Two prevalent types of distributional shifts in machine learning are the...
In this paper, we introduce audio-visual class-incremental learning, a
c...
Given an image set without any labels, our goal is to train a model that...
We introduce a novel robotic system for improving unseen object instance...
Unsupervised lifelong learning refers to the ability to learn over time ...
Unsupervised semantic segmentation aims to discover groupings within and...
Hyperbolic space can embed tree metric with little distortion, a desirab...
Non-Euclidean geometry with constant negative curvature, i.e., hyperboli...
Recent progress on few-shot learning has largely re-lied on annotated da...
There is an increasing number of pre-trained deep neural network models....
Current deep neural networks can achieve remarkable performance on a sin...
There is a growing interest in designing models that can deal with image...
Transfer learning, which allows a source task to affect the inductive bi...
Deep neural networks are the state-of-the-art methods for many real-worl...