Abstract | ||
---|---|---|
Data-driven approaches for edge detection have proven effective and achieve top results on modern benchmarks. However, all current data-driven edge detectors require manual supervision for training in the form of hand-labeled region segments or object boundaries. Specifically, human annotators mark semantically meaningful edges which are subsequently used for training. Is this form of strong, high-level supervision actually necessary to learn to accurately detect edges? In this work we present a simple yet effective approach for training edge detectors without human supervision. To this end we utilize motion, and more specifically, the only input to our method is noisy semi-dense matches between frames. We begin with only a rudimentary knowledge of edges (in the form of image gradients), and alternate between improving motion estimation and edge detection in turn. Using a large corpus of video data, we show that edge detectors trained using our unsupervised scheme approach the performance of the same methods trained with full supervision (within 3-5%). Finally, we show that when using a deep network for the edge detector, our approach provides a novel pre-training scheme for object detection. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/CVPR.2016.179 | 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
Field | DocType | Volume |
Object detection,Computer vision,Pattern recognition,Computer science,Edge detection,Edge detector,Unsupervised learning,Artificial intelligence,Motion estimation,Detector,Machine learning | Journal | abs/1511.04166 |
Issue | ISSN | Citations |
1 | 1063-6919 | 1 |
PageRank | References | Authors |
0.36 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yin Li | 1 | 797 | 35.85 |
Manohar Paluri | 2 | 1237 | 56.52 |
James M. Rehg | 3 | 5259 | 474.66 |
Piotr Dollár | 4 | 7999 | 307.07 |