Addressing Issues with Working Memory in Video Object Segmentation

TL;DR

This paper introduces a simple decision function to improve video object segmentation models by regulating working memory updates, enhancing robustness against sudden camera view changes and context shifts in real-world scenarios.

Contribution

A novel, easy-to-implement decision function that improves existing working memory-based VOS models by filtering irrelevant frames during abrupt scene changes.

Findings

Significant performance gains on videos with frame interjections.

Enhanced robustness to camera cuts and extreme context changes.

Applicable to any existing working memory-based VOS model.

Abstract

Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to predict object masks. We refer to the internal memory state of the initial image-mask pair and past image-masks as a working memory buffer. While the current state of the art models perform very well on clean video data, their reliance on a working memory of previous frames leaves room for error. Affinity-based algorithms include the inductive bias that there is temporal continuity between consecutive frames. To account for inconsistent camera views of the desired object, working memory models need an algorithmic modification that regulates the memory updates and avoid writing irrelevant frames into working memory. A simple algorithmic change is proposed that can be applied to any existing working memory-based VOS model to improve performance on inconsistent views, such as sudden camera cuts, frame interjections, and extreme context changes. The resulting model performances show significant improvement on video data with these frame interjections over the same model without the algorithmic addition. Our contribution is a simple decision function that determines whether working memory should be updated based on the detection of sudden, extreme changes and the assumption that the object is no longer in frame. By implementing algorithmic changes, such as this, we can increase the real-world applicability of current VOS models.