Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination

• URL: http://arxiv.org/abs/2504.08020v1
• Date: Thu, 10 Apr 2025 17:30:39 GMT
• Title: Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination
• Authors: Qi Bi, Jingjun Yi, Haolan Zhan, Wei Ji, Gui-Song Xia,
• Abstract summary: Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains.<n>This paper presents a novel Hyperbolic State Space Hallucination (HSSH) method.<n> Experiments on three FGDG benchmarks demonstrate its state-of-the-art performance.
• Score: 39.0240397696825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is particularly challenging in that the fine-grained category can be only discerned by some subtle and tiny patterns. Such patterns are particularly fragile under the cross-domain style shifts caused by illumination, color and etc. To push this frontier, this paper presents a novel Hyperbolic State Space Hallucination (HSSH) method. It consists of two key components, namely, state space hallucination (SSH) and hyperbolic manifold consistency (HMC). SSH enriches the style diversity for the state embeddings by firstly extrapolating and then hallucinating the source images. Then, the pre- and post- style hallucinate state embeddings are projected into the hyperbolic manifold. The hyperbolic state space models the high-order statistics, and allows a better discernment of the fine-grained patterns. Finally, the hyperbolic distance is minimized, so that the impact of style variation on fine-grained patterns can be eliminated. Experiments on three FGDG benchmarks demonstrate its state-of-the-art performance.

Related papers

• DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization [27.903842187045118]
  We propose a novel Flow Factorized State Space model, dubbed as DG-Famba, for visual domain generalization. To maintain domain consistency, we innovatively map the style-augmented and the original state embeddings by flow factorization. Experiments conducted on various visual domain generalization settings show its state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-04-10T17:24:53Z)
• DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration [62.44659039265439]
  We propose a Diffusion-Information-Diffusion framework to tackle blind face restoration. DiffMAC achieves high-generalization face restoration in diverse degraded scenes and heterogeneous domains. Results demonstrate the superiority of DiffMAC over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-15T08:44:15Z)
• Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning [70.0681902472251]
  We propose a novel contrastive learning framework to learn high-quality graph embeddings in hyperbolic space.<n>Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information.<n>We show that in the hyperbolic space one has to address the leaf- and height-level uniformity related to properties of trees.
  arXiv  Detail & Related papers  (2023-10-27T15:31:42Z)
• Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation [39.35385886870209]
  We introduce a dual-stage Feature Transform (dFT) layer within the Adversarial Semantic Hallucination+ framework. By leveraging semantic information for each pixel, our approach adaptively adjusts the pixel-wise hallucination strength. We validate the effectiveness of our proposed method through comprehensive experiments on publicly available semantic segmentation benchmark datasets.
  arXiv  Detail & Related papers  (2023-04-18T23:54:20Z)
• FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion [45.470475498688344]
  Some important operations in hyperbolic space still lack good definitions, making existing methods unable to fully leverage the merits of hyperbolic space. We develop a textbfFully and textbfFlexible textbfHyperbolic textbfRepresentation framework (textbfFFHR) that is able to transfer recent Euclidean-based advances to hyperbolic space.
  arXiv  Detail & Related papers  (2023-02-07T14:50:28Z)
• Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization [113.03189252044773]
  We propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle domain shift in various visual tasks. Our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2022-12-18T11:42:51Z)
• Enhancing Hyperbolic Graph Embeddings via Contrastive Learning [7.901082408569372]
  We propose a novel Hyperbolic Graph Contrastive Learning (HGCL) framework which learns node representations through multiple hyperbolic spaces. Experimental results on multiple real-world datasets demonstrate the superiority of the proposed HGCL.
  arXiv  Detail & Related papers  (2022-01-21T06:10:05Z)
• Generalization Error Bound for Hyperbolic Ordinal Embedding [21.320308755965748]
  Hyperbolic ordinal embedding (HOE) represents entities as points in hyperbolic space. We provide a generalization error bound of HOE for the first time, which is at most exponential with respect to the embedding space's radius. Our comparison between the bounds of HOE and Euclidean ordinal embedding shows that HOE's generalization error is reasonable as a cost for its exponential representation ability.
  arXiv  Detail & Related papers  (2021-05-21T17:31:08Z)
• Sparse Graphical Memory for Robust Planning [93.39298821537197]
  We introduce Sparse Graphical Memory (SGM), a new data structure that stores states and feasible transitions in a sparse memory. SGM aggregates states according to a novel two-way consistency objective, adapting classic state aggregation criteria to goal-conditioned RL. We show that SGM significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
  arXiv  Detail & Related papers  (2020-03-13T17:59:32Z)

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.