paper-with-me

홈 › Papers

Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution

2018-10-16 · Yue Lu, Yun Zhou, Zhuqing Jiang, Xiaoqiang Guo, Zixuan Yang

Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR). However, most CNN-based SR methods neglect the different importance among feature channels or fail to take full advantage of the hierarchical features. To address these issues, this paper presents a novel recursive unit. Firstly, at the beginning of each unit, we adopt a compact channel attention mechanism to adaptively recalibrate the channel importance of input features. Then, the multi-level features, rather than only deep-level features, are extracted and fused. Additionally, we find that it will force our model to learn more details by using the learnable upsampling method (i.e., transposed convolution) only on residual branch (instead of using it both on residual branch and identity branch) while using the bicubic interpolation on the other branch. Analytic experiments show that our method achieves competitive results compared with the state-of-the-art methods and maintains faster speed as well.

📄 PDF Abstract BibTeX arXiv:1810.06935

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Image Reconstruction of Multi Branch Feature Multiplexing Fusion Network with Mixed Multi-layer Attention

2022-05-27 · Yuxi Cai, Huicheng Lai

Image super-resolution reconstruction achieves better results than traditional methods with the help of the powerful nonlinear representation ability of convolution neural network. However, some existing algorithms also …

Image ReconstructionImage Super-ResolutionSuper-Resolution

Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features

2018-12-23 · Yingxue Xu, Guihua Wen, Yang Hu, Mingnan Luo 외

Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build the standard Chinese herbs datasets firstl…

Context-Guided Semantic Alignment for Feature Fusion Networks

2026-06-12 · Hyungseop Lee, Jiho Lee, Woochul Kang arxiv

Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes. However, directly fusing features from different pyramid levels often in…

Computational Efficiency

Differentiating Features for Scene Segmentation Based on Dedicated Attention Mechanisms

2019-11-19 · Zhiqiang Xiong, Zhicheng Wang, Zhaohui Yu, Xi Gu

Semantic segmentation is a challenge in scene parsing. It requires both context information and rich spatial information. In this paper, we differentiate features for scene segmentation based on dedicated attention mecha…

PositionScene ParsingScene SegmentationSemantic Segmentation

Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition

2026-08-03 · Guandi Wang, Ming Li, Yunsen Xing, Junle Liu arxiv

Deep multimodal fusion for object detection has demonstrated good performance through mining modal characteristics. However, existing feature-level fusion methods mainly weigh between two modalities and unify them in a u…

Object Detection