1 code implementation • 15 Jul 2024 • Jae Myung Kim, Jessica Bader, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
While text-to-image diffusion models have been shown to achieve state-of-the-art results in image synthesis, they have yet to prove their effectiveness in downstream applications.
1 code implementation • 2 May 2024 • Nishad Singhi, Jae Myung Kim, Karsten Roth, Zeynep Akata
In this paper, we find that this is noticeably driven by an independent treatment of concepts during intervention, wherein a change of one concept does not influence the use of other ones in the model's final decision.
2 code implementations • ICCV 2023 • Karsten Roth, Jae Myung Kim, A. Sophia Koepke, Oriol Vinyals, Cordelia Schmid, Zeynep Akata
The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3.
no code implementations • 6 Apr 2023 • Jae Myung Kim, A. Sophia Koepke, Cordelia Schmid, Zeynep Akata
In this work, we introduce ODmAP@k, an object decorrelation metric that measures a model's robustness to spurious correlations in the training data.
2 code implementations • CVPR 2023 • Youngwook Kim, Jae Myung Kim, Jieun Jeong, Cordelia Schmid, Zeynep Akata, Jungwoo Lee
Based on these findings, we propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
no code implementations • 21 Feb 2023 • Uddeshya Upadhyay, Jae Myung Kim, Cordelia Schmidt, Bernhard Schölkopf, Zeynep Akata
Recent advances in deep learning have shown that uncertainty estimation is becoming increasingly important in applications such as medical imaging, natural language processing, and autonomous systems.
1 code implementation • CVPR 2022 • Youngwook Kim, Jae Myung Kim, Zeynep Akata, Jungwoo Lee
In this work, we first regard unobserved labels as negative labels, casting the WSML task into noisy multi-label classification.
no code implementations • 29 Sep 2021 • Hyungjun Joo, Seokhyeon Ha, Jae Myung Kim, Sungyeob Han, Jungwoo Lee
As deep learning has been successfully deployed in diverse applications, there is ever increasing need for explaining its decision.
no code implementations • 29 Sep 2021 • Jae Myung Kim, Eunji Kim, Sungroh Yoon, Jungwoo Lee, Cordelia Schmid, Zeynep Akata
Explaining a complex black-box system in a post-hoc manner is important to understand its predictions.
no code implementations • 29 Sep 2021 • Jaehak Cho, Jae Myung Kim, Sungyeob Han, Jungwoo Lee
To address the issue, we propose a novel method that generates a union of disjoint PIs.
1 code implementation • ICCV 2021 • Jae Myung Kim, Junsuk Choe, Zeynep Akata, Seong Joon Oh
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks.
no code implementations • 1 Jan 2021 • Jae Myung Kim, Eunji Kim, Seokhyeon Ha, Sungroh Yoon, Jungwoo Lee
Saliency maps have been widely used to explain the behavior of an image classifier.
no code implementations • 16 Feb 2020 • Jae Myung Kim, Hyungjin Kim, Chanwoo Park, Jungwoo Lee
Our work aims to improve the robustness by adding a REST module in front of any black boxes and training only the REST module without retraining the original black box model in an end-to-end manner, i. e. we try to convert the real-world data into training distribution which the performance of the black-box model is best suited for.
1 code implementation • 17 Sep 2019 • Woojin Jung, Jaeyeon Yoon, Joon Yul Choi, Jae Myung Kim, Yoonho Nam, Eung Yeop Kim, Jong-Ho Lee
To overcome this limitation, a data augmentation method is proposed to generalize the network for a wider range of susceptibility.
Image and Video Processing
no code implementations • 8 Dec 2018 • Chanwoo Park, Jae Myung Kim, Seok Hyeon Ha, Jungwoo Lee
In this paper, we show that predictive uncertainty can be efficiently estimated when we incorporate the concept of gradients uncertainty into posterior sampling.