paper-with-me

Papers

Forget, Anticipate and Adapt: Test Time Training for Long Videos

2026-06-25 · Rajat Modi, Sebastian Noel, Xin Liang, Yogesh Singh Rawat arxiv

Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.

📄 PDF Abstract BibTeX arXiv:2606.26515

Code (0)

등록된 구현이 없습니다.

Tasks

Video Classification

Similar Papers 제목 키워드 기반

Efficient Test-Time Model Adaptation without Forgetting

2022-04-06 · Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen 외

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the…

modelTest-time Adaptation

MINGLE: Mixtures of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

2025-05-17 · Zihuan Qiu, Yi Xu, Chiyuan He, Fanman Meng 외

Continual model merging integrates independently fine-tuned models sequentially without access to original training data, providing a scalable and efficient solution to continual learning. However, current methods still …

Continual LearningMixture-of-ExpertsTest-time Adaptation

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

2024-03-18 · Mingkui Tan, Guohao Chen, Jiaxiang Wu, Yifan Zhang 외

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample. Although recent TTA has shown promising performance, we still face…

image-classificationImage ClassificationmodelSemantic Segmentation+1

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams

2026-05-29 · Jonathan Swinnen, Tinne Tuytelaars arxiv

In this work we introduce a novel approach to domain incremental learning, adapting models over time to evolving, non-stationary data. In contrast to other works, we do not attempt to avoid catastrophic forgetting, but r…

Semantic SegmentationIncremental LearningAction Recognition

Incremental Open-set Domain Adaptation

2024-08-31 · Sayan Rakshit, Hmrishav Bandyopadhyay, Nibaran Das, Biplab Banerjee

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains whe…

Domain Adaptationimage-classificationImage ClassificationIncremental Learning