Learning Features by Watching Objects Move
Deepak Pathak, Ross Girshick, Piotr Dollár et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2017
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation. Specifically, we use unsupervised motion-based segmentation on videos to obtain segments, which we use as pseudo ground truth to train a convolutional network to segment objects from a single frame. Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed pretext tasks studied in the literature. Indeed, our extensive experiments show that this is the case. When used for transfer learning on object detection, our representation significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target task is scarce.
Cited by 436 works. doi:10.1109/cvpr.2017.638
Authors
References
- ImageNet classification with deep convolutional neural networks
- ImageNet Large Scale Visual Recognition Challenge
- Histograms of Oriented Gradients for Human Detection
- Fully convolutional networks for semantic segmentation
- Reducing the Dimensionality of Data with Neural Networks
- Microsoft COCO: Common Objects in Context
- Fast R-CNN
- GAN(Generative Adversarial Nets)
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning Deep Architectures for AI