Bay Area Vision Meeting: Visual Recognition via Feature Learning

Bay Area Vision Meeting (more info below) Visual Recognition via Feature Learning Kai Yu March 7, 2011 ABSTRACT In this talk I will share some of our experiences at NEC Labs about large-scale image recognition by using feature learning. We worked on extending sparse coding to a broader family of nonlinear coding methods that explore the geometrical structure of sensory image data. The coding of image local features gives rise to significantly better image representations, which enables simple linear classifiers to achieve stronger performance than traditional nonlinear SVMs. The methods achieved state-of-the-art results on a range of challenging scene classification & object recognition tasks, including Caltech 101, Caltech 256, PASCAL VOC, and ImageNet.