HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection

• URL: http://arxiv.org/abs/2608.05771v2
• Date: Fri, 07 Aug 2026 08:07:42 GMT
• Title: HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection
• Abstract summary: Infrared small target detection (IRSTD) has achieved substantial progress under domain-consistent evaluation.<n>We propose HyTBE, a Hyperbolic Target-Background Expert model that expands source-domain relation patterns.<n>Experiments on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K demonstrate that HyTBE achieves stronger cross-domain generalization than competitive baselines.
• Score: 3.6870604311531885
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Infrared small target detection (IRSTD) has achieved substantial progress under domain-consistent evaluation, yet detector performance often degrades markedly when generalizing to unseen infrared domains. Existing methods primarily improve detection by enhancing target responses and suppressing background interference. However, when trained on only a limited set of source domains, their learned decision rules are inevitably established from a restricted range of source-domain target-background relation patterns. We formulate this cross-domain failure as target-background relation shift: unseen domains may exhibit relation patterns that are not observed during training, thereby weakening the discriminative capability learned from the source domains. To address this problem, we propose HyTBE, a Hyperbolic Target-Background Expert model that expands source-domain relation patterns and adaptively adjusts visual representations using explicit relation cues. The Target-Background Relation Intervention selectively perturbs either targets or backgrounds, broadening the observable relation patterns during training while maintaining valid supervision. Subsequently, the Hyperbolic Relation Modeling maps multi-scale visual cues into a Poincaré ball and characterizes the target-background relation of each feature token according to its relative distances to the target and background anchors. The Hyperbolic-guided MoE Adapter further uses these hyperbolic relation representations to calibrate multi-scale visual features and aggregate expert-specific feature corrections for different relation patterns. Leave-one-domain-out experiments on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K demonstrate that HyTBE achieves stronger cross-domain generalization than competitive baselines.

Related papers

• LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection [50.3892176822492]
  Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds.<n>Deep learning methods have improved IRSTD by learning discriminative image-to-mask mappings.<n>Deep unfolding methods partially address this issue by embedding model-driven iterations into neural networks.<n>We propose Latent Consistent Proximal unfolding network (LCPNet) to address these limitations.
  arXiv  Detail & Related papers  (2026-07-06T02:15:09Z)
• Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking [58.338848435042536]
  RGB-Event tracking improves localization by fusing RGB appearance textures and dense temporal motion cues from event sensors.<n>Real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion.<n>We present a hierarchical perturbation and retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation.
  arXiv  Detail & Related papers  (2026-06-24T23:34:06Z)
• DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection [75.11656789221072]
  We propose DisDop, a unified framework that distills multi-level domain priors from remote sensing foundation models.<n>DisDop achieves new state-of-the-art performance on open-vocabulary aerial detection benchmarks.
  arXiv  Detail & Related papers  (2026-05-23T16:01:20Z)
• Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain [26.03122882760887]
  We propose a spatial-spectral collaborative perception network for cross-domain IRSTD.<n>We develop a phase rectification module (PRM) to derive generalizable target awareness.<n>We employ an attention mechanism (OAM) in skip connections to preserve positional information.
  arXiv  Detail & Related papers  (2026-04-02T11:54:28Z)
• Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection [19.113214017897118]
  Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations.<n>We find a previously overlooked phenomenon: models exhibit imprecise and unfocused attention in target domains.<n>Our bio-inspired approach transforms astigmatic attention into focused patterns, substantially improving adaptation to target domains.
  arXiv  Detail & Related papers  (2026-03-19T06:55:32Z)
• SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection [18.86422994684341]
  Infrared small target detection (IRSTD) is crucial for surveillance and early-warning, with deployments spanning both single-frame analysis and video-mode tracking.<n>We propose SPIRIT, a unified and VFM-compatible framework that adapts VFMs to IRSTD via lightweight physics-informed plug-ins.
  arXiv  Detail & Related papers  (2026-02-02T09:15:29Z)
• VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection [9.029534000674388]
  VG-DETR integrates a Vision Foundation Model (VFM) into the training pipeline in a "free lunch" manner.<n>We introduce a VFM-guided pseudo-label mining strategy that leverages the VFM's semantic priors to assess the reliability of the generated pseudo-labels.<n>In addition, a dual-level VFM-guided alignment method is proposed, which aligns detector features with VFM embeddings at both the instance and image levels.
  arXiv  Detail & Related papers  (2025-08-15T02:35:56Z)
• Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector [72.05791402494727]
  This paper studies the challenging cross-domain few-shot object detection (CD-FSOD) It aims to develop an accurate object detector for novel domains with minimal labeled examples.
  arXiv  Detail & Related papers  (2024-02-05T15:25:32Z)
• Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection [81.07378219410182]
  We propose a new and general framework for DomainD, named Foreground-aware Graph-based Reasoning (FGRR) FGRR incorporates graph structures into the detection pipeline to explicitly model the intra- and inter-domain foreground object relations. Empirical results demonstrate that the proposed FGRR exceeds the state-of-the-art on four DomainD benchmarks.
  arXiv  Detail & Related papers  (2022-06-06T05:12:48Z)
• Ranking Distance Calibration for Cross-Domain Few-Shot Learning [91.22458739205766]
  Recent progress in few-shot learning promotes a more realistic cross-domain setting. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. We employ a re-ranking process for calibrating a target distance matrix by discovering the reciprocal k-nearest neighbours within the task.
  arXiv  Detail & Related papers  (2021-12-01T03:36:58Z)

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.