AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Functional Indirection Neural Estimator for Better Out-of-distribution Generalization

Kha Pham, Hung Le, Man Ngo, Truyen Tran

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 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 FINE functional memory instead of data-space baselines (Transformer)FINE-NICE · Omniglot Rotationtest accuracy (%): 64.8 -> 77.6Improved
Use MLP backbone instead of NICE backbone for non-invertible reflection (ablation)FINE · Omniglot Reflectiontest accuracy (%): 57.7 -> 95.1Improved
Use MLP backbone instead of NICE backbone for reflection (ablation)FINE · CIFAR100 Reflectiontest accuracy (%): 51.1 -> 80.6Improved
Add analogy-making and indirection memory to hypernetwork-style weight generationFINE-MLP vs HyperNet · Omniglot multi affinetest accuracy (%): 54.0 -> 72.0Improved
Increase training set from 1000 to 10000 points (ablation)FINE · Omniglot multi-affinetest accuracy (%): 64.4 -> 81.1Improved
Increase training set from 10,000 to 100,000 points (ablation)FINE · Omniglot multi-affinetest accuracy (%): 81.1 -> 85.3Improved
Increase number of memories (from 0 limit case) and NICE backbone layers (ablation)FINE · Omniglot multi-affinetest accuracy (%)Improved
Replace Group CNN (p4-CNN) encoder with MLP encoder (ablation)FINE-NICE · CIFAR100 multi-affinetest accuracy (%): 81.6 -> 70.0Hurt
Test on unseen translation rule vs ESBN on CIFAR100FINE · Extreme OOD CIFAR100 Translationtest accuracy (%): 16.4 -> 62Improved
Train on CIFAR100, test on Omniglot translation (unseen dataset and rule)FINE · Extreme OOD Translationtest accuracy (%): 30 -> 22.1Hurt
FINE-NICE vs ESBN on CIFAR100 SwapFINE-NICE · CIFAR100 Swaptest accuracy (%): 50.5 -> 51.6No clear effect
FINE vs Transformer on Omniglot Black-whiteFINE-NICE · Omniglot B&Wtest accuracy (%): 97.6 -> 98.4No 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