AI Paper Atlas

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

Transferability and Hardness of Supervised Classification Tasks

Anh T. Tran, Cuong V. Nguyen, Tal Hassner

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 159 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
transfer a face recognition network (lSVM on embeddings) instead of training a dedicated network, for highly transferable attributesResNet101 face recognition embedding · CelebA Maleaccuracy: 0.985 -> 0.992Improved
transfer a face recognition network instead of dedicated training, for weakly transferable attributesResNet101 face recognition embedding · CelebA Mouth Openaccuracy: 0.943 -> 0.901Hurt
transfer a face recognition network instead of dedicated training, averaged over 40 attributesResNet101 face recognition embedding · CelebA (average over 40 attributes)accuracy: 0.911 -> 0.902Hurt
transfer instead of dedicated training for attributes young and big noseface recognition transfer · CelebAaccuracyImproved
transfer from recognition vs best published result DMTL 2018face recognition transfer + lSVM · CelebAaccuracy: 0.926 -> 0.902Hurt
transfer from face recognition with far less training dataface recognition transfer + lSVM · CelebA Male and Double ChinaccuracyImproved
higher conditional entropy between source and target labelsCE estimate · CelebA, AwA2, CUB attribute taskstarget test errorHurt
higher conditional entropy of labels (estimated task hardness)CE H(Z|C) · CelebA, AwA2, CUBtest error of dedicated networks: correlation significant with p<0.001Hurt
higher estimated hardness on multi-class CelebA aggregateshardness estimate · CelebA multi-classaccuracy: Straight/Wavy/Other hardness 1.040, accuracy 0.713; Goatee/Beard/None hardness 0.557, accuracy 0.937Hurt
lower transferability (larger CE) from identity to attributeface recognition transfer · CelebAtransferred minus dedicated accuracy: Male 0.992 vs 0.985; Smiling 0.909 vs 0.933Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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