A review of binarized neural networks
T Simons, DJ Lee - Electronics, 2019 - mdpi.com
In this work, we review Binarized Neural Networks (BNNs). BNNs are deep neural networks
that use binary values for activations and weights, instead of full precision values. With …
that use binary values for activations and weights, instead of full precision values. With …
End-edge-cloud collaborative computing for deep learning: A comprehensive survey
The booming development of deep learning applications and services heavily relies on
large deep learning models and massive data in the cloud. However, cloud-based deep …
large deep learning models and massive data in the cloud. However, cloud-based deep …
Knowledge distillation: A survey
In recent years, deep neural networks have been successful in both industry and academia,
especially for computer vision tasks. The great success of deep learning is mainly due to its …
especially for computer vision tasks. The great success of deep learning is mainly due to its …
Binary neural networks: A survey
The binary neural network, largely saving the storage and computation, serves as a
promising technique for deploying deep models on resource-limited devices. However, the …
promising technique for deploying deep models on resource-limited devices. However, the …
Structured knowledge distillation for semantic segmentation
In this paper, we investigate the issue of knowledge distillation for training compact semantic
segmentation networks by making use of cumbersome networks. We start from the …
segmentation networks by making use of cumbersome networks. We start from the …
Relational knowledge distillation
Abstract Knowledge distillation aims at transferring knowledge acquired in one model (a
teacher) to another model (a student) that is typically smaller. Previous approaches can be …
teacher) to another model (a student) that is typically smaller. Previous approaches can be …
A survey of model compression and acceleration for deep neural networks
Deep neural networks (DNNs) have recently achieved great success in many visual
recognition tasks. However, existing deep neural network models are computationally …
recognition tasks. However, existing deep neural network models are computationally …
Distilling object detectors with fine-grained feature imitation
State-of-the-art CNN based recognition models are often computationally prohibitive to
deploy on low-end devices. A promising high level approach tackling this limitation is …
deploy on low-end devices. A promising high level approach tackling this limitation is …
Alignedreid: Surpassing human-level performance in person re-identification
In this paper, we propose a novel method called AlignedReID that extracts a global feature
which is jointly learned with local features. Global feature learning benefits greatly from local …
which is jointly learned with local features. Global feature learning benefits greatly from local …
A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking
MS Sarfraz, A Schumann, A Eberle… - Proceedings of the …, 2018 - openaccess.thecvf.com
Person re-identification is a challenging retrieval task that requires matching a person's
acquired image across non-overlapping camera views. In this paper we propose an effective …
acquired image across non-overlapping camera views. In this paper we propose an effective …