Self-taught object localization with deep networks
- 1 March 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using any ground-truth bounding boxes for training. The key idea is to analyze the change in the recognition scores when artificially masking out different regions of the image. The masking out of a region that includes the object typically causes a significant drop in recognition score. This idea is embedded into an agglomerative clustering technique that generates self-taught localization hypotheses. Our object localization scheme outperforms existing proposal methods in both precision and recall for small number of subwindow proposals (e.g., on ILSVRC-2012 it produces a relative gain of 23.4% over the state-of-the-art for top-1 hypothesis). Furthermore, our experiments show that the annotations automatically-generated by our method can be used to train object detectors yielding recognition results remarkably close to those obtained by training on manually-annotated bounding boxes.Keywords
Other Versions
This publication has 21 references indexed in Scilit:
- Object proposal by multi-branch hierarchical segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- PANDA: Pose Aligned Networks for Deep Attribute ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Weakly Supervised Object Localization with Latent Category LearningLecture Notes in Computer Science, 2014
- Simultaneous Detection and SegmentationLecture Notes in Computer Science, 2014
- How good are detection proposals, really?Published by British Machine Vision Association and Society for Pattern Recognition ,2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004