paper-with-me

홈 › Papers

Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search

2019-01-04 · Xiangxiang Chu, Bo Zhang, Ruijun Xu, Hailong Ma

Fabricating neural models for a wide range of mobile devices demands for a specific design of networks due to highly constrained resources. Both evolution algorithms (EA) and reinforced learning methods (RL) have been dedicated to solve neural architecture search problems. However, these combinations usually concentrate on a single objective such as the error rate of image classification. They also fail to harness the very benefits from both sides. In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and RL. In particular, we incorporate a variant of multi-objective genetic algorithm NSGA-II, in which the search space is composed of various cells so that crossovers and mutations can be performed at the cell level. Moreover, reinforced control is mixed with a natural mutating process to regulate arbitrary mutation, maintaining a delicate balance between exploration and exploitation. Therefore, not only does our method prevent the searched models from degrading during the evolution process, but it also makes better use of learned knowledge. Our experiments conducted in Super-resolution domain (SR) deliver rivalling models compared to some state-of-the-art methods with fewer FLOPS.

📄 PDF Abstract BibTeX arXiv:1901.01074

Code (4)

moremnas/MoreMNAS 공식 구현 tf
2023-MindSpore-1/ms-code-217/tree/main/sr_ea mindspore
2023-MindSpore-4/Code11/tree/main/sr_ea mindspore
2023-MindSpore-4/Code7/tree/main/sr_ea mindspore

Tasks

image-classificationImage ClassificationNeural Architecture SearchSuper-Resolution

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Reinforced Evolutionary Neural Architecture Search

2018-08-01 · Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang 외

Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption. To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search …

Neural Architecture SearchSemantic Segmentation

RENAS: Reinforced Evolutionary Neural Architecture Search

2019-06-01 · CVPR 2019 6 · Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang 외

Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption. To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search …

Neural Architecture SearchSemantic Segmentation

MobileCLIP2: Improving Multi-Modal Reinforced Training

2025-08-28 · Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar 외 arxiv

Foundation image-text models such as CLIP with zero-shot capabilities enable a wide array of applications. MobileCLIP is a recent family of image-text models at 3-15ms latency and 50-150M parameters with state-of-the-art…

Knowledge Distillation

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training

2023-11-28 · CVPR 2024 1 · Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli 외

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transfo…

Image CaptioningTransfer Learningzero-shot-classificationZero-Shot Learning

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

2022-11-05 · Haichao Zhang, Jiashi Li, Xin Xia, Kuangrong Hao 외

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the arc…

image-classificationImage ClassificationNeural Architecture SearchObject+2