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

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

doi:10.1109/tip.2022.3205215

Cited by 36 publications

(12 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, significant progress has been made in fine-grained visual classification [1,3,4,20]. In contrast to general image classification tasks, fine-grained visual classification places greater emphasis on subtle features that are hard to distinguish in images [2].…”

Section: Related Work 21 Fine-grained Visual Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Granularity Hypergraph Enhanced Hierarchical Neural Network Framework for Visual Classification

Jiang,

Chen,

Lei

et al. 2024

Preprint

View full text Add to dashboard Cite

Fine-grained single-label classification tasks aim to distinguish highly similar categories but often overlook inter-category relationships. Hierarchical multi-granularity visual classification strives to categorize image labels at various hierarchy levels, offering optimize label selection for people. This paper addresses the hierarchical multi-granularity classification problem from two perspectives: (1) effective utilization of labels at different levels and (2) efficient learning to distinguish multi-granularity visual features. To tackle these issues, we propose a novel multi-granularity hypergraph enhanced Hierarchical Neural Network (HNN) framework, seamlessly integrating swin transformers and hypergraph neural networks for handling visual classification tasks. Firstly, we employ swin transformer as a Image Hierarchical Feature Learning (IHFL) module to capture hierarchical features. Secondly, a Feature Reassemble (FR) module is applied to rearrange features at different hierarchy levels, creating a spectrum of features from coarse to fine-grained. Thirdly, to unveil the correlation between features at different granularity, we propose a Feature Relationship Mining (FRM) module. Within this module, a learnable hypergraph modeling method is introduced to construct coarse to fine-grained hypergraph structures. Simultaneously, multi-granularity hypergraph neural networks are employed to explore grouping relationships feature in different granularity, enhancing semantic feature representation learning within the hypergraph space. Finally, we adopt a Multi-Granularity Classifier (MGC) to predict hierarchical label probabilities. Experimental results demonstrate that HNN outperforms other state-of-the-art classification methods across three multi-granularity datasets.

show abstract

Section: Related Work 21 Fine-grained Visual Classificationmentioning

confidence: 99%

“…In recent years, the success of deep learning in the field of computer vision has propelled the development of Fine-Grained Visual Classification (FGVC) [1][2][3][4] tasks. Fine-grained single-label classification tasks aim to distinguish highly similar categories [5][6][7][8], but they often overlook the inter-category relationships.…”

Section: Introductionmentioning

confidence: 99%

Multi-Granularity Hypergraph Enhanced Hierarchical Neural Network Framework for Visual Classification

Jiang,

Chen,

Lei

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Behera et al [27] calculated the self-attention graph of output features to express the relationship between feature pixels. Bera et al [28] used graph convolutional neural networks to describe the relationship between features. Rao et al [29] proposed to add a counterfactual intervention to the attention diagram to predict categories.…”

Section: Fined-grained Image Classificationmentioning

confidence: 99%

ACANet: A Fine-grained Image Classification Optimization Method Based on Convolution and Attention Fusion

Zhi Tan,

Zhi Tan

2024

Journal of Computers

View full text Add to dashboard Cite

<p>The key to solve the problem of fine-grained image classification is to find the differentiation regions related to fine-grained features. In this paper, we try to add new network components to the original network and adjust various parameters to try to propose a new fine-grained image classification network. We propose a fine-grained image classification network based on the fusion of asymmetric convolution, convolution and self-attention mechanisms. Firstly, an enhanced module using asymmetric convolution to assist classical convolution proposed to help convolution learn deep features. Secondly, according to the common points of convolution and self-attention mechanism, we invented a fusion module of convolution and self-attention mechanism to improve the learning ability of the network.We integrate these two modules into the residual network and invent a new residual network .Finally, according to the experience, we design a new downsampling layer to adapt to the new component of the attention mechanism and improve the performance of the model. The experiment test on three publicly available datasets, and three methods for comparison. The results show that the new structure can effectively complete the task of fine-grained image classification, and the classification accuracy of different methods and different datasets are significantly improved.</p> <p> </p>

show abstract

“…• Many previous works [29,33,49] have proved that using too many graph convolutional network (GCN) layers to pass message can cause over-smoothing, which harms the spatial structure construction within object scope. Our experiment in Table 6 also verify this conclusion.…”

Section: Sfi-netmentioning

confidence: 99%

Semantic Feature Integration network for Fine-grained Visual Classification

Wang

Luo

2023

Preprint

View full text Add to dashboard Cite

Fine-Grained Visual Classification (FGVC) is known as a challenging task due to subtle differences among subordinate categories. Many current FGVC approaches focus on identifying and locating discriminative regions, but neglect the presence of unnecessary features that impair the understanding of object structure. These unnecessary features, including 1) ambiguous parts resulting from the visual similarity in object appearances and 2) noninformative parts (e.g., background noise), can have a significant adverse impact on classification results. To address this limitation, we propose the Semantic Feature Integration network (SFI-Net) to eliminate unnecessary information and reconstructing the semantic relations among discriminative features. The network consists of two modules: 1) the multi-level feature filter (MFF) module is proposed to remove unnecessary features with different receptive field, and then concatenate the preserved features on pixel level for subsequent disposal; 2) the semantic information reconstitution (SIR) module is presented to further establish semantic relations among discriminative features obtained from the MFF module. These two modules are carefully designed and can be trained end-to-end in a weakly-supervised way. Extensive experiments on four challenging fine-grained benchmarks demonstrate that our proposed SFI-Net achieves the state-of-the-arts performance. Especially, the classification accuracy of our model on CUB-200-2011 and Stanford Dogs reaches 92.64% and 93.03%, respectively.

show abstract

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

Cited by 36 publications

References 75 publications

Multi-Granularity Hypergraph Enhanced Hierarchical Neural Network Framework for Visual Classification

Multi-Granularity Hypergraph Enhanced Hierarchical Neural Network Framework for Visual Classification

ACANet: A Fine-grained Image Classification Optimization Method Based on Convolution and Attention Fusion

Semantic Feature Integration network for Fine-grained Visual Classification

Contact Info

Product

Resources

About