Representation Learning with Semantic-aware Instance and Sparse Token Alignments

• URL: http://arxiv.org/abs/2601.08165v1
• Date: Tue, 13 Jan 2026 02:55:48 GMT
• Title: Representation Learning with Semantic-aware Instance and Sparse Token Alignments
• Authors: Phuoc-Nguyen Bui, Toan Duc Nguyen, Junghyun Bum, Duc-Tai Le, Hyunseung Choo,
• Abstract summary: We propose a multi-level alignment framework, Representation Learning with Semantic-aware Instance and Sparse Token Alignments (SISTA)<n>We improve the conventional contrastive learning by incorporating inter-report similarity to eliminate the false negatives.<n>Our framework achieves significant improvements in fine-grained tasks even with limited labeled data.
• Score: 2.1008762019705434
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples as positives and unpaired ones as negatives. However, in medical datasets, there can be substantial similarities between images or reports from different patients. Rigidly treating all unpaired samples as negatives, can disrupt the underlying semantic structure and negatively impact the quality of the learned representations. In this paper, we propose a multi-level alignment framework, Representation Learning with Semantic-aware Instance and Sparse Token Alignments (SISTA) by exploiting the semantic correspondence between medical image and radiology reports at two levels, i.e., image-report and patch-word levels. Specifically, we improve the conventional contrastive learning by incorporating inter-report similarity to eliminate the false negatives and introduce a method to effectively align image patches with relevant word tokens. Experimental results demonstrate the effectiveness of the proposed framework in improving transfer performance across different datasets on three downstream tasks: image classification, image segmentation, and object detection. Notably, our framework achieves significant improvements in fine-grained tasks even with limited labeled data. Codes and pre-trained models will be made available.

Related papers

• FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention [19.49398094732301]
  False Negatives (FaNe) induced by semantically similar texts and insufficient fine-grained cross-modal alignment.<n>FaNe achieves state-of-the-art performance across image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2025-11-15T13:37:21Z)
• Robust image representations with counterfactual contrastive learning [17.273155534515393]
  We introduce counterfactual contrastive learning, a novel framework leveraging recent advances in causal image synthesis.<n>Our method, evaluated across five datasets, outperforms standard contrastive learning in terms of robustness to acquisition shift.<n>Further experiments show that the proposed framework extends beyond acquisition shifts, with models trained with counterfactual contrastive learning reducing subgroup disparities across biological sex.
  arXiv  Detail & Related papers  (2024-09-16T15:11:00Z)
• Contrastive Learning with Counterfactual Explanations for Radiology Report Generation [83.30609465252441]
  We propose a textbfCountertextbfFactual textbfExplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking what if'' scenarios. Experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports.
  arXiv  Detail & Related papers  (2024-07-19T17:24:25Z)
• LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations [4.680881326162484]
  Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection.<n>A common augmentation technique in contrastive learning is random cropping followed by resizing.<n>We introduce LeOCLR, a framework that employs a novel instance discrimination approach and an adapted loss function.
  arXiv  Detail & Related papers  (2024-03-11T15:33:32Z)
• ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification [16.415582577355536]
  Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. We propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges.
  arXiv  Detail & Related papers  (2024-01-02T22:15:20Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)
• 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)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Positional Contrastive Learning for Volumetric Medical Image Segmentation [13.086140606803408]
  We propose a novel positional contrastive learning framework to generate contrastive data pairs. The proposed PCL method can substantially improve the segmentation performance compared to existing methods in both semi-supervised setting and transfer learning setting.
  arXiv  Detail & Related papers  (2021-06-16T22:15:28Z)
• Incremental False Negative Detection for Contrastive Learning [95.68120675114878]
  We introduce a novel incremental false negative detection for self-supervised contrastive learning. During contrastive learning, we discuss two strategies to explicitly remove the detected false negatives. Our proposed method outperforms other self-supervised contrastive learning frameworks on multiple benchmarks within a limited compute.
  arXiv  Detail & Related papers  (2021-06-07T15:29:14Z)

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.