Research
Understand Before Detect: Vision--Language Learning for Omni-Domain Infrared Small Target Detection
arXiv:2608.07015v1 Announce Type: new Abstract: Omni-domain infrared small target (IRST) detection is crucial for infrared surveillance, yet remains challenging due to heterogeneous imaging domains an
arXiv:2608.07015v1 Announce Type: new Abstract: Omni-domain infrared small target (IRST) detection is crucial for infrared surveillance, yet remains challenging due to heterogeneous imaging domains and inconsistent target characteristics. Previous deep learning-based methods have been developed for visual-only paradigms and achieved promising performance on domain-specific tasks. However, existing methods follow the task-specific supervised learning paradigm. This paradigm simplifies the full-scene infrared observations to sparse target supervision, discarding the semantics that remain invariant across heterogeneous domains. Consequently, detection performance suffers substantially under domain shifts. To handle this issue, we introduce extbf{``understand before detect''}, a paradigm that formulates omni-domain IRST detection as an understanding-driven process, where holistic infrared target understanding precedes precise detection. Building on this paradigm, we propose extbf{JinSight}, which first develops holistic IRST understanding through language supervision and then transfers the learned cross-domain representations to precise small-target detection. By grounding infrared representations in language semantics, JinSight enables a single model to generalize across heterogeneous infrared domains. We then introduce Latent Semantic Interaction (LSI), which exchanges language-aligned global semantics with fine-grained spatial features in a compact low-rank space. To address the lack of multimodal omni-domain IRST benchmarks, we build extbf{OmniIRST-VL}, the first large-scale, highly diverse vision--language dataset for omni-domain IRST detection. It comprises over 39k annotations across six complementary instruction tasks covering both scene-level understanding and target-centric reasoning.
Related
- T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
- Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection
- Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection
- T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining
Source: arXiv cs.CV | 2026-08-10