paper-with-me

Papers

Rethinking Channel Dimensions for Efficient Model Design

2020-07-02 · CVPR 2021 1 · Dongyoon Han, Sangdoo Yun, Byeongho Heo, Youngjoon Yoo

Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like a piecewise linear function of the network stage. In this paper, we study an effective channel dimension configuration towards better performance than the convention. To this end, we empirically study how to design a single layer properly by analyzing the rank of the output feature. We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction. Based on the investigation, we propose a simple yet effective channel configuration that can be parameterized by the layer index. As a result, our proposed model following the channel parameterization achieves remarkable performance on ImageNet classification and transfer learning tasks including COCO object detection, COCO instance segmentation, and fine-grained classifications. Code and ImageNet pretrained models are available at https://github.com/clovaai/rexnet.

📄 PDF Abstract BibTeX arXiv:2007.00992

Code (10)

clovaai/rexnet 공식 구현 pytorch
2023-MindSpore-1/ms-code-34 mindspore
MS-Mind/MS-Code-02/tree/main/configs/rexnet mindspore
PaddlePaddle/PaddleClas paddle
YeongHyeon/ReXNet-TF2 tf
alexwitt2399/rexnet pytorch
lyqcom/rexnet mindspore
mindspore-ecosystem/mindcv/blob/main/mindcv/models/rexnet.py mindspore
paperswithcode/model-index pytorch
ysbsb/ReXNet-PyTorch pytorch

Tasks

Image ClassificationInstance Segmentationmodelobject-detectionObject DetectionSemantic SegmentationTransfer Learning

Similar Papers 제목 키워드 기반

Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising

2024-04-11 · Junyi Li, Zhilu Zhang, WangMeng Zuo

Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potent…

Computational EfficiencyDenoisingImage DenoisingImage Restoration+1

Rethinking Spatial Dimensions of Vision Transformers

2021-03-30 · ICCV 2021 10 · Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun 외

Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Sinc…

Dimensionality Reductionimage-classificationImage Classificationobject-detection+1

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

2023-09-27 · Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim 외

Large Language Models (LLMs) have recently demonstrated remarkable success across various tasks. However, efficiently serving LLMs has been a challenge due to the large memory bottleneck, specifically in small batch infe…

HumanEvalLanguage ModelingLanguage ModellingMMLU+1

Flexible Channel Dimensions for Differentiable Architecture Search

2023-06-13 · Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

Finding optimal channel dimensions (i.e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints. Recent work in neural architecture search aims at aut…

GPUNeural Architecture Search

Rethinking Gradient Operator for Exposing AI-enabled Face Forgeries

2022-05-02 · Zhiqing Guo, Gaobo Yang, Dengyong Zhang, Ming Xia

For image forensics, convolutional neural networks (CNNs) tend to learn content features rather than subtle manipulation traces, which limits forensic performance. Existing methods predominantly solve the above challenge…

Image Forensics