The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation

TL;DR

This paper presents a second-place solution for the RVOS challenge, enhancing the ReferFormer framework with training tricks and inference strategies to improve video object segmentation guided by language expressions.

Contribution

The work introduces specific training and inference techniques to significantly boost the performance of the ReferFormer model for RVOS.

Findings

Achieved second place in CVPR2022 Referring Youtube-VOS Challenge.

Implemented cyclical learning rates, semi-supervised training, and test-time augmentation.

Demonstrated improved segmentation accuracy over baseline models.

Abstract

The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual instances, this task is more challenging than the traditional semi-supervised video object segmentation where the ground truth object masks in the first frame are given. With the great achievement of Transformer in object detection and object segmentation, RVOS has been made remarkable progress where ReferFormer achieved the state-of-the-art performance. In this work, based on the strong baseline framework--ReferFormer, we propose several tricks to boost further, including cyclical learning rates, semi-supervised approach, and test-time augmentation inference. The improved ReferFormer ranks 2nd place on CVPR2022 Referring Youtube-VOS Challenge.