Papers Neural Network Compression
“Neural Network Compression” 태그가 달린 논문 216편 · 필터 해제
Forward and Backward Information Retention for Accurate Binary Neural Networks
Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accur…
BinarizationNeural Network CompressionQuantizationLearning Filter Basis for Convolutional Neural Network Compression
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these metho…
General Classificationimage-classificationImage ClassificationImage Super-Resolution+2DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for little loss of information. Whilst some of …
Neural Network CompressionQuantizationVideo CompressionSimilarity-Preserving Knowledge Distillation
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distil…
Knowledge DistillationNeural Network CompressionWeight Normalization based Quantization for Deep Neural Network Compression
With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quan…
Model CompressionNeural Network CompressionQuantizationCOP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level a…
Model CompressionNeural Network CompressionLearning Sparse Networks Using Targeted Dropout
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and t…
Network PruningNeural Network CompressionDeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression
We present DeepCABAC, a novel context-adaptive binary arithmetic coder for compressing deep neural networks. It quantizes each weight parameter by minimizing a weighted rate-distortion function, which implicitly takes th…
Neural Network CompressionQuantizationNETWORK COMPRESSION USING CORRELATION ANALYSIS OF LAYER RESPONSES
Principal Filter Analysis (PFA) is an easy to implement, yet effective method for neural network compression. PFA exploits the intrinsic correlation between filter responses within network layers to recommend a smaller n…
Domain AdaptationNeural Network CompressionSCANN: Synthesis of Compact and Accurate Neural Networks
Deep neural networks (DNNs) have become the driving force behind recent artificial intelligence (AI) research. An important problem with implementing a neural network is the design of its architecture. Typically, such an…
Dimensionality ReductionNeural Network CompressionSmall Data Image ClassificationCramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network
Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is bein…
Neural Network CompressionTransfer LearningData-Free Learning of Student Networks
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep n…
Neural Network CompressionOnline Multi-target regression trees with stacked leaf models
One of the current challenges in machine learning is how to deal with data coming at increasing rates in data streams. New predictive learning strategies are needed to cope with the high throughput data and concept drift…
Multi-target regressionNeural Network CompressionregressionMUSCO: Multi-Stage Compression of neural networks
The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selecti…
Neural Network CompressionCascaded Projection: End-to-End Network Compression and Acceleration
We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank…
Neural Network CompressionFocused Quantization for Sparse CNNs
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained de…
Model CompressionNeural Network CompressionQuantizationHardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
Many long short-term memory (LSTM) applications need fast yet compact models. Neural network compression approaches, such as the grow-and-prune paradigm, have proved to be promising for cutting down network complexity by…
Language ModelingLanguage ModellingNeural Network Compressionspeech-recognition+1Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
Quantization can improve the execution latency and energy efficiency of neural networks on both commodity GPUs and specialized accelerators. The majority of existing literature focuses on training quantized DNNs, while t…
Language ModelingLanguage ModellingNeural Network CompressionQuantizationDeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
DNNs have been quickly and broadly exploited to improve the data analysis quality in many complex science and engineering applications. Today's DNNs are becoming deeper and wider because of increasing demand on the analy…
Network PruningNeural Network CompressionEntropy-Constrained Training of Deep Neural Networks
We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measure…
Neural Network Compression