AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Latent Space Translation via Semantic Alignment

Valentino Maiorca, Luca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, Emanuele Rodolà

NeurIPS 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot reasoning · 2 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
translate with ortho instead of using absolute encodingslatent translation · CIFAR-10 stitchingaccuracy: 0.16 ± 0.22 -> 0.93 ± 0.04Improved
translate with ortho instead of relative representationslatent translation · CIFAR-100 fine stitchingaccuracy: 0.30 ± 0.24 -> 0.71 ± 0.09Improved
translate with ortho instead of relative representationslatent translation · TRECaccuracy: 0.36 ± 0.13 -> 0.79 ± 0.11Improved
translate with ortho instead of relative representationslatent translation · IMDBaccuracy: 0.51 ± 0.02 -> 0.59 ± 0.04Improved
replace unconstrained linear with l-ortho (orthogonalized linear) (ablation)latent translation · MNIST stitchingaccuracy: 0.89 ± 0.08 -> 0.81 ± 0.11Hurt
replace unconstrained linear with l-ortho (ablation)latent translation · CIFAR-10 stitchingaccuracy: 0.88 ± 0.11 -> 0.90 ± 0.09Improved
replace linear with l-ortho (ablation)latent translation · TRECaccuracy: 0.74 ± 0.25 -> 0.57 ± 0.25Hurt
replace ortho with affine (broader class) (ablation)latent translation · TRECaccuracy: 0.79 ± 0.11 -> 0.82 ± 0.12Improved
replace ortho with affine (ablation)latent translation · CIFAR-10accuracy: 0.93 ± 0.04 -> 0.92 ± 0.05No clear effect
use L2 normalization instead of standard scaling (ablation)linear translation · MNIST stitchingaccuracy: 0.89 ± 0.08 -> 0.61 ± 0.23Hurt
use L2 normalization instead of standard scaling (ablation)linear translation · TRECaccuracy: 0.74 ± 0.25 -> 0.44 ± 0.20Hurt
use L2 normalization instead of standard scaling (ablation)ortho translation · TRECaccuracy: 0.79 ± 0.11 -> 0.77 ± 0.12No clear effect

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