Learning Rare Category Classifiers on a Tight Labeling Budget
Abstract Many real-world ML deployments require learning a rare category model with a small labeling budget. Because often one also has access to large amounts of unlabeled data, it is...
Low-shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
Abstract For machine learning models trained with limited labeled training data, validation stands to become the main bottleneck to reducing overall annotation costs. We propose a statistical validation algorithm that...
Background Splitting: Finding Rare Classes in a Sea of Background
Abstract Video In this paper, we focus on the problem of training deep image classification models for a small number of extremely rare categories. In this common, real-world scenario, almost...
Processing Terabytes of Video on Hundreds of Machines
Starting off as a graduate student at Carnegie Mellon University, I was really excited about the many new types of applications that leaned heavily on computer vision to process videos....
Scanner: Efficient Video Analysis at Scale
Abstract Video A growing number of visual computing applications depend on the analysis of large video collections. The challenge is that scaling applications to operate on these datasets requires efficient...
Learning Patch Reconstructability for Accelerating Multi-View Stereo
Abstract We present an approach to accelerate multi-view stereo (MVS) by prioritizing computation on image patches that are likely to produce accurate 3D surface reconstructions. Our key insight is that...