Research output per year
Research output per year
Personal profile
Research Interests
I undertake machine learning research that bridges the gap between theory and practice, with the goal of making systems that depend on machine learning more reliable.
Fingerprint
Dive into the research topics where Henry Gouk is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Network
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., 27 Feb 2023, (Accepted/In press) 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 18 p. (Conference on Computer Vision and Pattern Recognition (CVPR)).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Why Do Self-Supervised Models Transfer? On the Impact of Invariance on Downstream Tasks
Ericsson, L., Gouk, H. & Hospedales, T., 25 Nov 2022, Proceedings of the 33rd British Machine Vision Conference 2022, (BMVC 2022). BMVA Press, 14 p. 509Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Loss Function Learning for Domain Generalization by Implicit Gradient
Gao, B., Gouk, H., Yang, Y. & Hospedales, T. M., 30 May 2022, (Accepted/In press) Proceedings of the 39th International Conference on Machine Learning. 15 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Self-Supervised Representation Learning: Introduction, advances, and challenges
Ericsson, L., Gouk, H., Loy, C. C. & Hospedales, T. M., 6 May 2022, In: IEEE Signal Processing Magazine. 39, 3, p. 42-62 21 p.Research output: Contribution to journal › Article › peer-review
Open AccessFile -
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
El Baz, A., Ullah, I., Alcobaça, E., Carvalho, A. C. P. L. F., Chen, H., Ferreira, F., Gouk, H., Guan, C., Guyon, I., Hospedales, T., Hu, S., Huisman, M., Hutter, F., Liu, Z., Mohr, F., Oztürk, E., van Rijn, J. N., Sun, H., Wang, X. & Zhu, W., 10 Apr 2022, (Accepted/In press) Proceedings of the NeurIPS 2021 Competition and Demonstration Track. Kiela, D., Caputo, B. & Ciccone, M. (eds.). PMLR, Vol. 176. p. 80-96 17 p. (Proceedings of Machine Learning Research; vol. 176).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile