ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation
This work addresses video object segmentation in kitchen scenes, representing an incremental improvement with domain-specific impact.
The authors tackled the problem of semi-supervised video object segmentation by introducing MSDeAOT, a variant of the AOT framework that incorporates transformers at multiple feature scales, achieving top-ranking performance in the EPIC-KITCHEN VISOR challenge.
The Associating Objects with Transformers (AOT) framework has exhibited exceptional performance in a wide range of complex scenarios for video object segmentation. In this study, we introduce MSDeAOT, a variant of the AOT series that incorporates transformers at multiple feature scales. Leveraging the hierarchical Gated Propagation Module (GPM), MSDeAOT efficiently propagates object masks from previous frames to the current frame using a feature scale with a stride of 16. Additionally, we employ GPM in a more refined feature scale with a stride of 8, leading to improved accuracy in detecting and tracking small objects. Through the implementation of test-time augmentations and model ensemble techniques, we achieve the top-ranking position in the EPIC-KITCHEN VISOR Semi-supervised Video Object Segmentation Challenge.