In Defense of Online Models for Video Instance Segmentation
This work addresses the challenge of handling long and ongoing videos in video instance segmentation, where online models are crucial but previously underperformed, offering a significant performance boost that is incremental but impactful for the domain.
The paper tackles the performance gap between online and offline models in video instance segmentation by identifying error-prone frame associations due to similar instance appearances. It proposes a contrastive learning-based online framework that achieves state-of-the-art results, with 49.5 AP on YouTube-VIS 2019 (improving by 13.2 AP over prior online and 2.1 AP over offline art) and 30.2 AP on OVIS (surpassing prior art by 14.8 AP).
In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent advantage in handling long video sequences and ongoing videos while offline models fail due to the limit of computational resources. Therefore, it would be highly desirable if online models can achieve comparable or even better performance than offline models. By dissecting current online models and offline models, we demonstrate that the main cause of the performance gap is the error-prone association between frames caused by the similar appearance among different instances in the feature space. Observing this, we propose an online framework based on contrastive learning that is able to learn more discriminative instance embeddings for association and fully exploit history information for stability. Despite its simplicity, our method outperforms all online and offline methods on three benchmarks. Specifically, we achieve 49.5 AP on YouTube-VIS 2019, a significant improvement of 13.2 AP and 2.1 AP over the prior online and offline art, respectively. Moreover, we achieve 30.2 AP on OVIS, a more challenging dataset with significant crowding and occlusions, surpassing the prior art by 14.8 AP. The proposed method won first place in the video instance segmentation track of the 4th Large-scale Video Object Segmentation Challenge (CVPR2022). We hope the simplicity and effectiveness of our method, as well as our insight into current methods, could shed light on the exploration of VIS models.