AI Paper Atlas

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

Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE

Alireza Nasiri, Tristan Bepler

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 7 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
increase discrete rotations from P4 to P16TARGET-VAE · MNIST(U)rotation correlation: 0.80 -> 0.93Improved
increase discrete rotations from P4 to P16TARGET-VAE · MNIST(U)translation correlation: 0.975, 0.976 -> 0.974, 0.971No clear effect
use TARGET-VAE instead of Spatial-VAETARGET-VAE P8 · MNIST(U)rotation correlation: 0.005 -> 0.859Improved
use TARGET-VAE instead of Spatial-VAETARGET-VAE P8 · MNIST(N)translation correlation: 0.994, 0.993 -> 0.981, 0.981Hurt
increase z_dim from 2 to 32TARGET-VAE P8 · MNIST(N)clustering accuracy (%): 60.1 -> 77.7Improved
increase z_dim from 2 to 32TARGET-VAE P16 · MNIST(U)clustering accuracy (%): 63.4 -> 71.2Improved
increase discrete rotations from P8 to P16 (z_dim=32)TARGET-VAE · MNIST(N)clustering accuracy (%): 77.7 -> 75.2Hurt
replace Spatial-VAE with TARGET-VAE P4 (z_dim=2)TARGET-VAE · MNIST(U)clustering accuracy (%): 28.2 -> 56.6Improved
replace group conv with regular conv, inference only on translation (Variant 1) (ablation)TARGET-VAE P4 · MNIST(U)clustering accuracy (%): 56.6 -> 33.8Hurt
use group conv layers without rotation inference (Variant 2) (ablation)Variant 1 · MNIST(U)clustering accuracy (%): 33.8% -> 37.1%Improved
remove theta_offset from posterior on theta (Variant 3) (ablation)TARGET-VAE P4 · MNIST(U)rotation correlation: 0.80 -> 0.008Hurt
remove theta_offset from posterior on theta (Variant 3) (ablation)TARGET-VAE P4 · MNIST(U)clustering accuracy (%): 56.6% -> 36.6%Hurt

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