Disentangle Object and Non-object Infrared Features via Language Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914255079473152 |
|---|---|
| author | Liu, Fan Wu, Ting Zhang, Chuanyi Yao, Liang Ma, Xing Zheng, Yuhui |
| author_facet | Liu, Fan Wu, Ting Zhang, Chuanyi Yao, Liang Ma, Xing Zheng, Yuhui |
| contents | Infrared object detection focuses on identifying and locating objects in complex environments (\eg, dark, snow, and rain) where visible imaging cameras are disabled by poor illumination. However, due to low contrast and weak edge information in infrared images, it is challenging to extract discriminative object features for robust detection. To deal with this issue, we propose a novel vision-language representation learning paradigm for infrared object detection. An additional textual supervision with rich semantic information is explored to guide the disentanglement of object and non-object features. Specifically, we propose a Semantic Feature Alignment (SFA) module to align the object features with the corresponding text features. Furthermore, we develop an Object Feature Disentanglement (OFD) module that disentangles text-aligned object features and non-object features by minimizing their correlation. Finally, the disentangled object features are entered into the detection head. In this manner, the detection performance can be remarkably enhanced via more discriminative and less noisy features. Extensive experimental results demonstrate that our approach achieves superior performance on two benchmarks: M\textsuperscript{3}FD (83.7\% mAP), FLIR (86.1\% mAP). Our code will be publicly available once the paper is accepted. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09228 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Disentangle Object and Non-object Infrared Features via Language Guidance Liu, Fan Wu, Ting Zhang, Chuanyi Yao, Liang Ma, Xing Zheng, Yuhui Computer Vision and Pattern Recognition Infrared object detection focuses on identifying and locating objects in complex environments (\eg, dark, snow, and rain) where visible imaging cameras are disabled by poor illumination. However, due to low contrast and weak edge information in infrared images, it is challenging to extract discriminative object features for robust detection. To deal with this issue, we propose a novel vision-language representation learning paradigm for infrared object detection. An additional textual supervision with rich semantic information is explored to guide the disentanglement of object and non-object features. Specifically, we propose a Semantic Feature Alignment (SFA) module to align the object features with the corresponding text features. Furthermore, we develop an Object Feature Disentanglement (OFD) module that disentangles text-aligned object features and non-object features by minimizing their correlation. Finally, the disentangled object features are entered into the detection head. In this manner, the detection performance can be remarkably enhanced via more discriminative and less noisy features. Extensive experimental results demonstrate that our approach achieves superior performance on two benchmarks: M\textsuperscript{3}FD (83.7\% mAP), FLIR (86.1\% mAP). Our code will be publicly available once the paper is accepted. |
| title | Disentangle Object and Non-object Infrared Features via Language Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.09228 |