paper-with-me

홈 › Papers

Probing Contextual Diversity for Dense Out-of-Distribution Detection

2022-08-30 · Silvio Galesso, Maria Alejandra Bravo, Mehdi Naouar, Thomas Brox

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.

📄 PDF Abstract BibTeX arXiv:2208.14195

Code (1)

moose-eccv22/moose_eccv2022 공식 구현 pytorch

Tasks

Diversityimage-classificationImage ClassificationOut-of-Distribution DetectionOut of Distribution (OOD) DetectionSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Online Learning for Adaptive Probing and Scheduling in Dense WLANs

2022-12-27 · Tianyi Xu, Ding Zhang, Zizhan Zheng

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…

Scheduling

On-Orbit Real-Time Wildfire Detection Under On-Board Constraints

2026-05-07 · Matthias Rötzer, Veronika Pörtge, Martin Ickerott, Jayendra Praveen Kumar Chorapalli 외 arxiv

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 Learning

Joint AP Probing and Scheduling: A Contextual Bandit Approach

2021-08-06 · Tianyi Xu, Ding Zhang, Parth H. Pathak, Zizhan Zheng

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 Making

Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words

2020-05-04 · ACL 2020 6 · Josef Klafka, Allyson Ettinger

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 Embeddings

Using Distributional Principles for the Semantic Study of Contextual Language Models

2021-11-23 · Olivier Ferret

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