Source-free domain adaptation (SFDA) is compelling because it allows ada...
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classi...
This paper introduces a generalized few-shot segmentation framework with...
Standard few-shot benchmarks are often built upon simplifying assumption...
We explore clustering the softmax predictions of deep neural networks an...
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classi...
Few-shot learning has recently attracted wide interest in image
classifi...
Transductive inference is widely used in few-shot learning, as it levera...
Mutual Information (MI) has been widely used as a loss regularizer for
t...
Training state-of-the-art vision models has become prohibitively expensi...
We introduce Transductive Infomation Maximization (TIM) for few-shot
lea...
Adversarial robustness has become a topic of growing interest in machine...
Few-shot segmentation has recently attracted substantial interest, with ...
We introduce Transductive Infomation Maximization (TIM) for few-shot
lea...