mlsanityData to 14 Oct 2026

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

arXiv 1310.1531 ↗First posted 6 Oct 2013cs.CVcited by 424

Not on the map. Why?

Abstract (arXiv)

We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks and there may be insufficient labeled or unlabeled data to conventionally train or adapt a deep architecture to the new tasks. We investigate and visualize the semantic clustering of deep convolutional features with respect to a variety of such tasks, including scene recognition, domain adaptation, and fine-grained recognition challenges. We compare the efficacy of relying on various network levels to define a fixed feature, and report novel results that significantly outperform the state-of-the-art on several important vision challenges. We are releasing DeCAF, an open-source implementation of these deep convolutional activation features, along with all associated network parameters to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.

Key facts. Cited by 424 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Oct 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 132; 2022: 108; 2023: 73; 2024: 56; 2025: 29; 2026: 24.

424 papers.

Sort:

By area:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  2. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  3. 2021Domain Generalization: A Surveycited by 764
  4. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 577
  5. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  6. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
  7. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 334
  8. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  9. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
  10. 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapterscited by 199
  11. 2022Unified Contrastive Learning in Image-Text-Label Spacecited by 194
  12. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
38 more
  1. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 173
  2. 2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 172
  3. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  4. 2022On-Device Training Under 256KB Memorycited by 160
  5. 2022Knowledge Distillation with the Reused Teacher Classifiercited by 141
  6. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  7. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  8. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  9. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  10. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  11. 2023The Expressive Power of Low-Rank Adaptationcited by 102
  12. 2021Pre-training without Natural Imagescited by 100
  13. 2021Region Similarity Representation Learningcited by 96
  14. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  15. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
  16. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  17. 2021A Survey on Bias in Visual Datasetscited by 84
  18. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  19. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  20. 2023Modular Deep Learningcited by 83
  21. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 82
  22. 2022An Information-Theoretic Approach to Transferability in Task Transfer Learningcited by 81
  23. 2021A Broad Study on the Transferability of Visual Representations with Contrastive Learningcited by 78
  24. 2024RLHF from Heterogeneous Feedback via Personalization and Preference Aggregationcited by 74
  25. 2023Learning Vision from Models Rivals Learning Vision from Datacited by 71
  26. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 68
  27. 2023The effectiveness of MAE pre-pretraining for billion-scale pretrainingcited by 68
  28. 2021Editing a classifier by rewriting its prediction rulescited by 65
  29. 2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
  30. 2021Pre-trained Gaussian Processes for Bayesian Optimizationcited by 63
  31. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  32. 2022Bootstrapped Masked Autoencoders for Vision BERT Pretrainingcited by 60
  33. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 60
  34. 2021Distributed Deep Learning in Open Collaborationscited by 58
  35. 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
  36. 2022Transferability in Deep Learning: A Surveycited by 57
  37. 2021DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingcited by 56
  38. 2023Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspectivecited by 54

50 most cited of 424 All 424 (JSON)