mlsanityData to 14 Oct 2026

Large-Scale Product Retrieval with Weakly Supervised Representation Learning

arXiv 2208.00955 ↗First posted 1 Aug 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Large-scale weakly supervised product retrieval is a practically useful yet computationally challenging problem. This paper introduces a novel solution for the eBay Visual Search Challenge (eProduct) held at the Ninth Workshop on Fine-Grained Visual Categorisation workshop (FGVC9) of CVPR 2022. This competition presents two challenges: (a) E-commerce is a drastically fine-grained domain including many products with subtle visual differences; (b) A lacking of target instance-level labels for model training, with only coarse category labels and product titles available. To overcome these obstacles, we formulate a strong solution by a set of dedicated designs: (a) Instead of using text training data directly, we mine thousands of pseudo-attributes from product titles and use them as the ground truths for multi-label classification. (b) We incorporate several strong backbones with advanced training recipes for more discriminative representation learning. (c) We further introduce a number of post-processing techniques including whitening, re-ranking and model ensemble for retrieval enhancement. By achieving 71.53% MAR, our solution "Involution King" achieves the second position on the leaderboard.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2020Supervised Contrastive Learningcited by 2,829
  6. 2019Contrastive Multiview Codingcited by 1,301
  7. 2017Random Erasing Data Augmentationcited by 1,239
  8. 2016Deep Networks with Stochastic Depthcited by 979
  9. 2021Going deeper with Image Transformerscited by 764
  10. 2017Focal Loss for Dense Object Detectioncited by 752
  11. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  12. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
13 more
  1. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 227
  2. 2021Whitening Sentence Representations for Better Semantics and Faster Retrievalcited by 202
  3. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  4. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  5. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  6. 2021ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationcited by 69
  7. 2021WhiteningBERT: An Easy Unsupervised Sentence Embedding Approachcited by 69
  8. 2022PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functionscited by 63
  9. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  10. 2021One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objectivecited by 43
  11. 2022FashionViL: Fashion-Focused Vision-and-Language Representation Learningcited by 32
  12. 2022CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrievalcited by 25
  13. 2021eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challengescited by 6

Built on by

Not cited yet.