用辅助分支对比学习提升视频目标检测鲁棒性。
Contrastive Learning through Auxiliary Branch for Video Object Detection
- 设计对比学习辅助分支增强特征表示能力。
- 在ImageNet VID上达84.0%和85.2% mAP，超越现有CNN模型。
- 无需额外计算开销，适合实际部署场景。
视频目标检测因运动模糊、遮挡和形变等图像退化问题，比静态图像检测更具挑战性。现有方法虽通过特征聚合与复杂后处理提升性能，但增加推理计算负担。本文提出一种简单有效的对比学习辅助分支（CLAB）方法，通过对比损失增强检测器主干的特征表示能力。进一步设计动态损失权重策略，在训练初期侧重辅助分支学习，后期逐步转向检测任务。在ImageNet VID数据集上，仅使用ResNet-101和ResNeXt-101主干，无需额外后处理，分别取得84.0%和85.2%的mAP，达到基于CNN模型的最新水平。
原文摘要 · Abstract (English)
Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly more difficult than detecting objects in still images. Prior approaches have improved video object detection performance by employing feature aggregation and complex post-processing techniques, though at the cost of increased computational demands. To improve robustness to image degradation without additional computational load during inference, we introduce a straightforward yet effective Contrastive Learning through Auxiliary Branch (CLAB) method. First, we implement a constrastive auxiliary branch using a contrastive loss to enhance the feature representation capability of the video object detector's backbone. Next, we propose a dynamic loss weighting strategy that emphasizes auxiliary feature learning early in training while gradually prioritizing the detection task as training converges. We validate our approach through comprehensive experiments and ablation studies, demonstrating consistent performance gains. Without bells and whistles, CLAB reaches a performance of 84.0% mAP and 85.2% mAP with ResNet-101 and ResNeXt-101, respectively, on the ImageNet VID dataset, thus achieving state-of-the-art performance for CNN-based models without requiring additional post-processing methods.
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。