Visual graphs for image classification: does the structure affect performance?
Deep learning models have emerged in machine learning and related fields, demonstrating astonishing performance in various visual tasks. Despite their great success, however, these models are unable to fully encode intrinsic visual structures, and often ignore the spatial, topological, and semantic information contained within an image. Graph neural networks offer a good framework to face this aspect, but their effective use for visual tasks has been only partly explored and mainly starting from a limited perspective. This work aims to address this gap by conducting a systematic comparison of
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%JuliaGraphs/GraphNeuralNetworks.jl →
- PossiblePossibly related (embedding) · 48%willyfh/visualtorch →
- PossiblePossibly related (embedding) · 47%lutzroeder/netron →
- PossiblePossibly related (embedding) · 47%voxel51/fiftyone →
- PossiblePossibly related (embedding) · 45%Graph Neural Networks: When Relationships Are the Signal - Snowflake →
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Visual graphs for image classification: does the structure a” ≈ “Tongyi-MAI/Z-Image-Turbo””
- LinkedLinked via arxiv author · 85%Alessandra Ibba →
“Visual graphs for image classification: does the structure affect performance?”
- PossiblePossibly related (embedding) · 48%Context and average best linear mappings [D] →