Deep Image Retrieval Is Not Robust To Label Noise

Abstract

Large-scale datasets are essential for the success of deep learning in image retrieval. However, manual assessment errors and semi-supervised annotation techniques can lead to label noise even in popular datasets. As previous works primarily studied annotation quality in image classification tasks, it is still unclear how label noise affects deep learning approaches to image retrieval. In this work, we show that image retrieval methods are less robust to label noise than image classification ones. Furthermore, we, for the first time, investigate different types of label noise specific to image retrieval tasks and study their effect on model performance.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keydereka2022deep

Related papers

• Learning With Label Noise For Image Retrieval By Selecting Interactions (2021)8.35
• End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66
• Noisy Self-training With Synthetic Queries For Dense Retrieval (2023)0.00
• Adapnet: Adaptive Noise-based Network For Low-quality Image Retrieval (2024)0.00
• A Review Of Image Retrieval Techniques: Data Augmentation And Adversarial Learning Approaches (2024)0.00
• Hard Negatives, Hard Lessons: Revisiting Training Data Quality For Robust Information Retrieval With Llms (2025)2.26
• INTENT: Invariance And Discrimination-aware Noise Mitigation For Robust Composed Image Retrieval (2026)0.00
• Exploring Uncertainty Measures For Image-caption Embedding-and-retrieval Task (2019)2.26