mlsanityData to 14 Oct 2026

DAP: Detection-Aware Pre-training with Weak Supervision

arXiv 2103.16651 ↗First posted 30 Mar 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In contrast to the widely used image classification-based pre-training (e.g., on ImageNet), which does not include any location-related training tasks, we transform a classification dataset into a detection dataset through a weakly supervised object localization method based on Class Activation Maps to directly pre-train a detector, making the pre-trained model location-aware and capable of predicting bounding boxes. We show that DAP can outperform the traditional classification pre-training in terms of both sample efficiency and convergence speed in downstream detection tasks including VOC and COCO. In particular, DAP boosts the detection accuracy by a large margin when the number of examples in the downstream task is small.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 40 of its 53 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

40 of 53 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  9. 2017Mask R-CNNcited by 7,277
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
28 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  3. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  4. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  5. 2017Focal Loss for Dense Object Detectioncited by 752
  6. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  7. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  8. 2018Rethinking ImageNet Pre-trainingcited by 377
  9. 2020Rethinking Pre-training and Self-trainingcited by 352
  10. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  11. 2015Weakly Supervised Deep Detection Networkscited by 183
  12. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
  13. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  14. 2019Attention-based Dropout Layer for Weakly Supervised Object Localizationcited by 125
  15. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  16. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 105
  17. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 99
  18. 2018Self-produced Guidance for Weakly-supervised Object Localizationcited by 72
  19. 2019WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detectioncited by 51
  20. 2017DSOD: Learning Deeply Supervised Object Detectors from Scratchcited by 41
  21. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  22. 2014Analyzing the Performance of Multilayer Neural Networks for Object Recognitioncited by 29
  23. 2020Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfercited by 28
  24. 2018TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detectioncited by 22
  25. 2018ScratchDet: Training Single-Shot Object Detectors from Scratchcited by 19
  26. 2019An Analysis of Pre-Training on Object Detectioncited by 12
  27. 2020Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detectioncited by 6
  28. 2019Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrumcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1.

7 papers.

  1. 2022Is Self-Supervised Learning More Robust Than Supervised Learning?cited by 17
  2. 2023Region-centric Image-Language Pretraining for Open-Vocabulary Detectioncited by 8
  3. 2022GPTR: Gestalt-Perception Transformer for Diagram Object Detectioncited by 2
  4. 2023Morphology-Enhanced CAM-Guided SAM for weakly supervised Breast Lesion Segmentationcited by 1
  5. 2022Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detectioncited by 0
  6. 2023Hypernymization of named entity-rich captions for grounding-based multi-modal pretrainingcited by 0
  7. 2024Weakly-Supervised Anomaly Detection in Surveillance Videos Based on Two-Stream I3D Convolution Networkcited by 0