Measuring the Interpretability of Unsupervised Representations via
Quantized Reverse Probing

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

International Conference on Learning Representations (ICLR), 2022

7 September 2022

Andrea Vedaldi

ArXiv (abs)PDF HTML Github (6★)

Papers citing "Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing"

6 / 6 papers shown

Title
LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision Mateusz Pach Dawid Rymarczyk K. Lewandowska Jacek Tabor Bartosz Zieliñski 223 11 0 23 May 2024
FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks Hamed Behzadi-Khormouji José Oramas 144 0 0 17 May 2023
Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail DataInternational Conference on Learning Representations (ICLR), 2023 Anna Kukleva Moritz Bohle Bernt Schiele Hilde Kuehne Christian Rupprecht 236 57 0 23 Mar 2023
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Mathilde Caron Ishan Misra Julien Mairal Priya Goyal Piotr Bojanowski Armand Joulin OCL SSL 1.1K 4,620 0 17 Jun 2020
ClusterFit: Improving Generalization of Visual RepresentationsComputer Vision and Pattern Recognition (CVPR), 2019 Xueting Yan Ishan Misra Abhinav Gupta Deepti Ghadiyaram D. Mahajan SSL VLM 244 136 0 06 Dec 2019
Billion-scale similarity search with GPUsIEEE Transactions on Big Data (TBD), 2017 Jeff Johnson Matthijs Douze Edouard Grave 881 4,423 0 28 Feb 2017