AI Paper Atlas

Research map / Detection and segmentation / CNN features

Hierarchical Spherical CNNs With Lifting-Based Adaptive Wavelets for Pooling and Unpooling

Mingxing Xu, Chenglin Li, Wenrui Dai, Siheng Chen, Junni Zou, Pascal Frossard, Hongkai Xiong

TPAMI 2025 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 4 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 downsampling pooling with learned lifting-based pooling and unpooling (ablation)UGSCNN-style backbone · SCIFAR10 reconstruction (test)MSE: 0.0030 -> 0.0017Improved
add lifting-based pooling with padding unpooling (ablation)HS-CNN · SCIFAR10 reconstruction (test)MSE: 0.0030 -> 0.0025Improved
add lifting-based unpooling (inverse wavelet) on top of lifting pooling (ablation)LiftHS-CNN* · SCIFAR10 reconstruction (test)MSE: 0.0025 -> 0.0017Improved
use learned adaptive wavelets instead of handcrafted wavelets (ablation)LiftHS-CNN · SCIFAR10 reconstruction (test)MSE: 0.0021 -> 0.0017Improved
use lifting pooling instead of mean pooling (ablation)UGSCNN-style backbone · SMNISTaccuracy (%): 99.55 -> 99.60Improved
use lifting pooling instead of downsampling (ablation)UGSCNN-style backbone · SModelNet40accuracy (%): 89.26 -> 91.37Improved
use learned instead of handcrafted wavelets (ablation)LiftHS-CNN · SModelNet40accuracy (%): 90.96 -> 91.37Improved
use mean or max pooling instead of downsampling (ablation)UGSCNN-style backbone · SModelNet40accuracy (%): 89.26 -> 90.76Improved
use lifting pooling and unpooling instead of downsampling (ablation)UGSCNN-style backbone · Stanford 2D3DS segmentationmIoU: 0.3789 -> 0.4534Improved
use learned instead of handcrafted wavelets (ablation)LiftHS-CNN · Stanford 2D3DS segmentationmIoU: 0.4217 -> 0.4534Improved
use lifting-based pooling/unpooling instead of downsampling/paddingUGSCNN · Stanford 2D3DS segmentationmAcc (%): 54.65 -> 61.87Improved
use handcrafted spherical wavelets instead of mean pooling (ablation)UGSCNN-style backbone · SMNISTaccuracy (%): 99.55 -> 99.50No 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