Joint unsupervised learning of deep representations and image clusters
In this paper, we propose a recurrent framework for joint unsupervised learning of deep
representations and image clusters. In our framework, successive operations in a clustering …
representations and image clusters. In our framework, successive operations in a clustering …
Unsupervised visual representation learning by context prediction
This work explores the use of spatial context as a source of free and plentiful supervisory
signal for training a rich visual representation. Given only a large, unlabeled image …
signal for training a rich visual representation. Given only a large, unlabeled image …
Visual explanation by interpretation: Improving visual feedback capabilities of deep neural networks
Interpretation and explanation of deep models is critical towards wide adoption of systems
that rely on them. In this paper, we propose a novel scheme for both interpretation as well as …
that rely on them. In this paper, we propose a novel scheme for both interpretation as well as …
Prototype-based dataset comparison
N Van Noord - Proceedings of the IEEE/CVF International …, 2023 - openaccess.thecvf.com
Dataset summarisation is a fruitful approach to dataset inspection. However, when applied
to a single dataset the discovery of visual concepts is restricted to those most prominent. We …
to a single dataset the discovery of visual concepts is restricted to those most prominent. We …
Mining mid-level visual patterns with deep CNN activations
The purpose of mid-level visual element discovery is to find clusters of image patches that
are representative of, and which discriminate between, the contents of the relevant images …
are representative of, and which discriminate between, the contents of the relevant images …
Deepcamp: Deep convolutional action & attribute mid-level patterns
The recognition of human actions and the determination of human attributes are two tasks
that call for fine-grained classification. Indeed, often rather small and inconspicuous objects …
that call for fine-grained classification. Indeed, often rather small and inconspicuous objects …
Object discovery from a single unlabeled image by mining frequent itemsets with multi-scale features
The goal of our work is to discover dominant objects in a very general setting where only a
single unlabeled image is given. This is far more challenge than typical co-localization or …
single unlabeled image is given. This is far more challenge than typical co-localization or …
EmerGPU: Understanding and mitigating resonance-induced voltage noise in GPU architectures
R Thomas, N Sedaghati… - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
This paper characterizes voltage noise in GPU architectures running general purpose
workloads. In particular, it focuses on resonance-induced voltage noise, which is caused by …
workloads. In particular, it focuses on resonance-induced voltage noise, which is caused by …
Unsupervised part mining for fine-grained image classification
Fine-grained image classification remains challenging due to the large intra-class variance
and small inter-class variance. Since the subtle visual differences are only in local regions of …
and small inter-class variance. Since the subtle visual differences are only in local regions of …
Unsupervised category discovery via looped deep pseudo-task optimization using a large scale radiology image database
Obtaining semantic labels on a large scale radiology image database (215,786 key images
from 61,845 unique patients) is a prerequisite yet bottleneck to train highly effective deep …
from 61,845 unique patients) is a prerequisite yet bottleneck to train highly effective deep …