Deep Image Retrieval is not Robust to Label Noise
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 23 May 2022.
Builds on
26 of 35 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
- 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
- 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
- 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
- 2020A Metric Learning Reality Checkcited by 321
- 2018Deep Face Recognition: A Surveycited by 276
- 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
14 more
- 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
- 2017No Fuss Distance Metric Learning using Proxiescited by 226
- 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
- 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 200
- 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
- 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
- 2018The Devil of Face Recognition is in the Noisecited by 65
- 2015The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognitioncited by 48
- 2017Level Playing Field for Million Scale Face Recognitioncited by 43
- 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
- 2020NoiseRank: Unsupervised Label Noise Reduction with Dependence Modelscited by 20
- 2017Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Predictioncited by 19
- 2018An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Imagescited by 11
- 2021Learning with Label Noise for Image Retrieval by Selecting Interactionscited by 8
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.