AI Paper Atlas

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

An end-to-end approach for the verification problem: learning the right distance

Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R Devon Hjelm, Tiago Falk

ICML 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 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
use the learned pairwise score instead of cosine scoringProposed verification model · Cifar-10EER: 3.56% -> 3.43%Improved
use the learned pairwise score instead of cosine scoringProposed verification model · Mini-ImageNet (Validation)EER: 30.66% -> 28.64%Improved
use the learned pairwise score instead of cosine scoringProposed verification model · Mini-ImageNet (Test)EER: 32.97% -> 29.26%Improved
add cosine score fusion to E2E scoreProposed verification model · Mini-ImageNet (Test)EER: 29.26% -> 29.32%No clear effect
add auxiliary cross-entropy loss (ablation)Proposed speaker verification model · VoxCeleb1 Test setEER: 3.44% -> 2.51%Improved
add auxiliary cross-entropy loss (ablation)Proposed speaker verification model · VoxCeleb1-EEER: 3.70% -> 2.57%Improved
add auxiliary cross-entropy loss (ablation)Proposed speaker verification model · VoxCeleb1-HEER: 7.76% -> 4.73%Improved
use learned E2E scoring instead of PLDAProposed speaker verification model · VoxCeleb1 Test setEER: 3.75% -> 2.51%Improved
fine-tune with multilingual data including target-domain speechProposed speaker verification model · NIST SRE 2018 CTSEER: 13.61% -> 8.43%Improved
add auxiliary loss (ablation)E2E image clustering model · CUBNMI: 58.5% -> 60.5%Improved
add auxiliary loss (ablation)E2E image clustering model · CARSNMI: 60.4% -> 59.9%Hurt
add auxiliary loss (ablation)E2E image clustering model · SOPNMI: 88.1% -> 89.2%Improved

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