3 citations · 4 across the 3 of their papers we have counts for
3 papers · 1 filter
Top-down Neural Attention by Excitation Backprop
Jianming Zhang, Zhe Lin, Jonathan Brandt +2
We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention…
Decomposition-Based Domain Adaptation for Real-World Font Recognition
Zhangyang Wang, Jianchao Yang, Hailin Jin +4
We present a domain adaption framework to address a domain mismatch between synthetic training and real-world testing data. We demonstrate our method on a challenging fine-grain cl…
Scalable Similarity Learning using Large Margin Neighborhood Embedding
Zhaowen Wang, Jianchao Yang, Zhe Lin +3
Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric app…