MARC: Multi-label Adaptive Retrieval Contrastive Loss For Remote Sensing Images

Abstract

Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article, Multi-Label Adaptive Contrastive Learning (MACL) is introduced as an extension of contrastive learning to address them. It integrates label-aware sampling, frequency-sensitive weighting, and dynamic-temperature scaling to achieve balanced representation learning across both common and rare categories. Extensive experiments on three benchmark datasets (DLRSD, ML-AID, and WHDLD), show that MACL consistently outperforms contrastive-loss based baselines, effectively mitigating semantic imbalance and delivering more reliable retrieval performance in large-scale remote-sensing archives. Code, pretrained models, and evaluation scripts will be released at https://github.com/Amna-128/MARC upon acceptance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyamir2025marc

Code

• Amna-128/MARC—

Related papers

• Mlrsnet: A Multi-label High Spatial Resolution Remote Sensing Dataset For Semantic Scene Understanding (2020)19.63
• CMIR-NET : A Deep Learning Based Model For Cross-modal Retrieval In Remote Sensing (2019)13.34
• Annotation Cost-efficient Active Learning For Deep Metric Learning Driven Remote Sensing Image Retrieval (2024)3.58
• Robust Cross-modal Representation Learning With Progressive Self-distillation (2022)12.33
• Exploring A Fine-grained Multiscale Method For Cross-modal Remote Sensing Image Retrieval (2022)16.73
• Generalized Contrastive Learning For Multi-modal Retrieval And Ranking (2024)6.01
• Learning Regional Attention Over Multi-resolution Deep Convolutional Features For Trademark Retrieval (2021)5.84
• MCA: 2D-3D Retrieval With Noisy Labels Via Multi-level Adaptive Correction And Alignment (2025)0.00