AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Sketching based Representations for Robust Image Classification with Provable Guarantees

Nishanth Dikkala, Sankeerth Rao Karingula, Raghu Meka, Jelani Nelson, Rina Panigrahy, Xin Wang

NeurIPS 2022 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 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
use LSH sketch projection instead of raw image projectionLSH sketch · Synthetic ellipse imagesaverage absolute discrete derivative: 12.22 -> 2.29Improved
use LSH sketch projection instead of raw image projectionLSH sketch · Synthetic hyperbola imagesaverage absolute discrete derivative: 18.31 -> 2.63Improved
use LSH sketch projection instead of raw image projectionLSH sketch · Synthetic rectangle imagesaverage absolute discrete derivative: 10.25 -> 1.32Improved
train 2-layer NN on LSH sketches of imagesLSH sketch · Fashion-MNIST (10% subsample)test accuracy: 100% train vs 79.3% testMixed

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