# Time-Contrastive Pretraining for In-Context Image and Video Segmentation

arXiv: https://arxiv.org/abs/2506.17837 · HTML: https://mlsanity.com/paper/2506.17837/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [Exploring Effective Factors for Improving Visual In-Context Learning](https://mlsanity.com/paper/2304.04748/) (2023)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Instruct Me More! Random Prompting for Visual In-Context Learning](https://mlsanity.com/paper/2311.03648/) (2023)
- [Flexible visual prompts for in-context learning in computer vision](https://mlsanity.com/paper/2312.06592/) (2023)

## Abstract (arXiv)

In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a time-contrastive self-supervised objective that pretrains a prompt retriever for visual ICL, and formulate ICL as a video object segmentation (VOS) task. Temporal addresses key limitations of grid-based methods that restrict the number and resolution of context images. By reframing ICL as a VOS problem, our approach supports a variable number of context images while preserving their full resolution. To address the challenge of selecting optimal context sets for queries, we pretrain a prompt retriever on videos via self-supervised learning, where adjacent frames serve as positives and distant frames as negatives. For image segmentation, the prompt retriever selects relevant sequences that, when combined with the query, form coherent videos for VOS processing. For video segmentation, it identifies keyframes, predicts their masks using our ICL pipeline, and propagates them throughout the sequence. When evaluated on MICCAI FLARE 2022, our method achieves substantial improvements over baselines: 90.95% Dice score for image segmentation (10.64% improvement) and 92.45% Dice for video segmentation (14.88% improvement).