AI Paper Atlas

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

Improving Contrastive Learning by Visualizing Feature Transformation

Rui Zhu, Bingchen Zhao, Jingen Liu, Zhenglong Sun, Chang Wen Chen

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 80 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 positive extrapolation (alpha_ex=2.0) (ablation)MoCoV1 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 71.1 -> 72.8Improved
replace positive extrapolation with positive interpolation (alpha_ex=2) (ablation)MoCoV1 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 71.1 -> 67.4Hurt
add negative interpolation (alpha_in=1.6) (ablation)MoCoV1 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 71.1 -> 74.6Improved
combine positive extrapolation and negative interpolation (ablation)MoCoV1 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 71.10 -> 76.87Improved
combine positive extrapolation and negative interpolation (ablation)MoCoV2 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 75.61 -> 78.33Improved
use dimension-level mixing instead of feature-level mixing (ablation)MoCoV1 + both FT · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 76.87 -> 77.21Improved
double the queue by adding interpolated negatives to original queue (2K) (ablation)MoCoV1 + neg FT · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 74.64 -> 74.73No clear effect
double original queue size without feature transformation (K to 2K) (ablation)MoCoV1 · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 71.10 -> 71.40No clear effect
start feature transformation at epoch 0 instead of never (ResNet-50) (ablation)MoCoV1 + both FT · ImageNet-100 (ResNet-50, FT start epoch)top-1 accuracy: 71.1 -> 76.9Improved
start feature transformation at epoch 80 instead of never (ResNet-50) (ablation)MoCoV1 + both FT · ImageNet-100 (ResNet-50, FT start epoch)top-1 accuracy: 71.1 -> 72.2Improved
train 500 epochs with FT instead of 200 (ablation)MoCoV2 + both FT · ImageNet-100 (200 epoch, linear readout)top-1 accuracy: 80.7 -> 81.5Mixed
add positive extrapolation (ablation)BYOL · ImageNet-1K (100 epoch)top-1 accuracy: 66.5 -> 67.2Improved

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