Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data

• URL: http://arxiv.org/abs/2604.19345v1
• Date: Tue, 21 Apr 2026 11:27:33 GMT
• Title: Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data
• Abstract summary: This paper investigates the intrinsic geometrical features of highly similar objects.<n>It introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor)<n>GAEor generates geometric attributes as novel alternative recognition cues.
• Score: 73.20753799870282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the ultra-fine-grained visual categorization (Ultra-FGVC) task in data-limited scenarios. Unlike prior work that often captures subtle yet critical distinctions, GAEor generates geometric attributes as novel alternative recognition cues. These attributes are determined by various details within the object, aligned with its geometric patterns, such as the intricate vein structures in soybean leaves. Crucially, each category exhibits distinct geometric descriptors that serve as powerful cues, even among objects with minimal visual variation -- a factor largely overlooked in recent research. GAEor discovers these geometric attributes by first amplifying geometry-relevant details via visual feedback from a backbone network, then embedding the relative polar coordinates of these details into the final representation. Extensive experiments demonstrate that GAEor significantly sets new state-of-the-art records in five widely-used Ultra-FGVC benchmarks.

Related papers

• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentation [11.12183614587322]
  Cross-domain few-shot medical image segmentation (CD-FSMIS) requires a model to generalise simultaneously to novel anatomical categories and unseen imaging domains.<n>Existing prototypical approaches inevitably entangle anatomical structure with domain-specific appearance variations.<n>We propose GeoProto, a geometry-aware CD-FSMIS framework that enriches matching with explicit structural priors.
  arXiv  Detail & Related papers  (2026-05-11T17:32:26Z)
• Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts [33.295461492913354]
  Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data.<n>Existing zero-shot GAD methods largely ignore intrinsic geometric differences across diverse anomaly patterns.<n>We propose GAD-MoRE, a novel framework for zero-shot Generalizable Graph Anomaly Detection.
  arXiv  Detail & Related papers  (2026-02-06T16:46:30Z)
• Bridging Structure and Appearance: Topological Features for Robust Self-Supervised Segmentation [8.584363058858935]
  Self-supervised semantic segmentation methods often fail when faced with appearance ambiguities.<n>We argue that this is due to an over-reliance on unstable, appearance-based features such as shadows, glare, and local textures.<n>We propose textbfGASeg, a novel framework that bridges appearance and geometry by leveraging stable topological information.
  arXiv  Detail & Related papers  (2025-12-30T05:34:28Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction [26.668204454537246]
  We introduce textbfVisual Gaussian Driving (VGD), a novel feed-forward end-to-end learning framework designed to address this challenge.<n>We show that our approach significantly outperforms state-of-the-art methods in both objective metrics and subjective quality under various settings.
  arXiv  Detail & Related papers  (2025-10-22T13:28:49Z)
• Geometry-Editable and Appearance-Preserving Object Compositon [67.98806888489385]
  General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties.<n>Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation.<n>We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion model that first leverages semantic embeddings to implicitly capture desired geometric transformations.
  arXiv  Detail & Related papers  (2025-05-27T09:05:28Z)
• Global graph features unveiled by unsupervised geometric deep learning [0.0]
  We introduce GAUDI, a novel unsupervised deep learning framework designed to capture both local details and global structure.<n>GAUDI consistently maps them into nearby regions of a structured and continuous latent space, effectively disentangling in process-level features from noise.<n>We demonstrate GAUDIs versatility across multiple applications, including small-world modeling, characterization of protein assemblies, analysis of collective motion in the Vicsek model, and identification of age-related changes in brain connectivity.
  arXiv  Detail & Related papers  (2025-03-07T16:38:41Z)
• Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution [8.107199775668942]
  Integrated Gradients (IG) is a prevalent feature attribution method for black-box deep learning models. We address two predominant challenges associated with IG: the generation of noisy feature visualizations and the vulnerability to adversarial attributional attacks. Our approach involves an adaptation of path-based feature attribution, aligning the path of attribution more closely to the intrinsic geometry of the data manifold.
  arXiv  Detail & Related papers  (2024-05-16T04:13:17Z)
• A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications [71.809127869349]
  This paper formalizes geometric graph as the data structure, on top of which we provide a unified view of existing models from the geometric message passing perspective.<n>We also summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
  arXiv  Detail & Related papers  (2024-03-01T12:13:04Z)
• The geometry of hidden representations of large transformer models [43.16765170255552]
  Large transformers are powerful architectures used for self-supervised data analysis across various data types. We show that the semantic structure of the dataset emerges from a sequence of transformations between one representation and the next. We show that the semantic information of the dataset is better expressed at the end of the first peak, and this phenomenon can be observed across many models trained on diverse datasets.
  arXiv  Detail & Related papers  (2023-02-01T07:50:26Z)
• Self-supervised Geometric Perception [96.89966337518854]
  Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels. We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
  arXiv  Detail & Related papers  (2021-03-04T15:34:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.