mlsanityData to 7 Oct 2026

Multi Positive Contrastive Learning with Pose-Consistent Generated Images

arXiv 2404.03256 ↗First posted 4 Apr 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Model pre-training has become essential in various recognition tasks. Meanwhile, with the remarkable advancements in image generation models, pre-training methods utilizing generated images have also emerged given their ability to produce unlimited training data. However, while existing methods utilizing generated images excel in classification, they fall short in more practical tasks, such as human pose estimation. In this paper, we have experimentally demonstrated it and propose the generation of visually distinct images with identical human poses. We then propose a novel multi-positive contrastive learning, which optimally utilize the previously generated images to learn structural features of the human body. We term the entire learning pipeline as GenPoCCL. Despite using only less than 1% amount of data compared to current state-of-the-art method, GenPoCCL captures structural features of the human body more effectively, surpassing existing methods in a variety of human-centric perception tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 55 of its 67 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

55 of 67 references.

References · 55

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  8. 2020Denoising Diffusion Implicit Modelscited by 9,655
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  12. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
38 more
  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  10. 2015Variational Inference with Normalizing Flowscited by 2,161
  11. 2016Density estimation using Real NVPcited by 2,029
  12. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  13. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  14. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  15. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  16. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  17. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  18. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  19. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  20. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  21. 2018Albumentations: fast and flexible image augmentationscited by 558
  22. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  23. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  24. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  25. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 298
  26. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  27. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  28. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 171
  29. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  30. 2021DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrievalcited by 102
  31. 2020Unsupervised Pre-training for Person Re-identificationcited by 94
  32. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  33. 2017HydraPlus-Net: Attentive Deep Features for Pedestrian Analysiscited by 89
  34. 2023Learning Vision from Models Rivals Learning Vision from Datacited by 71
  35. 2024SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?cited by 64
  36. 2022Learning Granularity-Unified Representations for Text-to-Image Person Re-identificationcited by 62
  37. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  38. 20193DPeople: Modeling the Geometry of Dressed Humanscited by 58

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.