paper-with-me

홈 › Papers

ScaleNet: Searching for the Model to Scale

2022-07-15 · Jiyang Xie, Xiu Su, Shan You, Zhanyu Ma, Fei Wang, Chen Qian

Recently, community has paid increasing attention on model scaling and contributed to developing a model family with a wide spectrum of scales. Current methods either simply resort to a one-shot NAS manner to construct a non-structural and non-scalable model family or rely on a manual yet fixed scaling strategy to scale an unnecessarily best base model. In this paper, we bridge both two components and propose ScaleNet to jointly search base model and scaling strategy so that the scaled large model can have more promising performance. Concretely, we design a super-supernet to embody models with different spectrum of sizes (e.g., FLOPs). Then, the scaling strategy can be learned interactively with the base model via a Markov chain-based evolution algorithm and generalized to develop even larger models. To obtain a decent super-supernet, we design a hierarchical sampling strategy to enhance its training sufficiency and alleviate the disturbance. Experimental results show our scaled networks enjoy significant performance superiority on various FLOPs, but with at least 2.53x reduction on search cost. Codes are available at https://github.com/luminolx/ScaleNet.

📄 PDF Abstract BibTeX arXiv:2207.07267

Code (1)

luminolx/scalenet 공식 구현 pytorch

Tasks

model

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 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…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

2020-11-30 · Hsin-Pai Cheng, Feng Liang, Meng Li, Bowen Cheng 외

Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neural architecture Search(NAS) for each tas…

Multi-Person Pose EstimationNeural Architecture SearchOne-Shot LearningPose Estimation+1

ScaleNet: A Shallow Architecture for Scale Estimation

2021-12-09 · CVPR 2022 1 · Axel Barroso-Laguna, Yurun Tian, Krystian Mikolajczyk

In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, …

3D ReconstructionCamera Pose EstimationGeometric MatchingPose Estimation

ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters

2025-10-21 · Zhiwei Hao, Jianyuan Guo, Li Shen, Kai Han 외 arxiv

Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally intensive and costly. To address this chal…

Image ClassificationObject Detection

ScaleNet: An Unsupervised Representation Learning Method for Limited Information

2023-10-03 · Huili Huang, M. Mahdi Roozbahani

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-sc…

Representation Learning

EcoScaleNet: A Lightweight Multi Kernel Network for Long Sequence 12 lead ECG Classification

2025-10-16 · Dong-Hyeon Kang, Ju-Hyeon Nam, Sang-Chul Lee arxiv

Accurate interpretation of 12 lead electrocardiograms (ECGs) is critical for early detection of cardiac abnormalities, yet manual reading is error prone and existing CNN based classifiers struggle to choose receptive fie…

ECG Classification