LocNet: Improving Localization Accuracy for Object Detection
Authors:
- Spyros GidarisSGSpyros Gidaris
- Nikos KomodakisNKNikos Komodakis
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 789-798
Abstract
We propose a novel object localization methodology with the purpose of boosting the localization accuracy of stateof-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of interest inside this region. To accomplish its goal, it relies on assigning conditional probabilities to each row and column of this region, where these probabilities provide useful information regarding the location of the boundaries of the object inside the search region and allow the accurate inference of the object bounding box under a simple probabilistic framework. For implementing our localization model, we make use of a convolutional neural network architecture that is properly adapted for this task, called LocNet. We show experimentally that LocNet achieves a very significant improvement on the mAP for high IoU thresholds on PASCAL VOC2007 test set and that it can be very easily coupled with recent stateof-the-art object detection systems, helping them to boost their performance. Finally, we demonstrate that our detection approach can achieve high detection accuracy even when it is given as input a set of sliding windows, thus proving that it is independent of box proposal methods.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection2015
- An active search strategy for efficient object class detection2015
- Going deeper with convolutions2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Multiscale Combinatorial Grouping2014
- BING: Binarized Normed Gradients for Objectness Estimation at 300fps2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Cracking BING and Beyond2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989