AI Paper Atlas

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

Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples

Shashanka Venkataramanan, Ewa Kijak, laurent amsaleg, Yannis Avrithis

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 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
Increase generated mixed examples from n=10 to n=1000 (ablation)MultiMix · CIFAR-100accuracy: 92.19 -> 93.43Improved
Use pairwise mixing (m=2) rather than a full-batch tuple (m=128), keeping n=1000 (ablation)MultiMix · CIFAR-100accuracy: 0.7\% lower accuracyHurt
Increase the interpolation depth toward the deepest layer (ablation)MultiMix · CIFAR-100accuracyImproved
Increase the number n of generated mixed examples (ablation)MultiMix and Dense MultiMix · CIFAR-100accuracyImproved
Add dense MultiMixMultiMix · CIFAR-100-Cclassification error (CE): 33.8 -> 31.7Improved
Replace AugMix with MultiMiximage classification · CIFAR100accuracy: 79.83 -> 81.81Improved
Replace AugMix with MultiMiximage classification · ImageNetaccuracy: 77.68 -> 78.81Improved
Use Input Mixup instead of the baselineCIFAR-100 classification · CIFAR-100ECE: 10.25 -> 18.50Hurt
Use MultiMix instead of the baselineCIFAR-100 classification · CIFAR-100ECE: 10.25 -> 5.63Improved
Use Dense MultiMix instead of the baselineCIFAR-100 classification · CIFAR-100OE: 1.11 -> 0.27Improved
Use MultiMix instead of DAMLOffice-Home open-domain classification · Office-Home Clipartaccuracy: 45.13 -> 46.01Improved
Use Dense MultiMix instead of DAMLOffice-Home open-domain classification · Office-Home Productaccuracy: 61.54 -> 62.28Improved

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