AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

James Thewlis, Samuel Albanie, Hakan Bilen, Andrea Vedaldi

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 52 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
add DVE to 64D embedding (ablation)equivariance baseline SmallNet · MAFL different-identity matchingpixel error: 5.68 -> 2.77Improved
add DVE to 16D embedding (ablation)equivariance baseline SmallNet · MAFL different-identity matchingpixel error: 5.65 -> 2.79Improved
add DVE to 3D embedding (ablation)equivariance baseline SmallNet · MAFL different-identity matchingpixel error: 2.89 -> 3.03Hurt
add DVE to 64D embedding (ablation)equivariance baseline SmallNet · MAFL same-identity matchingpixel error: 1.25 -> 1.28No clear effect
increase embedding dimension from 3 to 64 without DVE (ablation)equivariance baseline · MAFL different-identity matchingpixel error: 2.89 -> 5.68Hurt
increase embedding dimension from 3 to 64 without DVE (ablation)equivariance baseline · MAFL same-identity matchingpixel error: 1.33 -> 1.25Improved
add DVE to 20D embedding (ablation)equivariance baseline · Roboarm matchingmatching error: 10.34 -> 1.25Improved
add DVE to 3D embedding (ablation)equivariance baseline · Roboarm matchingmatching error: 1.42 -> 1.41No clear effect
add transformations (flow-based warps) to DVE, 20D (ablation)DVE · Roboarm matchingmatching error: 1.42 -> 1.25Improved
add unsupervised finetuning on AFLW to Hourglass 64D (ablation)DVE Hourglass · AFLW_M landmark regressionerror: 8.15 -> 7.53Improved
add unsupervised finetuning on AFLW to SmallNet 3D (ablation)DVE SmallNet · AFLW_M landmark regressionerror: 11.82 -> 11.12Improved
add unsupervised finetuning to Hourglass 64D (ablation)DVE Hourglass · 300W landmark regressionerror: 4.65 -> 4.65No clear effect

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