To address these challenges, this paper proposes a Lightweight Multi-scale Attention Feature Distillation Network (LMDN) for super-resolution reconstruction of digital rock images. The network consists of a Ligh
It achieves a PSNR of 24.26 dB and an SSIM of 0.8697 on the VIS dataset. Our work highlights the potential of attention-guided multi-scale feature fusion for lightweight passive NLOS imaging. The code is available at https://github.com/CS-wpf/LMS-NLOS....
The addition of these two attention mechanisms can effectively adjust the space and channel-wise information. In particular, group convolution is adopted in the SCAR block to further reduce the parameters. Additionally, a novel multi-scale feature attention (MSFA) module is designed to provide pixel...
It is a multi-scale feature fusion network (MFF-Metal) that captures effective feature representations through a feature fusion module and a multi-scale attention decoder. Moreover, a fusion loss function and soft label knowledge distillation are designed to improve performances while achieving light...
Secondly, based on a local cross-channel interaction strategy, a lightweight efficient channel attention mechanism (LECA) is designed. The kernel size of 1D convolution is affected by channel number and coefficients. Multi-scale feature input is used to retain more detailed features of different ...
MSDAN: A lightweight multi-scale distillation attention network for image super-resolution Environment in our experiments [python 3.8] [Ubuntu 20.04] BasicSR 1.4.2 PyTorch 1.13.0, Torchvision 0.14.0, Cuda 11.7 Installation git clone https://github.com/Supereeeee/MSDAN.git pip install -r require...
从图1可以看出,经过 \mathcal{F_{tr}} 操作输出的feature map分成了2支,其中一支是恒等映射,另一支经过了3个操作: \mathrm{F_{sq} (\cdot)} \rightarrow \mathrm{F_{ex} (\cdot, W)} \rightarrow \mathrm{F_{scale} (\cdot, \cdot)}。 在图2可以看的更清楚: \mathrm{F_{sq}(\cdot)} 指...
In order to improve the detection ability of small objects in complex backgrounds, such as drone aerial images, this paper proposes a lightweight small object detection network that introduces an attention mechanism based on the YOLOv4 network. First,
Finally, we design a lightweight multiscale feature extraction network, the PAN-CSP-Network. The newly designed network is named mini and lightweight YOLOv3 (ML-YOLOv3). Based on the helmet dataset, the FLPSs and parameter sizes of ML-YOLOv3 are only 29.7% and 29.4% of those of YOLOv3...
The feature extractor of our proposed model consists of three LMSAM modules that effectively extract multi-scale features. Additionally, an attention mechanism is introduced to assign varying weights to features of different scales in different channels. The label classifier consists of two convolutional...