Browse > Methodology > Quantization

Quantization

153 papers with code · Methodology

Leaderboards

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers with code

Near-Lossless Post-Training Quantization of Deep Neural Networks via a Piecewise Linear Approximation

31 Jan 2020jakc4103/piecewise-quantization

Quantization plays an important role for energy-efficient deployment of deep neural networks (DNNs) on resource-limited devices.

IMAGE CLASSIFICATION OBJECT DETECTION QUANTIZATION SEMANTIC SEGMENTATION

1
31 Jan 2020

Deep Optimized Multiple Description Image Coding via Scalar Quantization Learning

12 Jan 2020mdcnn/Deep-Multiple-Description-Coding

In this paper, we introduce a deep multiple description coding (MDC) framework optimized by minimizing multiple description (MD) compressive loss.

QUANTIZATION

1
12 Jan 2020

Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers

12 Jan 2020SITE5039/AgrLearn

We show that IB learning is, in fact, equivalent to a special class of the quantization problem.

QUANTIZATION REPRESENTATION LEARNING TEXT CLASSIFICATION

1
12 Jan 2020

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

3 Jan 2020Torment123/DFS

The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate "soft" choices to be made between fully utilizing and skipping a layer.

QUANTIZATION

5
03 Jan 2020

ZeroQ: A Novel Zero Shot Quantization Framework

1 Jan 2020amirgholami/ZeroQ

Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0. 5\% of one epoch training time of ResNet50 on ImageNet).

QUANTIZATION

45
01 Jan 2020

LEARNED STEP SIZE QUANTIZATION

ICLR 2020 hustzxd/LSQuantization

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases.

QUANTIZATION

11
01 Jan 2020

Towards Efficient Training for Neural Network Quantization

21 Dec 2019jakc4103/scale-adjusted-training

To deal with this problem, we propose a simple yet effective technique, named scale-adjusted training (SAT), to comply with the discovered rules and facilitates efficient training.

QUANTIZATION

2
21 Dec 2019

MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization

NeurIPS 2019 csyhhu/MetaQuant

However, these methods only heuristically make training-based quantization applicable, without further analysis on how the approximated gradients can assist training of a quantized network.

QUANTIZATION

24
01 Dec 2019

Coresets for Archetypal Analysis

NeurIPS 2019 smair/archetypalanalysis-coreset

Archetypal analysis represents instances as linear mixtures of prototypes (the archetypes) that lie on the boundary of the convex hull of the data.

QUANTIZATION

1
01 Dec 2019

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

27 Nov 2019skhobahi/deep1bitVAE

Parameterized mathematical models play a central role in understanding and design of complex information systems.

QUANTIZATION

1
27 Nov 2019