AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Generalized Parametric Contrastive Learning

Jiequan Cui, Zhisheng Zhong, Zhuotao Tian, Shu Liu, Bei Yu, Jiaya Jia

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive learning for imbalanced data · 82 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 GPaCo instead of PaCo (no momentum encoder, learnable-center generalization)PaCo · ImageNet-LT (ResNet-50)top-1 accuracy: 57.0 -> 58.5Improved
use GPaCo instead of PaCoPaCo · iNaturalist 2018 (ResNet-50)top-1 accuracy: 73.2 -> 75.4Improved
use GPaCo instead of PaCoPaCo · full ImageNet (ResNet-50)top-1 accuracy: 79.3 -> 79.7Improved
use GPaCo instead of SupconSupcon · full CIFAR-100top-1 accuracy: 76.5 -> 80.3Improved
add GPaCo as auxiliary loss for semantic segmentationUperNet Swin-T · ADE20KmIoU (s.s.): 44.5 -> 45.4Improved
use GPaCo fine-tuning instead of MAEMAE ViT-B · full ImageNettop-1 accuracy: 82.5 -> 84.0Improved
use two views instead of a single view (ablation)GPaCo ViT-B · full ImageNettop-1 accuracy: 82.5 -> 84.0Improved
use random resized crop scale (0.2,1) instead of (0.08,1) (ablation)PaCo · ImageNet-LT (ResNet-50)top-1 accuracy: 55.0 -> 52.2Hurt
use RandAug for view 1 instead of SimAug (ablation)PaCo · ImageNet-LT (ResNet-50)top-1 accuracy: 55.0 -> 57.0Improved
use RandAug for both views instead of one (ablation)PaCo · ImageNet-LT (ResNet-50)top-1 accuracy: 57.0 -> 56.5Hurt
use stronger augmentation (RandAugStack) for view 2 instead of SimAug (ablation)GPaCo · ImageNet-LT (ResNet-50)top-1 accuracy: 57.9 -> 58.5Improved
use PaCo instead of multi-task CE+re-weighting (ablation)CE · ImageNet-LT (ResNet-50)top-1 accuracy: 49.0 -> 51.0Improved

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