AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution

Jaeill Kim, Suhyun Kang, Duhun Hwang, Jungwook Shin, Wonjong Rhee

CVPR 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 14 citations (OpenAlex)

Read the paper

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 VNE− to ERM (ablation)ERM · PACS, VLCS, OfficeHome, TerraIncognitaAvg. accuracy: 1.7; 1.4; 1.0; 5.2Improved
Add VNE− to SWAD (ablation)SWAD · PACS, VLCS, OfficeHome, TerraIncognitaAvg. accuracy: 0.1; 0.3; 0.9; 0.8Improved
Add VNE+ to ERM (ablation)ERM · PACS, VLCS, OfficeHome, TerraIncognitaAvg. accuracy: -2.9; 0.1; -0.5; -1.1Mixed
Add VNE+ to SWAD (ablation)SWAD · PACS, VLCS, OfficeHome, TerraIncognitaAvg. accuracy: -2.1; -0.2; 0.3; -4.8Mixed
Add VNE+ to MAML (ablation)MAML · mini-ImageNet, 5-way 1-shot and 5-shotAvg. accuracy (%): +1.28; +1.83Improved
Add VNE+ to ANIL, BOIL, Baseline, Baseline++, and ProtoNet (ablation)Meta-learning algorithms · mini-ImageNet, 5-way 1-shot and 5-shotAvg. accuracy (%): 1.50; 1.34; 1.62; 2.22; 3.65; 1.92; 1.06; 3.32; 0.82; 2.48Improved
Add VNE− to meta-learning algorithms (ablation)MAML, ANIL, BOIL, Baseline, Baseline++, ProtoNet · mini-ImageNet, 5-way 1-shot and 5-shotAvg. accuracy (%): -2.02; -2.02; -1.30; -1.36; -1.19; -1.12; -14.98; -14.50; -18.43; -5.45; -2.10Hurt
Use I-VNE+Self-supervised learning · CIFAR-10Top-1: 93.9 -> 94.3Improved
Use I-VNE+Self-supervised learning · ImageNet-100Top-1: 84.5 -> 86.3Improved
Use I-VNE+ pretrainingResNet-50 transfer learning · COCO detection and instance segmentationAP / AP mask: 39.3 -> 41.2 AP; 34.4 -> 35.7 AP maskImproved
Add VNE+ to GAN training (ablation)DCGAN, PD-GAN, LOGAN, WGAN-GP, SAGAN, SNGAN, BigGAN · CIFAR-10FID: 42.55 -> 35.44; 28.02 -> 23.54; 18.88 -> 17.17; 24.62 -> 23.31; 9.55 -> 8.91; 9.97 -> 9.41; 5.34 -> 5.18Improved
Regularize with Frobenius norm rather than VNE (ablation)ResNet-18 supervised training · CIFAR-10, STL-10, CIFAR-100Dead units: 447; 365; 325Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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