Progressive Sparse Local Attention for Video object detection
arXiv:1903.09126
Abstract
Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Self-Attention Generative Adversarial Networks
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- OCNet: Object Context Network for Scene Parsing
- Deformable Convolutional Networks
- Seq-NMS for Video Object Detection
- Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms