Ravi Teja Mullapudi

Dynamic Model Specialization for Efficient Inference, Training and Supervision

Learning rare category classifiers on a tight labeling budget

Low-shot validation: Active importance sampling for estimating classifier performance on rare categories

Background splitting: Finding rare classes in a sea of background

Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings

Learning to move with affordance maps