no code implementations • 5 Dec 2023 • Yeji Song, Wonsik Shin, Junsoo Lee, Jeesoo Kim, Nojun Kwak
Finally, we decouple the motion from the appearance of the source video with an additional pseudo word.
1 code implementation • 23 Nov 2021 • Chaerin Kong, Jeesoo Kim, Donghoon Han, Nojun Kwak
Producing diverse and realistic images with generative models such as GANs typically requires large scale training with vast amount of images.
1 code implementation • ICCV 2021 • Jeesoo Kim, Junsuk Choe, Sangdoo Yun, Nojun Kwak
Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information.
2 code implementations • NeurIPS 2019 • Jisoo Jeong, Seungeui Lee, Jeesoo Kim, Nojun Kwak
Making a precise annotation in a large dataset is crucial to the performance of object detection.
Ranked #18 on Semi-Supervised Object Detection on COCO 2% labeled data
2 code implementations • ICCV 2019 • Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, Jin Young Choi
We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function.
Ranked #36 on Knowledge Distillation on ImageNet
no code implementations • 27 Sep 2018 • Jangho Kim, Jeesoo Kim, Nojun Kwak
The C-Net guarantees no degradation in the performance of the previously learned tasks and the H-Net shows high confidence in finding the origin of an input sample.
no code implementations • 7 Sep 2018 • Jangho Kim, Jeesoo Kim, Nojun Kwak
The StackNet guarantees no degradation in the performance of the previously learned tasks and the index module shows high confidence in finding the origin of an input sample.
no code implementations • 9 Jul 2018 • Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Daesik Kim, Nojun Kwak
Using a subnetwork based on a precedent work of image completion, our model makes the shape of an object.
no code implementations • CVPR 2018 • Daesik Kim, Youngjoon Yoo, Jeesoo Kim, Sangkuk Lee, Nojun Kwak
In this work, we introduce a new algorithm for analyzing a diagram, which contains visual and textual information in an abstract and integrated way.