Search Results for author:
Found 15 papers, 9 papers with code
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
More precisely, we created dataset splits of HMDB-51 or UCF-101 for training, and Kinetics-400 for testing, using the subset of the classes that are overlapping in both train and test datasets.
Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months
We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date.
Development of a Deep Learning Method to Identify Acute Ischemic Stroke Lesions on Brain CT
DL methods can be designed for AIS lesion detection on CT using the vast quantities of routinely-collected CT brain scan data.
Challenges of building medical image datasets for development of deep learning software in stroke
Despite the large amount of brain CT data generated in clinical practice, the availability of CT datasets for deep learning (DL) research is currently limited.
ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging
We investigate the best way to generate the saliency maps employed in our architecture and propose a way to obtain them from adversarially generated counterfactual images.
Contrastive Meta-Learning for Partially Observable Few-Shot Learning
We evaluate our approach on an adaptation of a comprehensive few-shot learning benchmark, Meta-Dataset, and demonstrate the benefits of POEM over other meta-learning methods at representation learning from partial observations.
Defining Benchmarks for Continual Few-Shot Learning
Both few-shot and continual learning have seen substantial progress in the last years due to the introduction of proper benchmarks.
Meta-Learning in Neural Networks: A Survey
We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning.
Learning to Learn By Self-Critique
In this paper, we propose a framework called \emph{Self-Critique and Adapt} or SCA.
Learning to learn via Self-Critique
In this paper, we propose a framework called Self-Critique and Adapt or SCA, which learns to learn a label-free loss function, parameterized as a neural network.
Ranked #23 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available.
Data Augmentation
Unsupervised Few-Shot Image Classification
+1
Dilated DenseNets for Relational Reasoning
Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning.
How to train your MAML
The field of few-shot learning has recently seen substantial advancements.
CINIC-10 is not ImageNet or CIFAR-10
In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10.
Ranked #6 on
Image Classification
on CINIC-10
Data Augmentation Generative Adversarial Networks
The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and generalise it to generate other within-class data items.
