FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory
Deep learning models have been widely applied across various domains and industries. However, many fields still face challenges due to limited and insufficient data. This paper proposes a Feature Augmentation on Adaptive Geodesic Curve (FAAGC) method in the pre-shape space to increase data. In the pre-shape space, objects with identical shapes lie on a great circle. Thus, we project deep model representations into the pre-shape space and construct a geodesic curve, i.e., an arc of a great circle, for each class. Feature augmentation is then performed by sampling along these geodesic paths. Extensive experiments demonstrate that FAAGC improves classification accuracy under data-scarce conditions and generalizes well across various feature types.
Code (0)
등록된 구현이 없습니다.
Tasks
ARCSimilar Papers 제목 키워드 기반
FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
Deep learning has yielded remarkable outcomes in various domains. However, the challenge of requiring large-scale labeled samples still persists in deep learning. Thus, data augmentation has been introduced as a critical…
Data AugmentationDeep LearningAn Elastica Geodesic Approach With Convexity Shape Prior
The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit the image …
Image SegmentationSegmentationSemantic SegmentationGeodesic Models with Convexity Shape Prior
The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit image features…
Image SegmentationSegmentationSemantic SegmentationAGC: Adaptive Geodesic Correction for Adversarial Robustness on Vision-Language Models
Vision-language models like CLIP have demonstrated remarkable zero-shot transfer capabilities. However, their susceptibility to imperceptible adversarial perturbations remains a critical security concern. While test-time…
Adversarial RobustnessData AugmentationFeature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models
Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of …