Cover Image

Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kühn, Paul Julius, Spengler, Cedric, Weinmann, Michael, Kuijper, Arjan, Sinha, Saptarshi Neil
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ECI: Effective Contrastive Information to Evaluate Hard-Negatives
by: Sinha, Aarush, et al.
Published: (2026)

Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data
by: Sinha, Saptarshi Neil, et al.
Published: (2025)

Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment
by: Song, Jia, et al.
Published: (2024)

SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection
by: Kühn, Paul Julius, et al.
Published: (2026)

Category-Oriented Representation Learning for Image to Multi-Modal Retrieval
by: Cheng, Zida, et al.
Published: (2023)

Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback
by: Dong, Qian, et al.
Published: (2023)

BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives
by: Sinha, Aarush, et al.
Published: (2025)

RangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation
by: Kühn, Paul Julius, et al.
Published: (2025)

XR: Cross-Modal Agents for Composed Image Retrieval
by: Yang, Zhongyu, et al.
Published: (2026)

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation
by: Ma, Shouxing, et al.
Published: (2025)

Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation
by: Ren, Kelin, et al.
Published: (2025)

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
by: Shi, Wentao, et al.
Published: (2026)

Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking
by: Zhu, Tianyu, et al.
Published: (2024)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
by: Sinha, Aarush
Published: (2025)

Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
by: Tran, Linh, et al.
Published: (2025)

Adversarial Hubness in Multi-Modal Retrieval
by: Zhang, Tingwei, et al.
Published: (2024)

DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers
by: Wasserman, Navve, et al.
Published: (2025)

Entity Image and Mixed-Modal Image Retrieval Datasets
by: Blaga, Cristian-Ioan, et al.
Published: (2025)

Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
by: Le, Van-Hoang, et al.
Published: (2025)

Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment
by: Wang, Yuanyi, et al.
Published: (2024)

MMHCL: Multi-Modal Hypergraph Contrastive Learning for Recommendation
by: Guo, Xu, et al.
Published: (2025)

Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization
by: Zhou, Chunying, et al.
Published: (2024)

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
by: Yang, Hao, et al.
Published: (2026)

Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive Learning
by: Sidiropoulos, Georgios, et al.
Published: (2024)

TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval
by: Jing, Xiaolun, et al.
Published: (2025)

MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin
by: Zhou, Tianshuo, et al.
Published: (2023)

Mitigating Popularity Bias in Counterfactual Explanations using Large Language Models
by: Hasami, Arjan, et al.
Published: (2025)

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling
by: Xia, Tian, et al.
Published: (2026)

Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions
by: Su, Weihang, et al.
Published: (2023)

Exploring the Nexus Between Retrievability and Query Generation Strategies
by: Sinha, Aman, et al.
Published: (2024)

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
by: Lee, Jinhyuk, et al.
Published: (2023)

Contrastive Pre-training for Deep Session Data Understanding
by: Li, Zixuan, et al.
Published: (2024)

SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval
by: Li, Xiaopeng, et al.
Published: (2024)

Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval
by: Sun, Zengbao, et al.
Published: (2024)

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval
by: Jang, Youngjoon, et al.
Published: (2026)

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
by: Jin, Bowen, et al.
Published: (2025)

The Effectiveness of Graph Contrastive Learning on Mathematical Information Retrieval
by: Wang, Pei-Syuan, et al.
Published: (2024)

A Contrastive Framework with User, Item and Review Alignment for Recommendation
by: Dong, Hoang V., et al.
Published: (2025)

Generative Multi-Modal Knowledge Retrieval with Large Language Models
by: Long, Xinwei, et al.
Published: (2024)

Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning
by: Nie, Zhijie, et al.
Published: (2024)