Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection
This work addresses the lack of open-vocabulary detection in thermal imagery, a domain where RGB-based methods fail, enabling language-driven thermal perception for applications like autonomous driving and surveillance.
Thermal-Det introduces the first open-vocabulary thermal object detector, leveraging LLM-supervised training on a synthetic thermal dataset and cross-modal distillation from RGB to thermal, achieving 2-4% AP gains over existing open-vocabulary detectors on public benchmarks.
Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge RGB-based semantics. We present Thermal-Det, the first large language model (LLM) supervised open-vocabulary detector tailored for thermal images. To enable large-scale training, we develop a synthetic dataset by converting GroundingCap-1M into the thermal domain and filtering captions to remove RGB-specific terms, yielding over one million thermally aligned samples with bounding boxes, grounding texts, and detailed captions. Thermal-Det jointly optimizes detection, captioning, and cross-modal distillation objectives. A frozen RGB teacher provides geometric and semantic pseudo-supervision for paired but unlabeled RGB-thermal data, transferring open-vocabulary knowledge without manual annotation. The model further employs a Thermal-Text Alignment Head for text calibration and a Modality-Fused Cross-Attention module for dual-modality reasoning. Unlike prior domain-adaptation methods, the detector is fully fine-tuned to internalize thermal contrast patterns while preserving language alignment. Experiments on public benchmarks show consistent 2-4% AP gains over existing open-vocabulary detectors, establishing a strong foundation for scalable, language-driven thermal perception.