no code implementations • 12 May 2023 • Minjae Lee, Seongmin Park, Hyungmin Kim, Minyong Yoon, Janghwan Lee, Jun Won Choi, Nam Sung Kim, Mingu Kang, Jungwook Choi
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements.
no code implementations • CVPR 2023 • Mingu Kang, Heon Song, Seonwook Park, Donggeun Yoo, Sérgio Pereira
To address this need, we execute the largest-scale study of SSL pre-training on pathology image data, to date.
no code implementations • 1 Sep 2022 • Amir Yazdanbakhsh, Ashkan Moradifirouzabadi, Zheng Li, Mingu Kang
The combined in-memory pruning and on-chip recompute of the relevant attention scores enables SPRINT to transform quadratic complexity to a merely linear one.
no code implementations • 7 Apr 2022 • Zheng Li, Soroush Ghodrati, Amir Yazdanbakhsh, Hadi Esmaeilzadeh, Mingu Kang
To best utilize this mathematical innovation, we devise a bit-serial architecture, dubbed LeOPArd, for transformer language models with bit-level early termination microarchitectural mechanism.
no code implementations • 9 Oct 2021 • Trung Q. Tran, Mingu Kang, Daeyoung Kim
Semi-supervised learning (SSL) has played an important role in leveraging unlabeled data when labeled data is limited.
no code implementations • 15 Feb 2021 • Mingu Kang, Trung Quang Tran, Seungju Cho, Daeyoung Kim
Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation.
no code implementations • 12 Feb 2021 • Trung Quang Tran, Mingu Kang, Daeyoung Kim
We obtain promising results (4. 21% error rate on CIFAR-10 with 4000 labels, 22. 32% error rate on CIFAR-100 with 10000 labels, and 2. 19% error rate on SVHN with 1000 labels) when the amount of labeled data is sufficient to learn semantics-oriented similarity representation.
no code implementations • 28 Feb 2020 • Seungju Cho, Tae Joon Jun, Mingu Kang, Daeyoung Kim
However, it turns out a deep learning based model is highly vulnerable to some small perturbation called an adversarial attack.