paper-with-me

홈 › Papers

Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search

2022-09-23 · Sławomir Kierat, Mateusz Sieniawski, Denys Fridman, Chen-Han Yu, Szymon Migacz, Paweł Morkisz, Alex-Fit Florea

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).

📄 PDF Abstract BibTeX arXiv:2209.11785

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationNeural Architecture Searchobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…
Batch Normalization 설명 없음
Sigmoid Activation 설명 없음
Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

2021-02-22 · Benjamin Hawks, Javier Duarte, Nicholas J. Fraser, Alessandro Pappalardo 외

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 SearchQuantization

Locality-Aware Redundancy Pruning for LLM Depth Compression

2026-05-27 · Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo 외 arxiv

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

2021-08-18 · ICCV 2021 10 · Zheng Zhan, Yifan Gong, Pu Zhao, Geng Yuan 외

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-Resolution

HAPM -- Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devices

2024-08-26 · Federico Nicolas Peccia, Luciano Ferreyro, Alejandro Furfaro

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…

Scheduling

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

2025-04-15 · Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Marcin Chochowski 외

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