Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos

• URL: http://arxiv.org/abs/2605.12320v2
• Date: Tue, 19 May 2026 14:33:39 GMT
• Title: Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
• Abstract summary: Learning robust representations of polyp tracklets is key to enabling AI-assisted colonoscopy applications.<n>In this work, we leverage the sequential workflow of colonoscopy procedures to derive self-supervised associations from temporal structure.<n>We demonstrate the effectiveness of the learned representations across multiple downstream tasks, including polyp retrieval and re-identification, size estimation, and histology classification.
• Score: 8.245519663146586
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning robust representations of polyp tracklets is key to enabling multiple AI-assisted colonoscopy applications, from polyp characterization to automated reporting and retrieval. Supervised contrastive learning is an effective approach for learning such representations, but it typically relies on correct positive and negative definitions. Collecting these labels requires linking tracklets that depict the same underlying polyp entity throughout the video, which is costly and demands specialized clinical expertise. In this work, we leverage the sequential workflow of colonoscopy procedures to derive self-supervised associations from temporal structure. Since temporally derived associations are not guaranteed to be correct, we introduce a noise-aware contrastive loss to account for noisy associations. We demonstrate the effectiveness of the learned representations across multiple downstream tasks, including polyp retrieval and re-identification, size estimation, and histology classification. Our method outperforms prior self-supervised and supervised baselines, and matches or exceeds recent foundation models across all tasks, using a lightweight encoder trained on only 27 videos. Code is available at https://github.com/lparolari/ntssl.

Related papers

• Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy [5.7522869823664005]
  Existing methods for polyp counting rely on self-supervised learning.<n>We introduce a paradigm shift by proposing a supervised contrastive loss that incorporates temporally-aware soft targets.<n>Results demonstrate a 2.2x reduction in fragmentation rate compared to prior approaches.
  arXiv  Detail & Related papers  (2025-07-03T09:55:48Z)
• Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation [51.67328507400985]
  In noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators.<n>This paper focuses on learning from partial labels annotated by pre-trained vision-language models.<n>It proposes an innovative collaborative consistency regularization (Co-Reg) method.
  arXiv  Detail & Related papers  (2025-06-03T12:48:54Z)
• PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis [28.764513004699676]
  PolypSegTrack is a novel foundation model that jointly addresses polyp detection, segmentation, classification and unsupervised tracking in colonoscopic videos.<n>Our approach leverages a novel conditional mask loss, enabling flexible training across datasets with either pixel-level segmentation masks or bounding box annotations.<n>Our unsupervised tracking module reliably associates polyp instances across frames using object queries, without relying on any visions.
  arXiv  Detail & Related papers  (2025-03-31T14:00:21Z)
• SSTFB: Leveraging self-supervised pretext learning and temporal self-attention with feature branching for real-time video polyp segmentation [4.027361638728112]
  We propose a video polyp segmentation method that performs self-supervised learning as an auxiliary task and a spatial-temporal self-attention mechanism for improved representation learning. Our experimental results demonstrate an improvement with respect to several state-of-the-art (SOTA) methods. Our ablation study confirms that the choice of the proposed joint end-to-end training improves network accuracy by over 3% and nearly 10% on both the Dice similarity coefficient and intersection-over-union.
  arXiv  Detail & Related papers  (2024-06-14T17:33:11Z)
• RT-GAN: Recurrent Temporal GAN for Adding Lightweight Temporal Consistency to Frame-Based Domain Translation Approaches [3.7873597471903944]
  We present a lightweight solution with a tunable temporal parameter, RT-GAN, for adding temporal consistency to individual frame-based approaches.<n>We demonstrate the effectiveness of our approach on two challenging use cases in colonoscopy.
  arXiv  Detail & Related papers  (2023-10-02T03:13:26Z)
• YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection [80.68520401539979]
  textbfYONA (textbfYou textbfOnly textbfNeed one textbfAdjacent Reference-frame) is an efficient end-to-end training framework for video polyp detection. Our proposed YONA outperforms previous state-of-the-art competitors by a large margin in both accuracy and speed.
  arXiv  Detail & Related papers  (2023-06-06T13:53:15Z)
• Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment [57.419727894848485]
  A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images. Most previous studies at-tempt to develop models for polyp differentiation using Narrow-Band Imaging (NBI) or other enhanced images. We propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification.
  arXiv  Detail & Related papers  (2021-08-05T09:31:46Z)
• Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos [76.37907640271806]
  We propose an Image-video-joint polyp detection network (Ivy-Net) to address the domain gap between colonoscopy images from historical medical reports and real-time videos. Experiments on the collected dataset demonstrate that our Ivy-Net achieves the state-of-the-art result on colonoscopy video.
  arXiv  Detail & Related papers  (2020-12-31T10:33:09Z)
• CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions [61.724894233252414]
  This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem. Existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels.
  arXiv  Detail & Related papers  (2020-07-15T09:52:35Z)
• LRTD: Long-Range Temporal Dependency based Active Learning for Surgical Workflow Recognition [67.86810761677403]
  We propose a novel active learning method for cost-effective surgical video analysis. Specifically, we propose a non-local recurrent convolutional network (NL-RCNet), which introduces non-local block to capture the long-range temporal dependency. We validate our approach on a large surgical video dataset (Cholec80) by performing surgical workflow recognition task.
  arXiv  Detail & Related papers  (2020-04-21T09:21:22Z)

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.