mlsanityData to 7 Oct 2026

SpotTune: Transfer Learning through Adaptive Fine-tuning

arXiv 1811.08737 ↗First posted 21 Nov 2018cs.CV cs.LG stat.MLcited by 166

Not on the map. Why?

Abstract (arXiv)

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained on the source task using data from the target task. In this paper, we propose an adaptive fine-tuning approach, called SpotTune, which finds the optimal fine-tuning strategy per instance for the target data. In SpotTune, given an image from the target task, a policy network is used to make routing decisions on whether to pass the image through the fine-tuned layers or the pre-trained layers. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach. Our method outperforms the traditional fine-tuning approach on 12 out of 14 standard datasets.We also compare SpotTune with other state-of-the-art fine-tuning strategies, showing superior performance. On the Visual Decathlon datasets, our method achieves the highest score across the board without bells and whistles.

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 37; 2023: 48; 2024: 23; 2025: 19; 2026: 4.

166 papers.

Sort:

By area:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  2. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  3. 2021Dynamic Neural Networks: A Surveycited by 405
  4. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  5. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  6. 2022Are Multimodal Transformers Robust to Missing Modality?cited by 183
  7. 2023SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Modelcited by 178
  8. 2022Finetune like you pretrain: Improved finetuning of zero-shot vision modelscited by 149
  9. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  10. 2022Three things everyone should know about Vision Transformerscited by 90
  11. 2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
  12. 2023Sensitivity-Aware Visual Parameter-Efficient Fine-Tuningcited by 74
38 more
  1. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  2. 2022Transferability in Deep Learning: A Surveycited by 57
  3. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  4. 2021AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognitioncited by 48
  5. 2021Improved Regularization and Robustness for Fine-tuning in Neural Networkscited by 45
  6. 2022Task Adaptive Parameter Sharing for Multi-Task Learningcited by 42
  7. 2022No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligencecited by 41
  8. 2021Scalable Diverse Model Selection for Accessible Transfer Learningcited by 40
  9. 2023Gradient-based Parameter Selection for Efficient Fine-Tuningcited by 40
  10. 2023Pre-trained Trojan Attacks for Visual Recognitioncited by 38
  11. 2021Adaptive Consistency Regularization for Semi-Supervised Transfer Learningcited by 37
  12. 2023Trainable Projected Gradient Method for Robust Fine-tuningcited by 37
  13. 2021AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognitioncited by 36
  14. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  15. 2021Improved Fine-Tuning by Better Leveraging Pre-Training Datacited by 36
  16. 2023FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policycited by 36
  17. 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
  18. 2024Revisiting the Power of Prompt for Visual Tuningcited by 32
  19. 2022Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoderscited by 30
  20. 2022TeST: Test-time Self-Training under Distribution Shiftcited by 29
  21. 2022Amplifying Membership Exposure via Data Poisoningcited by 29
  22. 2022Context-Aware Robust Fine-Tuningcited by 27
  23. 2022Fair Generative Models via Transfer Learningcited by 27
  24. 2021Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Datacited by 26
  25. 2023On the Connection between Pre-training Data Diversity and Fine-tuning Robustnesscited by 25
  26. 2022FedAdapter: Efficient Federated Learning for Modern NLPcited by 24
  27. 2022How to Fine-Tune Vision Models with SGDcited by 23
  28. 2022Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezingcited by 22
  29. 2022Spot-adaptive Knowledge Distillationcited by 22
  30. 2023A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directionscited by 22
  31. 2023How to prepare your task head for finetuningcited by 18
  32. 2023GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learningcited by 18
  33. 2023Fast Trainable Projection for Robust Fine-Tuningcited by 18
  34. 2023Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and Howcited by 17
  35. 2022Pre-trained Adversarial Perturbationscited by 16
  36. 2021Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learningcited by 15
  37. 2021VA-RED2: Video Adaptive Redundancy Reductioncited by 15
  38. 2022Federated Few-Shot Learning for Mobile NLPcited by 15

50 most cited of 166 All 166 (JSON)