AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Multiscale Graph Texture Network

Ravishankar Evani, Deepu Rajan, Shangbo Mao

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 5 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 GTN instead of RADAM on frozen ConvNeXt backbonesRADAM · KTH-TIPS2-baccuracy: 89.3 -> 92.5 (ConvNeXt-L)Improved
use GTN instead of RADAM on GTOS-MRADAM · GTOS-Maccuracy: 85.8 -> 93.9 (ConvNeXt-L)Improved
use GTN instead of RADAM on FMDRADAM · FMDaccuracy: 89.3 -> 88.1 (ConvNeXt-L)Hurt
use GTN instead of MPAP with ResNet50 on DTDMPAP · DTDaccuracy: 78.0 -> 74.6Hurt
scale up the frozen ConvNeXt backbone sizeGTN versus RADAM · DTDaccuracy: 75.4 -> 79.3 (ConvNeXt-N to L)Improved
add residual message passing on top of vertex representation (ablation)GTN · DTDaccuracy: 77.0 -> 77.5Improved
add vertex representation of latent texture attributes (ablation)GTN · DTDaccuracy: 27.6 -> 77.0Improved
add self-loop re-calibration at r=16 (ablation)GTN · DTDaccuracy: 71.4 -> 71.5No clear effect
add more backbone layers as graph sources (M from 1 to 5) (ablation)GTN · DTDaccuracy: 75.0 -> 77.5Improved
increase compression ratio r from 2 to 16 (ablation)GTN · DTDaccuracy: 77.9 -> 71.5Hurt

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