Unseen Object Segmentation in Videos via Transferable Representations
This addresses the labor-intensive annotation issue for video object segmentation, enabling segmentation of unseen categories, though it is incremental as it builds on transfer learning and self-learning approaches.
The paper tackles the problem of segmenting unseen object categories in videos without target annotations by transferring visual information from annotated source images, achieving favorable performance against state-of-the-art methods on benchmark datasets.
In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we exploit existing annotations in source images and transfer such visual information to segment videos with unseen object categories. Without using any annotations in the target video, we propose a method to jointly mine useful segments and learn feature representations that better adapt to the target frames. The entire process is decomposed into two tasks: 1) solving a submodular function for selecting object-like segments, and 2) learning a CNN model with a transferable module for adapting seen categories in the source domain to the unseen target video. We present an iterative update scheme between two tasks to self-learn the final solution for object segmentation. Experimental results on numerous benchmark datasets show that the proposed method performs favorably against the state-of-the-art algorithms.