5 papers
IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE
Rikuto Otsuka, Yuho Shoji, Yuka Ogino +2
This paper proposes image-adaptive contrast limited adaptive histogram equalization (IA-CLAHE). Conventional CLAHE is widely used to boost the performance of various computer visio…
Target Driven Adaptive Loss For Infrared Small Target Detection
Yuho Shoji, Takahiro Toizumi, Atsushi Ito
We propose a target driven adaptive (TDA) loss to enhance the performance of infrared small target detection (IRSTD). Prior works have used loss functions, such as binary cross-ent…
Rethinking Image Histogram Matching for Image Classification
Rikuto Otsuka, Yuho Shoji, Yuka Ogino +2
This paper rethinks image histogram matching (HM) and proposes a differentiable and parametric HM preprocessing for a downstream classifier. Convolutional neural networks have demo…
ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing
Yuka Ogino, Yuho Shoji, Takahiro Toizumi +1
We propose an image-adaptive object detection method for adverse weather conditions such as fog and low-light. Our framework employs differentiable preprocessing filters to perform…
Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions
Yuho Shoji, Yuka Ogino, Takahiro Toizumi +1
This paper proposes a deep feature extractor for iris recognition at arbitrary resolutions. Resolution degradation reduces the recognition performance of deep learning models train…