DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning

• URL: http://arxiv.org/abs/2506.21096v2
• Date: Tue, 01 Jul 2025 02:51:03 GMT
• Title: DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning
• Authors: Kang He, Yuzhe Ding, Haining Wang, Fei Li, Chong Teng, Donghong Ji,
• Abstract summary: We propose DALR (Dual-level Alignment Learning for Multimodal Sentence Representation) to address cross-modal misalignment bias and intra-modal semantic divergence.<n>For cross-modal alignment, we propose a consistency learning module that softens negative samples and utilizes semantic similarity from an auxiliary task to achieve fine-grained cross-modal alignment.<n>We also contend that sentence relationships go beyond binary positive-negative labels, exhibiting a more intricate ranking structure.
• Score: 26.78273142765571
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias and intra-modal semantic divergence, which significantly degrade sentence representation quality. To address these challenges, we propose DALR (Dual-level Alignment Learning for Multimodal Sentence Representation). For cross-modal alignment, we propose a consistency learning module that softens negative samples and utilizes semantic similarity from an auxiliary task to achieve fine-grained cross-modal alignment. Additionally, we contend that sentence relationships go beyond binary positive-negative labels, exhibiting a more intricate ranking structure. To better capture these relationships and enhance representation quality, we integrate ranking distillation with global intra-modal alignment learning. Comprehensive experiments on semantic textual similarity (STS) and transfer (TR) tasks validate the effectiveness of our approach, consistently demonstrating its superiority over state-of-the-art baselines.

Related papers

• Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence [83.15764564701706]
  We propose a novel framework that performs vision-language alignment by integrating Cauchy-Schwarz divergence with mutual information.<n>We find that the CS divergence seamlessly addresses the InfoNCE's alignment-uniformity conflict and serves complementary roles with InfoNCE.<n> Experiments on text-to-image generation and cross-modality retrieval tasks demonstrate the effectiveness of our method on vision-language alignment.
  arXiv  Detail & Related papers  (2025-02-24T10:29:15Z)
• Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction [8.011606196420757]
  The Aspect Sentiment Triplet Extraction task is one of the most prominent subtasks in fine-grained sentiment analysis.<n>Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner.<n>We propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations.
  arXiv  Detail & Related papers  (2025-02-04T02:23:45Z)
• DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning [59.4644086610381]
  We propose a novel denoising objective that inherits from another perspective, i.e., the intra-sentence perspective. By introducing both discrete and continuous noise, we generate noisy sentences and then train our model to restore them to their original form. Our empirical evaluations demonstrate that this approach delivers competitive results on both semantic textual similarity (STS) and a wide range of transfer tasks.
  arXiv  Detail & Related papers  (2024-01-24T17:48:45Z)
• RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank [54.854714257687334]
  We propose a novel approach, RankCSE, for unsupervised sentence representation learning. It incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework. An extensive set of experiments are conducted on both semantic textual similarity (STS) and transfer (TR) tasks.
  arXiv  Detail & Related papers  (2023-05-26T08:27:07Z)
• CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval [108.48540976175457]
  We propose Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-08-21T08:37:50Z)
• 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)
• Learning Relation Alignment for Calibrated Cross-modal Retrieval [52.760541762871505]
  We propose a novel metric, Intra-modal Self-attention Distance (ISD), to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations. We present Inter-modal Alignment on Intra-modal Self-attentions (IAIS), a regularized training method to optimize the ISD and calibrate intra-modal self-attentions mutually via inter-modal alignment.
  arXiv  Detail & Related papers  (2021-05-28T14:25:49Z)
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification [208.1227090864602]
  Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing VI-ReID methods tend to learn global representations, which have limited discriminability and weak robustness to noisy images. We propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
  arXiv  Detail & Related papers  (2020-07-18T03:08:13Z)

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.