Research output per year
Research output per year
Personal profile
Research Interests
I primarily work on meta-learning, with applications to various problems including data-efficient learning, domain adaptation and uncertainty calibration. I have also worked on hyperparameter optimization, neural architecture search and deep learning more broadly. I usually work with image or text data.
Fingerprint
Dive into the research topics where Ondrej Bohdal is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Bohdal, O., Tian, Y., Zong, Y., Chavhan, R., Li, D., Gouk, H., Guo, L. & Hospedales, T., 22 Aug 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, p. 7693-7703 11 p. (Conference on Computer Vision and Pattern Recognition (CVPR)).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Bohdal, O., Balles, L., Wistuba, M., Ermis, B., Archambeau, C. & Zappella, G., 1 May 2023, The Eleventh International Conference on Learning Representations: ICLR 2023. p. 1-20Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open Access -
Label Calibration for Semantic Segmentation Under Domain Shift
Bohdal, O., Li, D. & Hospedales, T., 4 Mar 2023, ICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML. p. 1-6Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Fairness in AI and Its Long-Term Implications on Society
Bohdal, O., Hospedales, T., Torr, P. H. S. & Barez, F., 21 Jan 2023, (Accepted/In press) p. 1-13. 13 p.Research output: Contribution to conference › Paper › peer-review
Open AccessFile -
A Channel Coding Benchmark for Meta-Learning
Li, R., Bohdal, O., Mishra, R. K., Kim, H., Li, D., Lane, N. & Hospedales, T., 14 Dec 2021, Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. Vanschoren, J. & Yeung, S. (eds.). Curran Associates Inc, Vol. 1. 12 p. (Advances in Neural Information Processing Systems).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile