AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Co-Domain Symmetry for Complex-Valued Deep Learning

Utkarsh Singhal, Yifei Xing, Stella X. Yu

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 15 citations (OpenAlex)

Check 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 co-domain symmetric complex layers instead of DCN layersCIFAR10 and CIFAR100 classifiers · CIFAR10/CIFAR100, RGB, LAB, and Sliding encodingsaccuracy: 65.17 -> 69.23; 58.64 -> 67.17; 63.83 -> 69.19; 32.52 -> 41.83; 27.36 -> 39.55; 28.87 -> 42.08Improved
Use co-domain symmetric complex layers instead of DCN layersSVHN classifier, Type-I model · SVHN RGB and LABaccuracy: 85.26 -> 89.39; 84.43 -> 88.86Improved
Use co-domain symmetric complex layers instead of DCN layersSVHN classifier, Type-E model · SVHN RGB and LABaccuracy: 85.26 -> 77.19; 84.43 -> 74.21Hurt
Use co-domain symmetric complex layers instead of the strongest real-valued or DCN baselineCIFARnet classifier · SVHN Slidingaccuracy: 87.44 -> 90.25Improved
Use co-domain symmetric complex layers instead of the strongest real-valued or DCN baselineCIFARnet classifier · SVHN Slidingaccuracy: 87.44 -> 88.39Improved
Use co-domain symmetric complex layers instead of SurRealMSTAR classifier · MSTAR 5% training dataaccuracy: 61.1 -> 69.5Improved
Use co-domain symmetric complex layers instead of SurRealMSTAR classifier · MSTAR 10% training dataaccuracy: 68.0 -> 78.3Improved
Use co-domain symmetric complex layers instead of SurRealMSTAR classifier · MSTAR 50% training dataaccuracy: 90.3 -> 91.3Improved
Use co-domain symmetric complex layers instead of SurRealMSTAR classifier · MSTAR 90% training dataaccuracy: 95.6 -> 95.2Hurt
Use co-domain symmetric complex layers instead of SurRealMSTAR classifier · MSTAR 100% training dataaccuracy: 94.9 -> 96.1Improved
Use co-domain symmetric complex layers instead of DCN at matched model sizeCIFAR10 LAB classifier · CIFAR10 LABaccuracy: 92.8 -> 93.7Improved
Use the Type-E composition rather than Type-I (ablation)Co-domain symmetric CIFAR classifiers · CIFAR100 RGB/LAB/Sliding versus SVHN RGB/LAB/Slidingaccuracy: 36.92 -> 41.83; 37.81 -> 39.55; 38.51 -> 42.08; 89.39 -> 77.19; 88.86 -> 74.21; 90.25 -> 88.39Mixed

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