AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Towards Open Set Deep Networks

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 1,699 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add activation-vector Meta-Recognition and an unknown class to SoftMaxBVLC AlexNet · ImageNet 2012 val + open-set and fooling imagesaccuracy versus SoftMax with optimal threshold: 4.3%Helped
Add activation-vector Meta-Recognition and an unknown class to SoftMaxBVLC AlexNet · ImageNet 2012 val + open-set and fooling imagesaccuracy versus base deep network: 12.3%Helped
Use OpenMax rather than thresholding SoftMax probabilitiesBVLC AlexNet · ImageNet 2012 val + open-set and fooling imagesF-measure: 3450 more imagesHelped
Use OpenMax rather than the base deep networkBVLC AlexNet · ImageNet 2012 val + open-set and fooling imagesF-measure: 9847 more imagesHelped
Use a weighted normalized Euclidean and cosine distance rather than pure Euclidean or other distance measures (ablation)OpenMax · ImageNet 2012open-set recognition performanceNo clear effect
Add uncertainty thresholding alongside the activation-vector unknown estimate (ablation)OpenMax · ImageNet 2012 val + open-set and fooling imagesopen-set recognitionHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy