Large Scale Visual Recognition through Adaptation using Joint Representation and Multiple Instance Learning

Journal of Machine Learning Research, Volume 17, 2016, Pages 142:1-142:31.

Cited by: 12|Bibtex|Views209
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

A major barrier towards scaling visual recognition systems is the difficulty of obtaining labeled images for large numbers of categories. Recently, deep convolutional neural networks (CNNs) trained used 1.2M+ labeled images have emerged as clear winners on object classification benchmarks. Unfortunately, only a small fraction of those lab...More

Code:

Data:

Your rating :
0

 

Tags
Comments