Timezone: »

Reshaping Visual Datasets for Domain Adaptation
Boqing Gong · Kristen Grauman · Fei Sha

Sun Dec 08 02:00 PM -- 06:00 PM (PST) @ Harrah's Special Events Center, 2nd Floor #None

In visual recognition problems, the common data distribution mismatches between training and testing make domain adaptation essential. However, image data is difficult to manually divide into the discrete domains required by adaptation algorithms, and the standard practice of equating datasets with domains is a weak proxy for all the real conditions that alter the statistics in complex ways (lighting, pose, background, resolution, etc.) We propose an approach to automatically discover latent domains in image or video datasets. Our formulation imposes two key properties on domains: maximum distinctiveness and maximum learnability. By maximum distinctiveness, we require the underlying distributions of the identified domains to be different from each other; by maximum learnability, we ensure that a strong discriminative model can be learned from the domain. We devise a nonparametric representation and efficient optimization procedure for distinctiveness, which, when coupled with our learnability constraint, can successfully discover domains among both training and test data. We extensively evaluate our approach on object recognition and human activity recognition tasks.

Author Information

Boqing Gong (University of Southern California (USC))
Kristen Grauman (University of Texas at Austin)
Fei Sha (University of Southern California (USC))

More from the Same Authors