用注意力机制筛选关键特征，让少样本视频目标检测更准更稳。
Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection
- 设计物体感知时序模块，只传递高置信度特征
- 5次样本下平均精度提升4.5%，最高达5.3%
- 无需复杂区域建议，适合资源受限场景
少样本视频目标检测（FSVOD）旨在用极少标注样本识别视频中新物体，克服传统方法依赖大量训练数据的局限。核心挑战在于：跨帧保持一致性（受遮挡和外观变化影响），以及不依赖昂贵的区域提议实现新物体泛化。本文提出一种新型物体感知时序建模方法，通过过滤机制选择性传播高置信度目标特征，实现高效特征传递，减少噪声累积，提升少样本下的检测准确率。结合少样本训练的检测与分类头，实现无需显式物体轨迹提议的鲁棒时序一致性。在5样本设置下，于FSVOD-500、FSYTV-40、VidOR、VidVRD数据集上分别取得3.7%、5.3%、4.3%、4.5%的AP提升，1/3/10样本配置也均表现更优。代码已开源。
原文摘要 · Abstract (English)
Few-shot Video Object Detection (FSVOD) addresses the challenge of detecting novel objects in videos with limited labeled examples, overcoming the constraints of traditional detection methods that require extensive training data. This task presents key challenges, including maintaining temporal consistency across frames affected by occlusion and appearance variations, and achieving novel object generalization without relying on complex region proposals, which are often computationally expensive and require task-specific training. Our novel object-aware temporal modeling approach addresses these challenges by incorporating a filtering mechanism that selectively propagates high-confidence object features across frames. This enables efficient feature progression, reduces noise accumulation, and enhances detection accuracy in a few-shot setting. By utilizing few-shot trained detection and classification heads with focused feature propagation, we achieve robust temporal consistency without depending on explicit object tube proposals. Our approach achieves performance gains, with AP improvements of 3.7% (FSVOD-500), 5.3% (FSYTV-40), 4.3% (VidOR), and 4.5 (VidVRD) in the 5-shot setting. Further results demonstrate improvements in 1-shot, 3-shot, and 10-shot configurations. We make the code public at: https://github.com/yogesh-iitj/fs-video-vit
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。