# Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

Source: [Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations](<https://www.sota2.com/research/paper/68fa70651e209131cea4ae49>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:41:08.783Z

Authors: Mohammadreza Salehi, Efstratios Gavves, Cees G. M. Snoek, Yuki M. Asano

Published: 2023-08-22T21:28:58.000Z

## Abstract

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich source has been largely overlooked. Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning. While methods designed solely for images face difficulties in achieving even the same performance on videos, our method improves not only the representation quality for videos-but also images. Our approach, which we call time-tuning, starts from image-pretrained models and fine-tunes them with a novel self-supervised temporal-alignment clustering loss on unlabeled videos. This effectively facilitates the transfer of high-level information from videos to image representations. Time-tuning improves the state-of-the-art by 8-10% for unsupervised semantic segmentation on videos and matches it for images. We believe this method paves the way for further self-supervised scaling by leveraging the abundant availability of videos. The implementation can be found here : https://github.com/SMSD75/Timetuning

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Object Segmentation on DAVIS 2017 (val)](<https://www.sota2.com/research/sota/video-object-segmentation-on-davis-2017-val.md>): Video Object Segmentation; DAVIS 2017 (val); J mean: 44.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.11796>)

[PDF](<https://arxiv.org/pdf/2308.11796.pdf>)
