AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation

Guhnoo Yun, Juhan Yoo, Kijung Kim, Jeongho Lee, Dong Hwan Kim

ICCV 2023 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 28 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 SPAM frequency-balancing token mixer instead of FocalNet-T mixerSPANet-S · ImageNet-1K valtop-1 accuracy: 82.3 -> 83.1Improved
use SPANet backbone instead of LITv2 for detectionRetinaNet · COCO val2017AP: 43.7 (LITv2-S) vs 43.3 (SPANet-S)Mixed
use SPANet-S backbone instead of Swin-T/LITv2-SSemantic FPN · ADE20KmIoU: 44.3 -> 45.4 (vs LITv2-S)Improved
add spectral pooling filter (SPF) to spectral pooling gate (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.2 -> 82.8Improved
aggregate SPG contexts by addition rather than Hadamard product (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.7 -> 82.8Improved
use low-pass radius [2,2,1,1] rather than [1,1,1,1] or [4,4,1,1] (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: -0.1 and -0.2 for the alternativesImproved
increase separable kernel size from 3 to 7 (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.8 -> 83.1Improved
increase separable kernel size from 3 to 5 (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.8 -> 82.7Hurt
use ResScale for branch output scaling (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.7 (none) -> 82.8Improved
use LayerScale instead of ResScale (ablation)SPANet-S · ImageNet-1K valtop-1 accuracy: 82.8 -> 82.6Hurt

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