AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Sequence Modeling with Multiresolution Convolutional Memory

Jiaxin Shi, Ke Alexander Wang, Emily Fox

ICML 2023 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 1 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
train filters end-to-end instead of fixed wavelet filters (ablation)MultiresConv · ListOps (smaller model)accuracy (%): 50.15 -> 52.08Improved
Xavier initialization instead of wavelet initialization of filters (ablation)MultiresConv trainable filters · ListOps (smaller model)accuracy (%): 52.08 -> 51.70No clear effect
increase MultiresConv depth from 7 to 11 (ablation)MultiresNet with Xavier init · ListOps (smaller model)accuracy (%): 51.70 -> 61.07Improved
increase filter size from 2 to 4 (ablation)MultiresNet with wavelet init · ListOps (smaller model)accuracy (%): 52.08 -> 59.23Improved
uniform-over-time memory instead of resolution fading TreeSelect (ablation)MultiresNet memory mechanism · ListOps (smaller model)accuracy (%): 51.70 -> 51.58No clear effect
MultiresNet architecture (learned filters, tree-structured dilated convs with memory) vs. prior modelssequential CIFAR-10 classification · sCIFARaccuracy (%): 93.15 vs 92.02 (Liquid-S4, next best)Improved
MultiresNet on PTB-XL ECG classificationPTB-XL · PTB-XL All/RhythmAUROC: All 0.938 (tied with S4); Rhythm 0.975 vs S4 0.977Mixed
MultiresNet without 2D bias on CIFAR-10 autoregressive density estimationautoregressive CIFAR-10 · CIFAR-10 bpdbits per dimension: 2.84 vs Sparse Transformer 2.80 (better than S4 2.85 and PixelSNAIL 2.85)Mixed

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