChuang1205/PAL
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。