1 citations · 2 across the 4 of their papers we have counts for
4 papers · 1 filter
Dense Pruning of Pointwise Convolutions in the Frequency Domain
Mark Buckler, Neil Adit, Yuwei Hu +2
Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the v…
Optimizing JPEG Quantization for Classification Networks
Zhijing Li, Christopher De Sa, Adrian Sampson
Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream…
EVA: Exploiting Temporal Redundancy in Live Computer Vision
Mark Buckler, Philip Bedoukian, Suren Jayasuriya +1
Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic…
High Five: Improving Gesture Recognition by Embracing Uncertainty
Diman Zad Tootaghaj, Adrian Sampson, Todd Mytkowicz +1
Sensors on mobile devices---accelerometers, gyroscopes, pressure meters, and GPS---invite new applications in gesture recognition, gaming, and fitness tracking. However, programmin…