Active Testing for Face Detection and Localization

Abstract

We provide a novel search technique, which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images. We show exponential gains in computation over traditional sliding window approaches, while keeping similar performance levels.

16 pages, 5 figures, accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010

Cited by in corpus (13)

• WhittleSearch: Interactive Image Search with Relative Attribute Feedback
• Learning Sampling Distributions for Efficient Object Detection
• Multi-environment model estimation for motility analysis of Caenorhabditis Elegans
• Geometry in Active Learning for Binary and Multi-class Image Segmentation
• Robust Periocular Recognition By Fusing Sparse Representations of Color and Geometry Information
• Optimal Solutions for Adaptive Search Problems with Entropy Objectives
• Asynchronous Decentralized 20 Questions for Adaptive Search
• An active search strategy for efficient object class detection
• Interpretable by Design: Learning Predictors by Composing Interpretable Queries
• Probabilistic Group Testing under Sum Observations: A Parallelizable 2-Approximation for Entropy Loss
• Robust Active Learning for Electrocardiographic Signal Classification
• Active query-driven visual search using probabilistic bisection and convolutional neural networks
• On Decentralized Estimation with Active Queries