Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search
We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over inner hidden dimensions with O(1) memory and compute complexity. Second, we present an algorithm for pruning blocks within a stochastic layer of the SuperNet during the search. Third, we describe a novel technique for pruning unnecessary stochastic layers during the search. The optimized models resulting from the search are called PruNet and establishes a new state-of-the-art Pareto frontier for NVIDIA V100 in terms of inference latency for ImageNet Top-1 image classification accuracy. PruNet as a backbone also outperforms GPUNet and EfficientNet on the COCO object detection task on inference latency relative to mean Average Precision (mAP).
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationNeural Architecture Searchobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference
Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumpti…
Bayesian OptimizationComputational EfficiencyNeural Architecture SearchQuantizationLocality-Aware Redundancy Pruning for LLM Depth Compression
Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local …
Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Though recent years have witnessed remarkable progress in single image super-resolution (SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep learning methods are confronted with the compu…
Image Super-ResolutionNeural Architecture SearchSSIMSuper-ResolutionHAPM -- Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devices
During the last years, algorithms known as Convolutional Neural Networks (CNNs) had become increasingly popular, expanding its application range to several areas. In particular, the image processing field has experienced…
SchedulingEfficient Hybrid Language Model Compression through Group-Aware SSM Pruning
Hybrid LLM architectures that combine Attention and State Space Models (SSMs) achieve state-of-the-art accuracy and runtime performance. Recent work has demonstrated that applying compression and distillation to Attentio…
Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression+1