Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-boosting Attention Mechanism

Shu, Yangyang; Yu, Baosheng; Xu, Haiming; Liu, Lingqiao

doi:10.1007/978-3-031-19806-9_26

Cited by 11 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Ambiguous decision boundary among AD subtypes: The decision boundary between different AD stages' subjects is more ambiguous than natural image-based classification problems. For example, according the ADNI differentiate criterion [72], the Mini-Mental State Examination (MMSE) score ranges of NC, MCI, and AD are [24][25][26][27][28][29][30], [24][25][26][27][28][29][30], and [20][21][22][23][24][25][26], respectively, and there obviously exists overlaps between different stages, as shown in Fig. A1.…”

Section: Discussionmentioning

confidence: 99%

“…Due to the small inter-class variations between fine-grained categories and the large intra-class variations in individual differences [24], numerous researchers have paid their attention on the fine-grained classification field [25], [26], [27], [28]. However, existing state-of-the-art (SOTA) fine-grained classification methods mainly focus on fine-grained labeled data to mine discriminative information, which can be roughly divided into two general categories [24]: recognition by localization-classification subnetworks [25], [26], [27], [28], and recognition by end-to-end feature encoding [29].…”

Section: B Fine-grained Classificationmentioning

confidence: 99%

“…AD-related competing methods includes 3D-ResNet f 2 [51], 3D-SENet [5], I3D [52], ResAttNet [19], TripleMRNet [20], TSM-Res18 [53], and MedicalNet [18]. Specifically, 3D-ResNet For fine-grained methods, ProtoTree [26], SAM [27], ViT-NeT [28], and MPNCOV+SEB [29] were selected as baselines. The first three fall within the recognition of localizationclassification subnetworks, whereas the last one is categorized under recognition by end-to-end feature encoding.…”

Section: A Experimental Setupmentioning

confidence: 99%

See 2 more Smart Citations

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Yang

Zhou

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Mild cognitive impairment (MCI) is often at high risk of progression to Alzheimer's disease (AD).Existing works to identify the progressive MCI (pMCI) typically require MCI subtype labels, pMCI vs. stable MCI (sMCI), determined by whether or not an MCI patient will progress to AD after a long follow-up. However, prospectively acquiring MCI subtype data is time-consuming and resource-intensive; the resultant small datasets could lead to severe overfitting and difficulty in extracting discriminative information. Inspired by that various longitudinal biomarkers and cognitive measurements present an ordinal pathway on AD progression, we propose a novel Hybrid-granularity Ordinal PrototypE learning (HOPE) method to characterize AD ordinal progression for MCI progression prediction. First, HOPE learns an ordinal metric space that enables progression prediction by prototype comparison. Second, HOPE leverages a novel hybridgranularity ordinal loss to learn the ordinal nature of AD via effectively integrating instance-to-instance ordinality, instance-to-class compactness, and class-to-class separation. Third, to make the prototype learning more stable, HOPE employs an exponential moving average strategy to learn the global prototypes of NC and AD dynamically. Experimental results on the internal ADNI and the external NACC datasets demonstrate the superiority of the proposed HOPE over existing state-of-the-art methods as well as its interpretability. Source code is made available at https://github.com/thibault-wch/ HOPE-for-mild-cognitive-impairment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: B Fine-grained Classificationmentioning

confidence: 99%

Section: A Experimental Setupmentioning

confidence: 99%

See 1 more Smart Citation

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Yang

Zhou

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…It allows neural networks to concentrate on essential parts of the information being processed while neglecting insignificant or irrelevant parts. To date, the attention mechanism has been widely applied in multiple deep-learning domains such as natural language processing, computer vision, and speech recognition, including classic structures like SE-Net [28], ECA-Net [32], CBAM [33], and SAM [34]. Xu et al [35] were the first to employ the attention mechanism for the resolution of computer vision problems in 2015, laying a solid foundation for the mechanism's development within computer vision.…”

Section: Attention Mechanismmentioning

confidence: 99%

Discerning Reality through Haze: An Image Dehazing Network Based on Multi-Feature Fusion

Wang,

Jiang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Numerous single-image dehazing algorithms have been developed, employing a spectrum of techniques ranging from intricate physical computations to state-of-the-art deep-learning methodologies. However, conventional deep-learning approaches, particularly those based on standard convolutional neural networks (CNNs), often result in the persistence of residual fog patches when applied to images featuring high fog concentration or heterogeneous fog distribution. In response to this challenge, we propose an innovative solution known as the multi-feature fusion image dehazing network (MFID-Net). This approach employs an end-to-end methodology to directly capture the mapping relationship between hazy and fog-free images. Central to our approach is the introduction of a novel multi-feature fusion (MF) module, strategically designed to address channel and pixel characteristics in regions with uneven or high fog concentrations. Notably, this module achieves effective haze reduction while minimizing computational resources, thereby mitigating the issue of residual fog patches. Experimental results underscore the superior performance of our algorithm compared to similar dehazing methods, as evidenced by higher scores in structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and computational velocity. Moreover, MFID-Net exhibits significant advancements in restoring details within expansive monochromatic areas, such as skies and white walls.

show abstract

Distilling Local Texture Features for Colorectal Tissue Classification in Low Data Regimes

Demidov,

Al Majzoub,

Kumar

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-boosting Attention Mechanism

Cited by 11 publications

References 23 publications

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Discerning Reality through Haze: An Image Dehazing Network Based on Multi-Feature Fusion

Distilling Local Texture Features for Colorectal Tissue Classification in Low Data Regimes

Contact Info

Product

Resources

About