AI Paper Atlas

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

Unsupervised learning of object frames by dense equivariant image labelling

James Thewlis, Hakan Bilen, Andrea Vedaldi

NeurIPS 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 12 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 robust distance loss with γ = 0.5 instead of Llog (ablation)SIMPLE dense labelling network · MAFLnearest landmark error: 75.02 % -> 13.29 %Improved
use DILATIONS instead of SIMPLE (ablation)Ldist, γ = 0.5 dense labelling network · MAFLnearest landmark error: 13.29 % -> 10.53 %Improved
use DILATIONS instead of SIMPLE (ablation)Ldist, γ = 0.5 dense labelling network · MAFLregression landmark error: 7.18 % -> 5.87 %Improved
use DILATIONS instead of SIMPLE (ablation)Llog dense labelling network · MAFLnearest landmark error: 75.02 % -> 11.05 %Improved
use DILATIONS instead of SIMPLE (ablation)Llog dense labelling network · MAFLregression landmark error: — -> 5.83 %Improved
use the distance loss with γ = 0.5 instead of the negative log-likelihood loss (ablation)DILATIONS dense labelling network · MAFLregression landmark error: 5.83 % -> 5.87 %No clear effect
use the distance loss with γ = 0.5 instead of Llog (ablation)SIMPLE dense labelling network · Roboarmcapsule center prediction error (% image width): 0.97 % -> 1.14 %Hurt
use label dimension 2 instead of 3 (ablation)SIMPLE Ldist, γ = 0.5 · Roboarmcapsule center prediction error (% image width): 1.14 % -> 1.29 %Hurt
use label dimension 5 instead of 3 (ablation)SIMPLE Ldist, γ = 0.5 · Roboarmcapsule center prediction error (% image width): 1.14 % -> 1.16 %No clear effect
use label dimension 20 instead of 3 (ablation)SIMPLE Ldist, γ = 0.5 · Roboarmcapsule center prediction error (% image width): 1.14 % -> 1.28 %Hurt
increase the receptive field by switching from SIMPLE to DILATIONS (ablation)dense face labelling · Human facesleft/right eye disambiguationImproved
use Llog rather than the distance loss (ablation)SIMPLE dense labelling network · Human faceslandmark consistencyHurt

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