AI Paper Atlas

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

Your Dissimilarities Define You: Complementary Learning Exploiting Class Diversities

Dimitrios Katsikas, Nikolaos Passalis, Anastasios Tefas

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

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 CDLuni to cross-entropyResNet-50 · ImageNet valtop-1 error (%): 23.72 -> 22.61Improved
add CDLuni to cross-entropyResNet-101 · ImageNet valtop-1 error (%): 22.78 -> 21.46Improved
add CDLuni to MaxSupResNet-50 · ImageNet valtop-1 error (%): 22.88 -> 22.35Improved
add CDLuni to MaxSupResNet-101 · ImageNet valtop-1 error (%): 21.39 -> 21.52Hurt
add CDLself to OLSResNet-50 · ImageNet valtop-1 error (%): 22.51 -> 22.31Improved
add CDLuni to CE on DeiT-Small without MixUp/CutMixDeiT-Small · ImageNet valtop-1 error (%): 25.61 -> 23.12Improved
add CDLuni to all baseline lossesResNet-18 and DenseNet-121 · CIFAR-100, TinyImageNeterror rate (%): 24.98 -> 23.92 (CE, RN18 CIFAR-100)Improved
add CDLuni to MaxSupDenseNet-121 · TinyImageNeterror rate (%): 36.32 -> 35.04Improved
use CE + CDLself instead of other self-KD methodsResNet-34 · CIFAR-100 (self-KD)error rate (%): 22.62 -> 22.44 (vs OLS)Improved
use CE + CDLself instead of OLS on MobileNetV2 TinyImageNetMobileNetV2 · TinyImageNet (self-KD)error rate (%): 39.11 -> 38.88Improved
add CDLself to CE for open-set recognitionResNet-18 · Open-set CIFAR-100OSCR: 64.49 -> 66.82Improved
add confusing samples with uniform target to CDL (ablation)CE + CDLself · Open-set CIFAR-100OSCR: 66.82 -> 68.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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