AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Unifying Visual Contrastive Learning for Object Recognition from a Graph Perspective

Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Chenyu Wang, Wanli Ouyang

ECCV 2022 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis · 4 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 non-linear ReLU(BN) activation instead of identity in the predictor (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 68.5 -> 69.3Improved
make W' trainable under ReLU(BN) activation (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 67.5 -> 69.3Improved
use Softmax instead of ReLU(BN) activation (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 69.3 -> 69.4No clear effect
add neighborhood aggregation on the target branch (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 69.3 -> 71.4Improved
add self-loop term on the target branch (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 71.4 -> 71.8Improved
add aggregation and self-loop terms to online branch as well (ablation)GCN predictor · ImageNet-1K linear eval (200 epochs, predictor ablation)top-1 accuracy: 71.8 -> 71.9No clear effect
add node feature masking with drop probability 0.3 (ablation)UniVCL · ImageNet-1K linear eval (200 epochs, graph augmentation)top-1 accuracy: 71.9 -> 72.1Improved
add edge modification with drop probability 0.3 (ablation)UniVCL · ImageNet-1K linear eval (200 epochs, graph augmentation)top-1 accuracy: 71.9 -> 72.2Improved
raise graph masking drop probability to 0.7 (ablation)UniVCL · ImageNet-1K linear eval (200 epochs, graph augmentation)top-1 accuracy: 71.9 -> 70.1Hurt
add PPR diffusion on the target branch (ablation)UniVCL · ImageNet-1K linear eval (200 epochs, graph augmentation) with diffusiontop-1 accuracy: 72.2 -> 72.8Improved
add heat diffusion online and PPR diffusion target (ablation)UniVCL · ImageNet-1K linear eval (200 epochs, graph augmentation) with diffusiontop-1 accuracy: 72.2 -> 72.9Improved
add neighborhood aggregation graph predictor vs MOCOv2 identity predictor (200 epochs)UniVCL · ImageNet-1K linear eval (200 epochs)top-1 accuracy: 68.6 -> 72.9Improved

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