ProcSim: Proxy-based Confidence for Robust Similarity Learning
Not on the map. Why?
Abstract (arXiv)
Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized distance to its class representative. The experimental results show that the proposed method achieves state-of-the-art performance on the DML benchmark datasets injected with uniform and the proposed semantically coherent noise.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 50 of its 73 references that are in the map. First posted on arXiv 1 Nov 2023.
Builds on
50 of 73 references.
References · 50
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
- 2017A Closer Look at Memorization in Deep Networkscited by 942
38 more
- 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
- 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
- 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
- 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
- 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
- 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
- 2020A Metric Learning Reality Checkcited by 321
- 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
- 2017Sampling Matters in Deep Embedding Learningcited by 285
- 2017No Fuss Distance Metric Learning using Proxiescited by 226
- 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
- 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
- 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
- 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
- 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
- 2019Cross-Batch Memory for Embedding Learningcited by 132
- 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
- 2018Deep Metric Learning with Hierarchical Triplet Losscited by 112
- 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
- 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
- 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
- 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 88
- 2019Improved Embeddings with Easy Positive Triplet Miningcited by 67
- 2020DiVA: Diverse Visual Feature Aggregation for Deep Metric Learningcited by 40
- 2019Divide and Conquer the Embedding Space for Metric Learningcited by 39
- 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
- 2018Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspectioncited by 27
- 2020Transferring Dense Pose to Proximal Animal Classescited by 23
- 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
- 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
- 2021Hierarchical Proxy-based Loss for Deep Metric Learningcited by 18
- 2019Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrievalcited by 15
- 2021Adaptive Hierarchical Similarity Metric Learning with Noisy Labelscited by 8
- 2021Learning with Label Noise for Image Retrieval by Selecting Interactionscited by 8
- 2022Deep Image Retrieval is not Robust to Label Noisecited by 2
- 2019Semantic Granularity Metric Learning for Visual Searchcited by 1
- 2022Improving Generalization of Metric Learning via Listwise Self-distillationcited by 1
Built on by
Citing papers per year: 2024: 2.
2 papers.