Papers › SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

5 Sep 2022arXiv:2209.02109archive 2025-07-28

Asish Bera, Zachary Wharton, Yonghuai Liu, Nik Bessis, Ardhendu Behera

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ardhendubehera/sr-gnn officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Image ClassificationGraph Neural NetworkHuman-Object Interaction DetectionImage CategorizationObject

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification FGVC Aircraft SR-GNN Accuracy 95.4 #2 of 57 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft SR-GNN FLOPS 9.8 #2 of 57 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft SR-GNN PARAMS 30.9 #2 of 57 Archive leaderboard report
Fine-Grained Image Classification NABirds SR-GNN Accuracy 91.2% #10 of 30 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers SR-GNN Accuracy 97.9% #16 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers SR-GNN FLOPS 9.8 #16 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers SR-GNN PARAMS 30.9 #16 of 25 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars SR-GNN Accuracy 96.1 #7 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars SR-GNN FLOPS 9.8 #7 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars SR-GNN PARAMS 30.9 #7 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Dogs MP Accuracy 97.3% #1 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections