Pith. sign in

REVIEW 2 cited by

Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.05561 v1 pith:SJA5H4AS submitted 2021-12-10 cs.CV

classification cs.CV
keywords attentionglobalinformationmechanismchannelenhanceinteractionsmechanisms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A variety of attention mechanisms have been studied to improve the performance of various computer vision tasks. However, the prior methods overlooked the significance of retaining the information on both channel and spatial aspects to enhance the cross-dimension interactions. Therefore, we propose a global attention mechanism that boosts the performance of deep neural networks by reducing information reduction and magnifying the global interactive representations. We introduce 3D-permutation with multilayer-perceptron for channel attention alongside a convolutional spatial attention submodule. The evaluation of the proposed mechanism for the image classification task on CIFAR-100 and ImageNet-1K indicates that our method stably outperforms several recent attention mechanisms with both ResNet and lightweight MobileNet.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 416 citations worldwide. Full citation record

  1. DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration

    cs.CL 2025-06 conditional novelty 4.0 of 10

    DAM derives per-layer and per-head attention masks from a calibration dataset and extrapolates them to long inputs, matching full-attention retrieval accuracy while reducing memory and compute.

  2. FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound

    eess.IV 2025-06 reject novelty 2.0 of 10

    FPDANet combines a ResNet backbone with dual attention and bilateral feature fusion to reach 91.05% top-1 accuracy on 21 fetal ultrasound view classes, but the architecture reuses known modules without citation and th...

Pith tools