Probing Contextual Diversity for Dense Out-of-Distribution Detection
Detection of out-of-distribution (OoD) samples in the context of image classification has recently become an area of interest and active study, along with the topic of uncertainty estimation, to which it is closely related. In this paper we explore the task of OoD segmentation, which has been studied less than its classification counterpart and presents additional challenges. Segmentation is a dense prediction task for which the model's outcome for each pixel depends on its surroundings. The receptive field and the reliance on context play a role for distinguishing different classes and, correspondingly, for spotting OoD entities. We introduce MOoSe, an efficient strategy to leverage the various levels of context represented within semantic segmentation models and show that even a simple aggregation of multi-scale representations has consistently positive effects on OoD detection and uncertainty estimation.
Code (1)
Tasks
Diversityimage-classificationImage ClassificationOut-of-Distribution DetectionOut of Distribution (OOD) DetectionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Online Learning for Adaptive Probing and Scheduling in Dense WLANs
Existing solutions to network scheduling typically assume that the instantaneous link rates are completely known before a scheduling decision is made or consider a bandit setting where the accurate link quality is discov…
SchedulingOn-Orbit Real-Time Wildfire Detection Under On-Board Constraints
We present a deployed system for on-orbit wildfire detection aboard a nine-satellite commercial thermal infrared constellation, operating under demanding joint constraints: sub-megabyte model footprint, sub-150 ms per-ba…
Representation LearningJoint AP Probing and Scheduling: A Contextual Bandit Approach
We consider a set of APs with unknown data rates that cooperatively serve a mobile client. The data rate of each link is i.i.d. sampled from a distribution that is unknown a priori. In contrast to traditional link schedu…
Decision MakingSchedulingSequential Decision MakingSpying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words
Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are…
Word EmbeddingsUsing Distributional Principles for the Semantic Study of Contextual Language Models
Many studies were recently done for investigating the properties of contextual language models but surprisingly, only a few of them consider the properties of these models in terms of semantic similarity. In this article…
Semantic SimilaritySemantic Textual Similarity