CTVIS: Consistent Training for Online Video Instance Segmentation

TL;DR

The paper introduces CTVIS, a training strategy that aligns training and inference for online video instance segmentation, improving discriminative embeddings and achieving state-of-the-art results on multiple benchmarks.

Contribution

It proposes a novel consistent training approach that constructs contrastive items using inference-like mechanisms, enhancing embedding discrimination for better VIS performance.

Findings

Outperforms SOTA models by up to 5 points on three benchmarks.

Effective in handling occlusion, re-identification, and deformation.

Pseudo-video training surpasses fully-supervised methods.

Abstract

The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is directly supervised by the contrastive loss computed upon the contrastive items (CIs), which are sets of anchor/positive/negative embeddings. Recent online VIS methods leverage CIs sourced from one reference frame only, which we argue is insufficient for learning highly discriminative embeddings. Intuitively, a possible strategy to enhance CIs is replicating the inference phase during training. To this end, we propose a simple yet effective training strategy, called Consistent Training for Online VIS (CTVIS), which devotes to aligning the training and inference pipelines in terms of building CIs. Specifically, CTVIS constructs CIs by referring inference the momentum-averaged embedding and the memory bank storage mechanisms, and adding noise to the relevant embeddings. Such an extension allows a reliable comparison between embeddings of current instances and the stable representations of historical instances, thereby conferring an advantage in modeling VIS challenges such as occlusion, re-identification, and deformation. Empirically, CTVIS outstrips the SOTA VIS models by up to +5.0 points on three VIS benchmarks, including YTVIS19 (55.1% AP), YTVIS21 (50.1% AP) and OVIS (35.5% AP). Furthermore, we find that pseudo-videos transformed from images can train robust models surpassing fully-supervised ones.