Search Results for author:
Found 6 papers, 1 papers with code
Dense Pruning of Pointwise Convolutions in the Frequency Domain
Our key insights are that 1) pointwise convolutions commute with frequency transformation and thus can be computed in the frequency domain without modification, 2) each channel within a given layer has a different level of sensitivity to frequency domain pruning, and 3) each channel's sensitivity to frequency pruning is approximately monotonic with respect to frequency.
Optimizing JPEG Quantization for Classification Networks
While a long history of work has sought better Q-tables, existing work either seeks to minimize image distortion or to optimize for models of the human visual system.
EVA$^2$: Exploiting Temporal Redundancy in Live Computer Vision
Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices.
High Five: Improving Gesture Recognition by Embracing Uncertainty
We introduce a new statistical quantization approach that mitigates these problems by (1) during training, producing gesture-specific codebooks, HMMs, and error models for gesture sequences; and (2) during classification, exploiting the error model to explore multiple feasible HMM state sequences.
Abstractions for AI-Based User Interfaces and Systems
We propose to treat these challenges as language-design problems.
Reconfiguring the Imaging Pipeline for Computer Vision
We propose a new image sensor design that can compensate for skipping these stages.
