1 code implementation • ICCV 2023 • Jungsoo Lee, Debasmit Das, Jaegul Choo, Sungha Choi
To be more specific, entropy minimization attempts to raise the confidence values of an individual sample's prediction, but individual confidence values may rise or fall due to the influence of signals from numerous other predictions (i. e., wisdom of crowds).
no code implementations • CVPR 2023 • Seokeon Choi, Debasmit Das, Sungha Choi, Seunghan Yang, Hyunsin Park, Sungrack Yun
Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains.
1 code implementation • CVPR 2023 • Junha Song, Jungsoo Lee, In So Kweon, Sungha Choi
Second, our novel self-distilled regularization controls the output of the meta networks not to deviate significantly from the output of the frozen original networks, thereby preserving well-trained knowledge from the source domain.
no code implementations • 10 Feb 2023 • Hyesu Lim, Byeonggeun Kim, Jaegul Choo, Sungha Choi
In this paper, we identify that CBN and TBN are in a trade-off relationship and present a new test-time normalization (TTN) method that interpolates the statistics by adjusting the importance between CBN and TBN according to the domain-shift sensitivity of each BN layer.
no code implementations • 24 Jul 2022 • Sungha Choi, Seunghan Yang, Seokeon Choi, Sungrack Yun
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift between the source and target domains.
1 code implementation • ICCV 2021 • Sanghun Jung, Jungsoo Lee, Daehoon Gwak, Sungha Choi, Jaegul Choo
However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation.
Ranked #4 on Anomaly Detection on Lost and Found
2 code implementations • CVPR 2021 • Sungha Choi, Sanghun Jung, Huiwon Yun, Joanne Kim, Seungryong Kim, Jaegul Choo
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving.
Ranked #5 on Robust Object Detection on DWD
1 code implementation • arXiv.org 2020 • Seokwoo Jung, Sungha Choi, Mohammad Azam Khan, Jaegul Choo
This paper addresses the problem that pixel embedding in proposal-free instance segmentation based lane detection is difficult to optimize.
Ranked #10 on Lane Detection on TuSimple
1 code implementation • CVPR 2020 • Sungha Choi, Joanne T. Kim, Jaegul Choo
This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban-scene images.
Ranked #17 on Semantic Segmentation on Cityscapes test (using extra training data)
2 code implementations • CVPR 2019 • Wonwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo
However, applying this approach in image translation is computationally intensive and error-prone due to the expensive time complexity and its non-trivial backpropagation.