no code implementations • 17 Apr 2022 • Ginam Kim, Hyunsung Kim, Joseph Kihoon Kim, Sung-Sik Cho, Yeong-Hun Park, Suk-Ju Kang
In addition, we propose a classification task to distinguish between normal and abnormal states of wearing a seat belt using results that combine 3D pose estimation with seat-belt segmentation.
no code implementations • 7 Oct 2021 • Jouwon Song, Kyeongbo Kong, Ye-In Park, Seong-Gyun Kim, Suk-Ju Kang
Finally, the coordinate channel, which represents the pixel location information, is concatenated to an input of AnoSeg to consider the positional relationship of each pixel in the image.
Ranked #57 on Anomaly Detection on MVTec AD
no code implementations • 8 Jul 2021 • Kyeongbo Kong, Kyunghun Kim, Woo-Jin Song, Suk-Ju Kang
Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks.
no code implementations • 8 Jul 2021 • Jae-hun Shim, Kyeongbo Kong, Suk-Ju Kang
Neural architecture search (NAS), an important branch of automatic machine learning, has become an effective approach to automate the design of deep learning models.
no code implementations • 31 Mar 2021 • Jou Won Song, Kyeongbo Kong, Ye In Park, Suk-Ju Kang
By applying the attention map to an image feature map, ADGAN learns the normal class distribution from which the useless region is removed, and it is possible to greatly reduce the problem difficulty of the anomaly detection task.
no code implementations • 5 Oct 2020 • Kyunghun Kim, Yeohun Yun, Keon-Woo Kang, Kyeongbo Kong, Siyeong Lee, Suk-Ju Kang
The bidirectional boundary region rearrangement enables the generation of the missing region using bidirectional information similar to that of the image inpainting task, thereby generating the higher quality than the conventional methods using unidirectional information.
1 code implementation • 29 Jun 2020 • Jung Hee Kim, Siyeong Lee, Suk-Ju Kang
We tackle the problem in stack reconstruction-based methods by proposing a novel framework with a fully differentiable high dynamic range imaging (HDRI) process.
no code implementations • 9 Jun 2020 • Saehyun Ahn, Jung-Woo Chang, Suk-Ju Kang
In this paper, we present a novel approach to accelerate deformable convolution on FPGA.
no code implementations • 15 Nov 2019 • Jung-Woo Chang, Saehyun Ahn, Keon-Woo Kang, Suk-Ju Kang
To implement the DeConv layer in hardware, the state-of-the-art accelerator reduces the high computational complexity via the DeConv-to-Conv conversion and achieves the same results.
1 code implementation • ECCV 2018 • Siyeong Lee, Gwon Hwan An, Suk-Ju Kang
Because most images have a low dynamic range, recovering the lost dynamic range from a single low dynamic range image is still prevalent.
no code implementations • 19 Jan 2018 • Siyeong Lee, Gwon Hwan An, Suk-Ju Kang
The proposed model is based on a convolutional neural network composed of dilated convolutional layers, and infers LDR images with various exposures and illumination from a single LDR image of the same scene.