arXiv Computer Vision
RGB-to-IR image translation for infrared vehicle detection in unseen UAV domains
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Aug 19
Training with synthetic data for drone detection in thermal imagery
The paper explores a synthetic-first training approach for detecting drones in medium- and long-wave infrared imagery, combining synthetic scene generation with fine-tuning on real data. It demonstrates that synthetic data can establish initial object representations, but real infrared data is crucial to close domain gaps and improve reliability. The study finds that aligning datasets has a greater impact on performance than increasing model size, and that semantic alignment in feature space is the strongest predictor of success, with radiometric factors like entropy and dynamic range also contributing.
arXiv AI
Jul 7
Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models
arXiv:2607. 02718v1 Announce Type: cross Abstract: Recent advances in large-scale image generative models enable photorealistic scene synthesis with controllable attributes.
arXiv Computer Vision
1d ago
Domain shift-robust object detection with GenAI image editing
arXiv:2609.02299v1 Announce Type: new Abstract: Object detectors often degrade under domain shifts such as changes in lighting, weather, or occlusion. These shifts alter object appearance and expose...
arXiv Machine Learning
Aug 24
On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift
arXiv:2608.21254v1 Announce Type: cross Abstract: Accurate agricultural weed detection in real-world field conditions is essential for precision agriculture, enabling targeted intervention and reduci...
arXiv AI
1d ago
InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
InfraPatch is a white‑box, per‑instance framework that generates small grayscale patches to target infrared‑adapted vision‑language models (IR‑VLMs). The method optimizes a single‑channel patch within a 5% local‑area budget, using proxy‑guided placement and task‑adaptive objectives to induce desired behaviors in image classification, captioning, and binary visual question answering. Across ten IR‑VLM variants tested on synthetic infrared images, InfraPatch achieves targeted attack success rates ranging from 86% to 100%, revealing significant vulnerability differences among architectures and tasks.
arXiv Computer Vision
2d ago
Multimodal RGB-Infrared Combination for UAV-Based Wildfire Segmentation: A Comparative Study on FLAME3
The paper examines RGB‑infrared fusion for binary wildfire segmentation using UAV imagery on the FLAME3 dataset. It compares RGB and infrared baselines with three fusion strategies across U‑Net, DeepLabV3+, and SegFormer architectures. Results show thermal data dominates segmentation performance, and feature‑level fusion with transformer‑based models yields the best results.