Brand is Beyond Logos – Understanding Visual Brand
Logos come to mind when we think about iconic brands. However, a spectrum of visual cues is used to establish the signature of a brand. This includes color, pattern, shape. We train deep neural network to predict a variety of fashion brand and analyze visual representations using strength and extent of neuron activations. Logo is demonstrated to be at one end of the spectrum. Study of versatility of neurons shows that they are diverse in nature and contain specialists and generalists. Potential applications of making neural network explainable include personalization, elimination of bias in prediction, model improvement. This includes image quality, visual search, segmentation, pose estimation, iris/face recognition, coarse and fine grained prediction.
Robinson Piramuthu is currently head of “AI - Computer Vision” at the New Product Development organization at eBay Inc. He has over 20 years of experience in computer vision. Robinson joined eBay Research Labs in 2011 and was later head of the computer vision team, which specialized in computer vision research for visual commerce. Robinson has technical publications at top conferences such as CVPR, ICCV, KDD, WSDM, WACV, ICIP. He co-organized the workshop on Large Scale Visual Commerce at ICCV ’13 Sydney and at CVPR ’15. He received his PhD from University of Michigan Ann Arbor in 2000.