In this paper, we address the few-shot classification task from a new perspective of optimal
matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to …

Recent work has shown how to embed differentiable optimization problems (that is,
problems whose solutions can be backpropagated through) as layers within deep learning …

Many meta-learning approaches for few-shot learning rely on simple base learners such as
nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained …

Data association across frames is at the core of Multiple Object Tracking (MOT) task. This
problem is usually solved by a traditional graph-based optimization or directly learned via …

This paper provides a tutorial overview of recent advances in learning control policy
representations for complex systems. We focus on control policies that are determined by …

Few-shot remote sensing scene classification (FSRSSC) is an important task, which aims to
recognize novel scene classes with few examples. Recently, several studies attempt to …

Optimization is a ubiquitous modeling tool and is often deployed in settings which
repeatedly solve similar instances of the same problem. Amortized optimization methods …

In this work, we develop methods for few-shot image classification from a new perspective of
optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as …

We present HUME, a simple model-agnostic framework for inferring human labeling of a
given dataset without any external supervision. The key insight behind our approach is that …

We scrutinise an important observation plaguing scene-level sketch research--that a
significant portion of scene sketches are" partial". A quick pilot study reveals:(i) a scene …