Training OOD Detectors in their Natural Habitats
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data, which naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. Our key idea is to formulate a constrained optimization problem and to show how to tractably solve it. Our learning objective maximizes the OOD detection rate, subject to constraints on the classification error of ID data and on the OOD error rate of ID examples. We extensively evaluate our approach on common OOD detection tasks and demonstrate superior performance.
Code (1)
Tasks
BIG-bench Machine LearningOut of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Image background assessment as a novel technique for insect microhabitat identification
The effects of climate change, urbanisation and agriculture are changing the way insects occupy habitats. Some species may utilise anthropogenic microhabitat features for their existence, either because they prefer them …
ManagementAnimal Detection in Man-made Environments
Automatic detection of animals that have strayed into human inhabited areas has important security and road safety applications. This paper attempts to solve this problem using deep learning techniques from a variety of …
Edge Detectionobject-detectionObject DetectionSynthetic Data Generation+1Automated classification of natural habitats using ground-level imagery
Accurate classification of terrestrial habitats is critical for biodiversity conservation, ecological monitoring, and land-use planning. Several habitat classification schemes are in use, typically based on analysis of s…
SOCRATES: A Stereo Camera Trap for Monitoring of Biodiversity
The development and application of modern technology is an essential basis for the efficient monitoring of species in natural habitats and landscapes to trace the development of ecosystems, species communities, and popul…
Instance SegmentationStereo MatchingAutonomous Mosquito Habitat Detection Using Satellite Imagery and Convolutional Neural Networks for Disease Risk Mapping
Mosquitoes are known vectors for disease transmission that cause over one million deaths globally each year. The majority of natural mosquito habitats are areas containing standing water that are challenging to detect us…