Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire video offline, impairing their application in a streaming fashion. In this work, we aim to surpass these limitations and design an RVOS method capable of effectively operating in streaming-like scenarios while retaining contextual information from past frames. We build upon the Segment-Anything 2 (SAM2) model, that provides robust segmentation and tracking capabilities and is naturally suited for streaming processing. We make SAM2 wiser, by empowering it with natural language understanding and explicit temporal modeling at the feature extraction stage, without fine-tuning its weights, and without outsourcing modality interaction to external models. To this end, we introduce a novel adapter module that injects temporal information and multi-modal cues in the feature extraction process. We further reveal the phenomenon of tracking bias in SAM2 and propose a learnable module to adjust its tracking focus when the current frame features suggest a new object more aligned with the caption. Our proposed method, SAMWISE, achieves state-of-the-art across various benchmarks, by adding a negligible overhead of just 4.9 M parameters.
Click on a caption to see how SAMWISE segments the referred object.
@misc{cuttano2024samwise,
title = {SAMWISE: Infusing wisdom in SAM2 for Text-Driven Video Segmentation},
author = {Claudia Cuttano and Gabriele Trivigno and Gabriele Rosi and Carlo Masone and Giuseppe Averta},
year = {2024},
eprint = {2411.17646},
url = {https://arxiv.org/abs/2411.17646},
}