Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation

• URL: http://arxiv.org/abs/2604.10950v2
• Date: Tue, 14 Apr 2026 08:11:15 GMT
• Title: Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
• Abstract summary: DiTTA (Distillation-assisted Test-Time Adaptation) is a novel framework that converts an ISS model into a temporally-aware VSS model without annotated videos.<n>We demonstrate DiTTA's effectiveness, achieving competitive or superior performance relative to fully-supervised VSS methods.
• Score: 58.40817037271021
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids annotation costs but ignores crucial temporal coherence. Recent foundation models such as SAM2 enable high-quality mask propagation yet remain impractical for direct VSS due to limited semantic understanding and computational overhead. In this paper, we propose DiTTA (Distillation-assisted Test-Time Adaptation), a novel framework that converts an ISS model into a temporally-aware VSS model through efficient test-time adaptation (TTA), without annotated videos. DiTTA distills SAM2's temporal segmentation knowledge into the ISS model during a brief, single-pass initialization phase, complemented by a lightweight temporal fusion module to aggregate cross-frame context. Crucially, DiTTA achieves robust generalization even when adapting with highly limited partial video snippets (e.g., initial 10%), significantly outperforming zero-shot refinement approaches that repeatedly invoke SAM2 during inference. Extensive experiments on VSPW and Cityscapes demonstrate DiTTA's effectiveness, achieving competitive or superior performance relative to fully-supervised VSS methods, thus providing a practical and annotation-free solution for real-world VSS tasks.

Related papers

• DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding [11.584150931573738]
  Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries.<n>Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations.<n>We propose DSE-VTG, a framework that addresses both frame-wise visual encoding and fixed query embeddings.
  arXiv  Detail & Related papers  (2026-09-08T15:03:41Z)
• TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning [54.70019148172847]
  We leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels.<n>The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously.<n>TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data.
  arXiv  Detail & Related papers  (2026-04-01T09:52:57Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution [57.87099307245989]
  This paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba)<n>TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames.<n>Our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7% reduction complexity (in MACs)
  arXiv  Detail & Related papers  (2025-08-14T08:42:15Z)
• Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild [38.94246183524246]
  We propose a novel approach by representing the inherent correspondence between reference-target image pairs as a pseudo video.<n>This perspective allows the latest version of SAM, known as SAM2, to be adapted to downstream tasks in a lightweight manner.<n>We term this approach Correspondence As Video for SAM (CAV-SAM)
  arXiv  Detail & Related papers  (2025-08-11T08:42:49Z)
• Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models [96.97910688908956]
  We introduce the first zero-shot approach for Video Semantic (VSS) based on pre-trained diffusion models. We propose a framework tailored for VSS based on pre-trained image and video diffusion models. Experiments show that our proposed approach outperforms existing zero-shot image semantic segmentation approaches.
  arXiv  Detail & Related papers  (2024-05-27T08:39:38Z)
• ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection [10.012716326383567]
  Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. We present ZEETAD, featuring two modules: dual-localization and zero-shot proposal classification. We enhance discriminative capability on unseen classes by minimally updating the frozen CLIP encoder with lightweight adapters.
  arXiv  Detail & Related papers  (2023-11-01T00:17:37Z)
• End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning [5.587301322663445]
  We introduce an end-to-end streaming video temporal action segmentation model with reinforcement learning (SVTAS-RL) The SVTAS-RL model significantly outperforms existing STAS models and achieves competitive performance to the state-of-the-art TAS model on multiple datasets under the same evaluation criteria.
  arXiv  Detail & Related papers  (2023-09-27T14:30:34Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.