Details

Autor(en) / Beteiligte

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

Titel

Generalized Sparselet Models for Real-Time Multiclass Object Recognition

Ist Teil von

• IEEE transactions on pattern analysis and machine intelligence, 2015-05, Vol.37 (5), p.1001-1012

Ort / Verlag

United States: IEEE

Erscheinungsjahr

2015

Quelle

IEEE Xplore

Beschreibungen/Notizen

• 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.