AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning

K L Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 5 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
constrain NN search with neighbors of a previous augmentation (CMSF_self) instead of unconstrained MSFMSF (256K) · ImageNet-1k SSL (200 epochs)linear top-1 accuracy: 72.2 -> 73.0Improved
constrain NN search (CMSF_self) instead of MSFMSF (256K) · ImageNet-1k SSL (200 epochs)20-NN accuracy: 65.1 -> 66.4Improved
add multi-crop inputsCMSF_self · ImageNet-1k SSL (200 epochs)linear top-1 accuracy: 73.0 -> 74.4Improved
add multi-crop inputsCMSF_self · ImageNet-1k SSL (200 epochs)20-NN accuracy: 66.4 -> 66.2Hurt
relax constraint by raising k' from 5 to 80 (ablation)CMSF_self · ImageNet-1k SSL1-NN accuracy: 63.2 -> 61.7Hurt
use SSL CMSF_self instead of MSFMSF · Transfer, mean over 10 datasetsmean transfer accuracy: 76.3 -> 77.4Improved
use top-10 neighbors instead of top-all in supervised CMSF (ablation)CMSF_sup · ImageNet-1k supervisedlinear top-1 accuracy: 75.7 -> 76.4Improved
use top-10 neighbors instead of top-all on coarse-grained labels (ablation)CMSF_sup · ImageNet-coarse train, ImageNet-1k vallinear top-1 accuracy: 67.0 -> 74.2Improved
use CMSF_sup top-10 instead of cross-entropy on coarse labelsXent · ImageNet-coarse train, ImageNet-1k vallinear top-1 accuracy: 61.4 -> 74.2Improved
use top-10 neighbors instead of top-all under label noise (ablation)CMSF_sup · ImageNet-100 noisy labelsaccuracyImproved
use CMSF over cross-entropy for fine-grained transferXent (1000 ep) · Transfer, mean over 10 datasetsmean transfer accuracy: 78.9 -> 80.1Improved
add pseudo-label constraint on unlabeled data (ablation)CMSF_semi-basic · ImageNet semi-supervised (10% labels)top-1 accuracy: 68.6 -> 69.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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