mlsanityData to 7 Oct 2026

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

arXiv 2101.01260 ↗First posted 4 Jan 2021cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes with a completely independent set of parameters. While this guarantees high performance, it is also highly inefficient, as each model has to be separately downloaded and stored. In this paper we address the question: can task-specific detectors be trained and represented as a shared set of weights, plus a very small set of additional weights for each task? The main contributions of this paper are the following: 1) we perform the first systematic study of parameter-efficient transfer learning techniques for object detection problems; 2) we propose a technique to learn a model patch with a size that is dependent on the difficulty of the task to be learned, and validate our approach on 10 different object detection tasks. Our approach achieves similar accuracy as previously proposed approaches, while being significantly more compact.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 4 Jan 2021.

Builds on

36 of 55 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2019Searching for MobileNetV3cited by 1,984
  10. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  11. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  12. 2014How transferable are features in deep neural networks?cited by 1,216
24 more
  1. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  2. 2017Learning multiple visual domains with residual adapterscited by 553
  3. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  4. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  5. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
  6. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  7. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  8. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  9. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  10. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  11. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 166
  12. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  13. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  14. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  15. 2017Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Executioncited by 59
  16. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  17. 2019Few-shot Adaptive Faster R-CNNcited by 42
  18. 2019Depthwise Convolution is All You Need for Learning Multiple Visual Domainscited by 36
  19. 2018K for the Price of 1: Parameter-efficient Multi-task and Transfer Learningcited by 34
  20. 2019RPC: A Large-Scale Retail Product Checkout Datasetcited by 27
  21. 2017Revisiting knowledge transfer for training object class detectorscited by 26
  22. 2018Adding New Tasks to a Single Network with Weight Transformations using Binary Maskscited by 21
  23. 2018UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networkscited by 9
  24. 2015Seeing Behind the Camera: Identifying the Authorship of a Photographcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2023StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptationcited by 4
  2. 2026YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Familycited by 0