AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Meta-Learning Sparse Implicit Neural Representations

Jaeho Lee, Jihoon Tack, Namhoon Lee, Jinwoo Shin

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 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 Meta-SparseINR instead of Dense-Narrow at a similar parameter countSIREN · CelebAPSNR: \approx 20.52 -> \approx 26.73Improved
Use Meta-SparseINR instead of random pruningFFN · CelebA, 41.0% surviving parametersPSNR: 21.54\stdv{0.17} -> 23.91\stdv{0.23}Improved
Use Meta-SparseINR instead of Dense-NarrowFFN · CelebA, approximately 41% surviving parametersPSNR: 19.39\stdv{2.37} -> 23.91\stdv{0.23}Improved
Use Meta-SparseINR instead of random pruningFFN · CelebA, 10.74% surviving parametersPSNR: 15.88\stdv{0.23} -> 18.41\stdv{0.38}Improved
Use Meta-SparseINR instead of Dense-NarrowFFN · CelebA, approximately 11–13% surviving parametersPSNR: 14.95\stdv{1.76} -> 18.41\stdv{0.38}Improved
Replace magnitude pruning with random pruning (ablation)Meta-SparseINR · CelebA, FFN with 80.0% surviving parametersPSNR: 24.88\stdv{1.62} vs. 25.15\stdv{0.20}No clear effect
Replace meta-learned weights with standard random initialization (ablation)Dense-Narrow · CelebA, FFN with 80.8% surviving-parameter counterpartPSNR: 22.27\stdv{2.55} -> 15.82\stdv{0.04}Hurt
Use winning-ticket pruning at initialization instead of trained initial weights (ablation)Sparse INR · 512×512 natural imagesPSNRNo clear effect
Use Reptile instead of MAML for meta-learning (ablation)Meta-SparseINR · CelebAPSNR: ≈ 2Hurt
Use Meta-SparseINR instead of JPEG compressionImage compression · Image compression comparisonbits per pixelHurt

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