A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark · HackerPapers discussions

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark — mentioned by Datenstrom

Tue, 15 Feb 2022 20:08:10 GMT

While this is true there is also a lot of interesting research going on that makes model training and adaptation to new tasks much more efficient. For example in meta-learning methods like Model Agnostic Meta-Learning (MAML)[1] you learn a model that learns to initialize weights for another model such that it converges very quickly for a new task. For datasets benchmarking new task adaptation there are Meta-Dataset (MD)[2] for Meta-Learning, and the Visual Task Adaptation Benchmark (VTAB)[3] for Representation Learning. Recently to compare the two approaches VTAB+MD[4] was created. Of course…

Paper and discussion history. A mention is not an endorsement.

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark — mentioned by Datenstrom

Wed, 01 Sep 2021 13:56:05 GMT

Hey HN, We’re Mike, Mark, Patrick, and Derek of Emerald AI (emerald-ai.info), and we’re building a platform to clean, balance, and annotate data for rapidly deploying Computer Vision (CV) models. Unlike other data platforms that support vision data types, we do not assume that your data is ready for labeling. We provide tools to analyze, sort, arrange, and visualize your raw data, downselect to the most beneficial, and search for more underrepresented attributes and classes. We use a combination of active, bayesian, and meta-learning to make this possible with very little labeled data. We’ve…

Paper and discussion history. A mention is not an endorsement.