DAP: Detection-Aware Pre-training with Weak Supervision

@article{Zhong2021DAPDP,
  title={DAP: Detection-Aware Pre-training with Weak Supervision},
  author={Yuanyi Zhong and Jianfeng Wang and Lijuan Wang and Jian Peng and Yu-Xiong Wang and Lei Zhang},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={4535-4544}
}
  • Yuanyi Zhong, Jianfeng Wang, +3 authors Lei Zhang
  • Published 30 March 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pretraining, 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… Expand

References

SHOWING 1-10 OF 52 REFERENCES
DSOD: Learning Deeply Supervised Object Detectors from Scratch
TLDR
Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch following the single-shot detection (SSD) framework, and one of the key findings is that deep supervision, enabled by dense layer-wise connections, plays a critical role in learning a good detector. Expand
An Analysis of Pre-Training on Object Detection
TLDR
This work provides a detailed analysis of convolutional neural networks which are pre-trained on the task of object detection, and analyzes how well their features generalize to tasks like image classification, semantic segmentation and object detection on small datasets like PASCAL-VOC, Caltech-256, SUN-397, Flowers-102 etc. Expand
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
TLDR
An effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain, is proposed. Expand
Attention-Based Dropout Layer for Weakly Supervised Object Localization
  • Junsuk Choe, Hyunjung Shim
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
An Attention-based Dropout Layer (ADL), which utilizes the self-attention mechanism to process the feature maps of the model to improve the accuracy of WSOL, achieving a new state-of-the-art localization accuracy in CUB-200-2011 dataset. Expand
WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection
TLDR
This paper proposes a novel WSOD framework with Objectness Distillation (i.e., WSOD2) by designing a tailored training mechanism for weakly-supervised object detection, and explores different adaptive training curves for BU/TD objectness, and shows that the proposedWSOD2 can achieve state-of-the-art results. Expand
Rethinking ImageNet Pre-Training
TLDR
Experiments show that ImageNet pre-training speeds up convergence early in training, but does not necessarily provide regularization or improve final target task accuracy, and these discoveries will encourage people to rethink the current de facto paradigm of `pre-training and fine-tuning' in computer vision. Expand
Weakly Supervised Deep Detection Networks
  • Hakan Bilen, A. Vedaldi
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper proposes a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification. Expand
Exploring the Limits of Weakly Supervised Pretraining
TLDR
This paper presents a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images and shows improvements on several image classification and object detection tasks, and reports the highest ImageNet-1k single-crop, top-1 accuracy to date. Expand
ScratchDet: Training Single-Shot Object Detectors From Scratch
  • Rui Zhu, Shifeng Zhang, +4 authors Tao Mei
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
The ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods. Expand
Evaluating Weakly Supervised Object Localization Methods Right
TLDR
It is argued that WSOL task is ill-posed with only image-level labels, and a new evaluation protocol is proposed where full supervision is limited to only a small held-out set not overlapping with the test set. Expand
...
1
2
3
4
5
...