Deepemd: Few-shot image classification with differentiable earth mover's distance and structured classifiers
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 …
matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to …
Differentiable convex optimization layers
Recent work has shown how to embed differentiable optimization problems (that is,
problems whose solutions can be backpropagated through) as layers within deep learning …
problems whose solutions can be backpropagated through) as layers within deep learning …
Meta-learning with differentiable convex optimization
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 …
nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained …
Learnable graph matching: Incorporating graph partitioning with deep feature learning for multiple object tracking
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 …
problem is usually solved by a traditional graph-based optimization or directly learned via …
A tutorial on derivative-free policy learning methods for interpretable controller representations
JA Paulson, F Sorourifar… - 2023 American Control …, 2023 - ieeexplore.ieee.org
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 …
representations for complex systems. We focus on control policies that are determined by …
SGMNet: Scene graph matching network for few-shot remote sensing scene classification
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 …
recognize novel scene classes with few examples. Recently, several studies attempt to …
Tutorial on amortized optimization
B Amos - Foundations and Trends® in Machine Learning, 2023 - nowpublishers.com
Optimization is a ubiquitous modeling tool and is often deployed in settings which
repeatedly solve similar instances of the same problem. Amortized optimization methods …
repeatedly solve similar instances of the same problem. Amortized optimization methods …
Deepemd: Differentiable earth mover's distance for few-shot learning
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 …
optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as …
The pursuit of human labeling: a new perspective on unsupervised learning
A Gadetsky, M Brbic - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …
given dataset without any external supervision. The key insight behind our approach is that …
Partially does it: Towards scene-level fg-sbir with partial input
PN Chowdhury, AK Bhunia… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …
significant portion of scene sketches are" partial". A quick pilot study reveals:(i) a scene …