8 papers
G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
Yechan Kim, JongHyun Park, Dongho Yoon +2
This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD addresses key limitations of…
Regional Attention-Enhanced Swin Transformer for Clinically Relevant Medical Image Captioning
Zubia Naz, Farhan Asghar, Muhammad Ishfaq Hussain +4
Automated medical image captioning translates complex radiological images into diagnostic narratives that can support reporting workflows. We present a Swin-BART encoder-decoder sy…
SWIR-LightFusion: Multi-spectral Semantic Fusion of Synthetic SWIR with Thermal IR (LWIR/MWIR) and RGB
Muhammad Ishfaq Hussain, Ma Van Linh, Zubia Naz +3
Enhancing scene understanding in adverse visibility conditions remains a critical challenge for surveillance and autonomous navigation systems. Conventional imaging modalities, suc…
Investigating Long-term Training for Remote Sensing Object Detection
JongHyun Park, Yechan Kim, Moongu Jeon
Recently, numerous methods have achieved impressive performance in remote sensing object detection, relying on convolution or transformer architectures. Such detectors typically ha…
Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noise
Yechan Kim, Dongho Yoon, Younkwan Lee +7
While previous studies on image segmentation focus on handling severe (or explicit) label noise, real-world datasets also exhibit subtle (or implicit) label imperfections. These ar…
NSegment : Label-specific Deformations for Remote Sensing Image Segmentation
Yechan Kim, DongHo Yoon, SooYeon Kim +1
Labeling errors in remote sensing (RS) image segmentation datasets often remain implicit and subtle due to ambiguous class boundaries, mixed pixels, shadows, complex terrain featur…