Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table
By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant functions face the issue of how to represent originally high-bit input data with low-bit values. To fully quantize deep neural networks, we propose pixel embedding, which replaces each float-valued input pixel with a vector of quantized values by using a lookup table. The lookup table or low-bit representation of pixels is differentiable and trainable by backpropagation. Such replacement of inputs with vectors is similar to word embedding in the natural language processing field. Experiments on ImageNet and CIFAR-100 show that pixel embedding reduces the top-5 error gap caused by quantizing the floating points at the first layer to only 1% for the ImageNet dataset, and the top-1 error gap caused by quantizing first and last layers to slightly over 1% for the CIFAR-100 dataset. The usefulness of pixel embedding is further demonstrated by inference time measurements, which demonstrate over 1.7 times speedup compared to floating point precision first layer.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of t…
Face ParsingSD-$π$XL: Generating Low-Resolution Quantized Imagery via Score Distillation
Low-resolution quantized imagery, such as pixel art, is seeing a revival in modern applications ranging from video game graphics to digital design and fabrication, where creativity is often bound by a limited palette of …
Region-based semantic segmentation with end-to-end training
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region clas…
SegmentationSemantic SegmentationSemantic Instance Segmentation via Deep Metric Learning
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together. Our similarity metric is based on a dee…
Instance SegmentationMetric LearningObject Proposal GenerationSegmentation+1Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and …
Edge-computingQuantization