paper-with-me

홈 › Papers

Mobile-Former: Bridging MobileNet and Transformer

2021-08-12 · CVPR 2022 1 · Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Xiaoyi Dong, Lu Yuan, Zicheng Liu

We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Different from recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. 6 or fewer tokens) that are randomly initialized to learn global priors, resulting in low computational cost. Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power. It outperforms MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. For instance, Mobile-Former achieves 77.9\% top-1 accuracy at 294M FLOPs, gaining 1.3\% over MobileNetV3 but saving 17\% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP in RetinaNet framework. Furthermore, we build an efficient end-to-end detector by replacing backbone, encoder and decoder in DETR with Mobile-Former, which outperforms DETR by 1.1 AP but saves 52\% of computational cost and 36\% of parameters.

📄 PDF Abstract BibTeX arXiv:2108.05895

Code (4)

ACheun9/Pytorch-implementation-of-Mobile-Former pytorch
BR-IDL/PaddleViT paddle
aaboys/mobileformer pytorch
federicopozzi33/MobileOne-PyTorch pytorch

Tasks

Decoderobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 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…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
FPN 설명 없음
Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…
RetinaNet RetinaNet is a one-stage object detection model that utilizes a focal loss function to address class imbalance during training.…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Similar Papers 제목 키워드 기반

Rethinking Vision Transformers for MobileNet Size and Speed

2022-12-15 · ICCV 2023 1 · Yanyu Li, Ju Hu, Yang Wen, Georgios Evangelidis 외

With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are propos…

EfficientFormer: Vision Transformers at MobileNet Speed

2022-06-02 · Yanyu Li, Geng Yuan, Yang Wen, Ju Hu 외

Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \textit{e.g.}, attention…

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

2021-10-05 · ICLR 2022 4 · Sachin Mehta, Mohammad Rastegari

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However,…

Image Classificationobject-detectionObject Detection

MixMobileNet: A Mixed Mobile Network for Edge Vision Applications

2024-01-26 · Electronics 2024 1 · Yanju Meng, Peng Wu, Jian Feng, XiaoMing Zhang

Currently, vision transformers (ViTs) have rivaled comparable performance to convolutional neural networks (CNNs). However, the computational demands of the transformers’ self-attention mechanism pose challenges for thei…

image-classificationImage ClassificationInductive Biasobject-detection+1

Dynamic Mobile-Former: Strengthening Dynamic Convolution with Attention and Residual Connection in Kernel Space

2023-04-13 · Seokju Yun, Youngmin Ro

We introduce Dynamic Mobile-Former(DMF), maximizes the capabilities of dynamic convolution by harmonizing it with efficient operators.Our Dynamic MobileFormer effectively utilizes the advantages of Dynamic MobileNet (Mob…

image-classificationImage Classification