mlsanityData to 7 Oct 2026

5th Place Solution to Kaggle Google Universal Image Embedding Competition

arXiv 2210.09495 ↗First posted 18 Oct 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In this paper, we present our solution, which placed 5th in the kaggle Google Universal Image Embedding Competition in 2022. We use the ViT-H visual encoder of CLIP from the openclip repository as a backbone and train a head model composed of BatchNormalization and Linear layers using ArcFace. The dataset used was a subset of products10K, GLDv2, GPR1200, and Food101. And applying TTA for part of images also improves the score. With this method, we achieve a score of 0.684 on the public and 0.688 on the private leaderboard. Our code is available. https://github.com/riron1206/kaggle-Google-Universal-Image-Embedding-Competition-5th-Place-Solution

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

13 of 18 references.

References · 13

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  6. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  7. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  8. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  9. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  10. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  11. 2020Products-10K: A Large-scale Product Recognition Datasetcited by 42
  12. 2021GPR1200: A Benchmark for General-Purpose Content-Based Image Retrievalcited by 14
1 more
  1. 20221st Place Solution in Google Universal Images Embeddingcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  2. 2024Efficient and Discriminative Image Feature Extraction for Universal Image Retrievalcited by 1