Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification

• URL: http://arxiv.org/abs/2509.00752v1
• Date: Sun, 31 Aug 2025 09:03:39 GMT
• Title: Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification
• Authors: Y Hop Nguyen, Doan Anh Phan Huu, Trung Thai Tran, Nhat Nam Mai, Van Toi Giap, Thao Thi Phuong Dao, Trung-Nghia Le,
• Abstract summary: We present a unified vision-language framework tailored for ENT endoscopy image analysis.<n>It simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval.<n>We achieve 95% accuracy and F1-score in classification, Recall@1 of 0.93 and 0.92 for image-to-image and text-to-image retrieval respectively, and MRR scores of 0.97 and 0.96.
• Score: 2.5995006632251516
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present a unified vision-language framework tailored for ENT endoscopy image analysis that simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval. Unlike conventional CNN-based pipelines that struggle to capture cross-modal semantics, our approach leverages the CLIP ViT-B/16 backbone and enhances it through Low-Rank Adaptation, multi-level CLS token aggregation, and spherical feature interpolation. These components collectively enable efficient fine-tuning on limited medical data while improving representation diversity and semantic alignment across modalities. To bridge the gap between visual inputs and textual diagnostic context, we introduce class-specific natural language prompts that guide the image encoder through a joint training objective combining supervised classification with contrastive learning. We validated our framework through participation in the ACM MM'25 ENTRep Grand Challenge, achieving 95% accuracy and F1-score in classification, Recall@1 of 0.93 and 0.92 for image-to-image and text-to-image retrieval respectively, and MRR scores of 0.97 and 0.96. Ablation studies demonstrated the incremental benefits of each architectural component, validating the effectiveness of our design for robust multimodal medical understanding in low-resource clinical settings.

Related papers

• BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation [3.7276397365086233]
  BiCLIP is a framework engineered to bolster robustness in medical segmentation.<n>It features a bidirectional multimodal fusion mechanism that enables visual features to iteratively refine textual representations.<n>It exhibits significant resistance to clinical artifacts, including motion blur and low-dose CT noise.
  arXiv  Detail & Related papers  (2026-02-25T18:11:47Z)
• CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios [53.94122089629544]
  We introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages.
  arXiv  Detail & Related papers  (2024-04-23T17:59:01Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation [14.536384387956527]
  We develop a novel Multi-Scale Cross Supervised Contrastive Learning framework to segment structures in medical images. Our approach contrasts multi-scale features based on ground-truth and cross-predicted labels, in order to extract robust feature representations. It outperforms state-of-the-art semi-supervised methods by more than 3.0% in Dice.
  arXiv  Detail & Related papers  (2023-06-25T16:55:32Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Medical Images [14.304996977665212]
  This study proposes a knowledge-based learning framework towards enhanced recognition of medical images. It works in three phases by synergizing contrastive learning and generative learning models. The proposed framework statistically excels in self-supervised benchmarks, achieving 2.08, 1.23, 1.12, 0.76 and 1.38 percentage points improvements over SimCLR in AUC/Dice.
  arXiv  Detail & Related papers  (2022-11-27T03:58:58Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)
• Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation [46.678279106837294]
  We propose a cross-level constrastive learning scheme to enhance representation capacity for local features in semi-supervised medical image segmentation. With the help of the cross-level contrastive learning and consistency constraint, the unlabelled data can be effectively explored to improve segmentation performance.
  arXiv  Detail & Related papers  (2022-02-08T15:12:11Z)
• Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation [16.517086214275654]
  We present a novel semi-supervised 2D medical segmentation solution that applies Contrastive Learning (CL) on image patches, instead of full images. These patches are meaningfully constructed using the semantic information of different classes obtained via pseudo labeling. We also propose a novel consistency regularization scheme, which works in synergy with contrastive learning.
  arXiv  Detail & Related papers  (2021-06-12T15:43:24Z)
• Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation [6.889911520730388]
  We aim to boost the performance of semi-supervised learning for medical image segmentation with limited labels. We learn latent representations directly at feature-level by imposing contrastive loss on unlabeled images. We conduct experiments on an MRI and a CT segmentation dataset and demonstrate that the proposed method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-05-27T03:27:58Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)

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.