Test-time adaptation (TTA) methods, which generally rely on the model's
...
Single domain generalization aims to train a generalizable model with on...
We present DejaVu, a novel framework which leverages conditional image
r...
Test-time adaptive (TTA) semantic segmentation adapts a source pre-train...
We consider the problem of improving the human instance segmentation mas...
Deep learning models for verification systems often fail to generalize t...
This paper presents a novel framework to integrate both semantic and ins...
In recent visual self-supervision works, an imitated classification
obje...
In this work, we propose a data-driven scheme to initialize the paramete...
In this paper, we extend the traditional few-shot learning (FSL) problem...
In this paper, we address the Online Unsupervised Domain Adaptation (OUD...
This paper proposes a multi-layer neural network structure for few-shot ...
Zero-shot learning (ZSL) for image classification focuses on recognizing...
Domain adaptation (DA) addresses the real-world image classification pro...
The assumption that training and testing samples are generated from the ...