AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Simplicial Embeddings in Self-Supervised Learning and Downstream Classification

Samuel Lavoie, Christos Tsirigotis, Max Schwarzer, Ankit Vani, Michael Noukhovitch, Kenji Kawaguchi, Aaron Courville

ICLR 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 6 citations (OpenAlex)

Read the paper

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 SEM to the SSL representationSeven SSL methods · CIFAR-100 testlinear-probe top-1 accuracy: 65.8± 0.3 -> 69.5± 0.2; 69.3± 0.3 -> 71.0± 0.3; 70.7± 0.2 -> 73.9± 0.2; 70.7± 0.3 -> 73.0± 0.2; 64.6± 0.3 -> 67.7± 0.2; Improved
Add SEM to BYOLBYOL · ImageNet in-distribution, ImageNet-V2, ImageNet-R, ImageNet-C, ImageNet-Alinear-probe top-1 accuracy: 71.9 -> 74.1; 59.2 -> 61.2; 18.8 -> 22.1; 39.5 -> 43.4; 1.65 -> 2.53Improved
Add SEM to BYOLBYOL · ImageNet transfer: Food101, CIFAR-10, CIFAR-100, SUN, Flower (linear probe); DTD (linear probe)linear-probe top-1 accuracy: 74.2 -> 74.7; 91.8 -> 93.5; 74.9 -> 78.6; 60.9 -> 62.1; 88.9 -> 91.5; 72.2 -> 71.9Mixed
Add SEM to BYOLBYOL · ImageNet transfer: Food101, CIFAR-10, CIFAR-100, SUN, DTD, Flower (fine-tuned)fine-tuned top-1 accuracy: 83.1 -> 84.7; 97.2 -> 97.2; 83.6 -> 85.6; 59.1 -> 63.3; 69.2 -> 71.3; 85.4 -> 91.7Mixed
Add SEM to BYOLBYOL · ImageNet with 1% and 10% labelstop-1 accuracy: 51.6 -> 56.7; 67.5 -> 69.9Improved
Increase the number of simplices L while retaining softmax normalization (ablation)BYOL + SEM · CIFAR-100 downstream classificationaccuracyImproved
Remove softmax normalization while increasing L (ablation)BYOL + SEM (BYOL + Embed control) · CIFAR-100 downstream classificationaccuracyNo clear effect
Use hard-discretized Gumbel codes during pretraining instead of SEM (ablation)SSL representation · CIFAR-100 downstream classificationaccuracyHurt
Use vector quantization instead of SEM (ablation)SSL representation · CIFAR-100 downstream classificationaccuracyHurt
Use hard argmax discretization of pretrained SEM features for downstream classification (ablation)BYOL + SEM · CIFAR-100 downstream classificationaccuracyImproved
Use sparse matrix multiplication in the embedder and projector (ablation)BYOL + SEM · CIFAR-100accuracyMixed
Increase simplex dimension V (ablation)BYOL + SEM · CIFAR-100 downstream classificationaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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