AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Neural Metamorphosis

Xingyi Yang, Xinchao Wang

ECCV 2024 · Probabilistic and scientific modeling › Dynamical systems · approach: Synaptic plasticity learning rules · 6 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
replace layer-wise TSP permutation (Greedy) with mSHP weight permutation (ablation)NeuMeta · CIFAR10accuracy: 91.67 -> 91.87Improved
replace layer-wise TSP 2-Opt permutation with mSHP (ablation)NeuMeta · CIFAR10accuracy: 91.31 -> 91.87Improved
add mSHP weight permutation versus no permutation (ablation)NeuMeta · CIFAR10accuracy: 91.62 -> 91.87Improved
add mSHP weight permutation versus no permutation (ablation)NeuMeta · CIFAR10total variation: 58141.80 -> 45576.02Improved
add residual connections to the INR (ablation)NeuMeta INR · CIFAR10accuracy: 90.18 -> 91.87Improved
use block-based INR with separate MLPs per parameter (ablation)NeuMeta INR · CIFAR10accuracy: 91.74 -> 91.87Improved
add EMA with gamma 0.995 during INR training (ablation)NeuMeta INR · CIFAR10accuracy: 91.32 -> 91.87Improved
increase EMA gamma to 0.999 from 0.995 (ablation)NeuMeta INR · CIFAR10accuracy: 91.87 -> 91.42Hurt
increase INR depth to 12 layers with 256 hidden units (ablation)NeuMeta INR · CIFAR10accuracy: 91.87 -> 91.27Hurt
use 8 layers, 512 hidden units, 32 frequencies versus 5 layers, 256 hidden, 32 frequencies (ablation)NeuMeta INR · CIFAR10accuracy: 91.23 -> 91.87Improved
extend morphing to network depth, evaluating unseen depths beyond training range 1-3NeuMeta · MNIST depth morphingaccuracy: about 99% in-range; 56.97% at L1=L2=7Mixed

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