Flow Based Self-supervised Pixel Embedding for Image Segmentation
This work addresses image segmentation for computer vision applications, but it is incremental as it builds on existing advances in optical flow estimation and motion-based feature learning.
The paper tackles the problem of image segmentation by proposing a self-supervised approach that learns image features from motion cues, specifically optical flow, resulting in significantly better performance in few-shot segmentation tasks compared to networks trained from scratch.
We propose a new self-supervised approach to image feature learning from motion cue. This new approach leverages recent advances in deep learning in two directions: 1) the success of training deep neural network in estimating optical flow in real data using synthetic flow data; and 2) emerging work in learning image features from motion cues, such as optical flow. Building on these, we demonstrate that image features can be learned in self-supervision by first training an optical flow estimator with synthetic flow data, and then learning image features from the estimated flows in real motion data. We demonstrate and evaluate this approach on an image segmentation task. Using the learned image feature representation, the network performs significantly better than the ones trained from scratch in few-shot segmentation tasks.