Search Results for author:
Found 6 papers, 2 papers with code
Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Instead, the bottleneck lies in the linear projection layers of multi-head attention and feedforward networks, constituting a substantial portion of the model size and contributing significantly to computation, memory, and power usage.
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Humans read and write hundreds of billions of messages every day.
Ranked #18 on
Question Answering
on Quora Question Pairs
Shallow Networks for High-Accuracy Road Object-Detection
The ability to automatically detect other vehicles on the road is vital to the safety of partially-autonomous and fully-autonomous vehicles.
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
(2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car.
Ranked #1 on
Image Classification
on ImageNet-P
FireCaffe: near-linear acceleration of deep neural network training on compute clusters
Therefore, the key consideration here is to reduce communication overhead wherever possible, while not degrading the accuracy of the DNN models that we train.
Ranked #955 on
Image Classification
on ImageNet
DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
Recently, there has been a flurry of industrial activity around logo recognition, such as Ditto's service for marketers to track their brands in user-generated images, and LogoGrab's mobile app platform for logo recognition.
Ranked #2 on
Object Detection
on FlickrLogos-32
