Generalized Sparselet Models for Real-Time Multiclass Object Recognition

Hyun Oh Song, Ross Girshick, Stefan Zickler, Christopher Geyer,
Pedro Felzenszwalb, Trevor Darrell

Abstract

The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with deformable part models at 5Hz on a laptop computer with almost no decrease in task performance. Our framework is trained in the standard structured output prediction formulation and is generically applicable for speeding up object recognition systems where the computational bottleneck is in multiclass, multi-convolutional inference. We experimentally demonstrate the efficiency and task performance of our method on PASCAL VOC, subset of ImageNet, Caltech101 and Caltech256 dataset.


Demo Video 1



Demo Video 2



References

Generalized Sparselet Models for Real-Time Multiclass Object Recognition
Hyun Oh Song, Ross Girshick, Stefan Zickler, Christopher Geyer, Pedro Felzenszwalb, Trevor Darrell
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
paper / code

Sparselet Models for Efficient Multiclass Object Detection
Hyun Oh Song, Stefan Zickler, Tim Althoff, Ross Girshick, Mario Fritz, Christopher Geyer, Pedro Felzenszwalb, Trevor Darrell
European Conference on Computer Vision (ECCV), 2012
paper / poster / bibtex

Discriminatively Activated Sparselets
Hyun Oh Song*, Ross Girshick*, Trevor Darrell
International Conference on Machine Learning (ICML), 2013
Oral presentation
paper / slide / poster / supp / bibtex