Object Detection in Video with Spatiotemporal Sampling Networks

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames. This naturally renders the approach robust to occlusion or motion blur in individual frames. Our framework does not require additional supervision, as it optimizes sampling locations directly with respect to object detection performance. Our STSN outperforms the state-of-the-art on the ImageNet VID dataset and compared to prior video object detection methods it uses a simpler design, and does not require optical flow data for training. We also show that after training STSN on videos, we can adapt it for object detection in images, by adding and training a single deformable convolutional layer on still-image data. This leads to improvements in accuracy compared to traditional object detection in images.