Compact Twice Fusion Network for Edge Detection
- URL: http://arxiv.org/abs/2307.04952v1
- Date: Tue, 11 Jul 2023 00:46:59 GMT
- Title: Compact Twice Fusion Network for Edge Detection
- Authors: Yachuan Li, Zongmin Li, Xavier Soria P., Chaozhi Yang, Qian Xiao, Yun
Bai, Hua Li, Xiangdong Wang
- Abstract summary: The significance of multi-scale features has been gradually recognized by the edge detection community.
We propose a Compact Twice Fusion Network (CTFN) to fully integrate multi-scale features.
CTFN includes two lightweight multi-scale feature fusion modules.
- Score: 5.379716918698048
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: The significance of multi-scale features has been gradually recognized by the
edge detection community. However, the fusion of multi-scale features increases
the complexity of the model, which is not friendly to practical application. In
this work, we propose a Compact Twice Fusion Network (CTFN) to fully integrate
multi-scale features while maintaining the compactness of the model. CTFN
includes two lightweight multi-scale feature fusion modules: a Semantic
Enhancement Module (SEM) that can utilize the semantic information contained in
coarse-scale features to guide the learning of fine-scale features, and a
Pseudo Pixel-level Weighting (PPW) module that aggregate the complementary
merits of multi-scale features by assigning weights to all features.
Notwithstanding all this, the interference of texture noise makes the correct
classification of some pixels still a challenge. For these hard samples, we
propose a novel loss function, coined Dynamic Focal Loss, which reshapes the
standard cross-entropy loss and dynamically adjusts the weights to correct the
distribution of hard samples. We evaluate our method on three datasets, i.e.,
BSDS500, NYUDv2, and BIPEDv2. Compared with state-of-the-art methods, CTFN
achieves competitive accuracy with less parameters and computational cost.
Apart from the backbone, CTFN requires only 0.1M additional parameters, which
reduces its computation cost to just 60% of other state-of-the-art methods. The
codes are available at https://github.com/Li-yachuan/CTFN-pytorch-master.
Related papers
- FuseFormer: A Transformer for Visual and Thermal Image Fusion [3.6064695344878093]
We propose a novel methodology for the image fusion problem that mitigates the limitations associated with using classical evaluation metrics as loss functions.
Our approach integrates a transformer-based multi-scale fusion strategy that adeptly addresses local and global context information.
Our proposed method, along with the novel loss function definition, demonstrates superior performance compared to other competitive fusion algorithms.
arXiv Detail & Related papers (2024-02-01T19:40:39Z) - Dual-scale Enhanced and Cross-generative Consistency Learning for
Semi-supervised Polyp Segmentation [52.06525450636897]
Automatic polyp segmentation plays a crucial role in the early diagnosis and treatment of colorectal cancer.
Existing methods rely heavily on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations.
We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised polyp (DEC-Seg) from colonoscopy images.
arXiv Detail & Related papers (2023-12-26T12:56:31Z) - Mutual-Guided Dynamic Network for Image Fusion [51.615598671899335]
We propose a novel mutual-guided dynamic network (MGDN) for image fusion, which allows for effective information utilization across different locations and inputs.
Experimental results on five benchmark datasets demonstrate that our proposed method outperforms existing methods on four image fusion tasks.
arXiv Detail & Related papers (2023-08-24T03:50:37Z) - CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for
Multi-Modality Image Fusion [138.40422469153145]
We propose a novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network.
We show that CDDFuse achieves promising results in multiple fusion tasks, including infrared-visible image fusion and medical image fusion.
arXiv Detail & Related papers (2022-11-26T02:40:28Z) - MODNet: Multi-offset Point Cloud Denoising Network Customized for
Multi-scale Patches [14.078359217301973]
We propose a Multi-offset Denoising Network (MODNet) customized for multi-scale patches.
A multi-scale perception module is designed to embed multi-scale geometric information for each scale feature.
Experiments demonstrate that our method achieves new state-of-the-art performance on both synthetic and real-scanned datasets.
arXiv Detail & Related papers (2022-08-30T11:21:39Z) - BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
We develop a new point cloud upsampling pipeline called BIMS-PU.
We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors.
We show that our method achieves superior results to state-of-the-art approaches.
arXiv Detail & Related papers (2022-06-25T13:13:37Z) - Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation
for Reference-based Super-Resolution [48.093500219958834]
We propose an Accelerated Multi-Scale Aggregation network (AMSA) for Reference-based Super-Resolution.
The proposed AMSA achieves superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.
arXiv Detail & Related papers (2022-01-12T08:40:23Z) - Learning Robust and Lightweight Model through Separable Structured
Transformations [13.208781763887947]
We propose a separable structural transformation of the fully-connected layer to reduce the parameters of convolutional neural networks.
We successfully reduce the amount of network parameters by 90%, while the robust accuracy loss is less than 1.5%.
We evaluate the proposed approach on datasets such as ImageNet, SVHN, CIFAR-100 and Vision Transformer.
arXiv Detail & Related papers (2021-12-27T07:25:26Z) - EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object
Detection [56.03081616213012]
We propose EPNet++ for multi-modal 3D object detection by introducing a novel Cascade Bi-directional Fusion(CB-Fusion) module.
The proposed CB-Fusion module boosts the plentiful semantic information of point features with the image features in a cascade bi-directional interaction fusion manner.
The experiment results on the KITTI, JRDB and SUN-RGBD datasets demonstrate the superiority of EPNet++ over the state-of-the-art methods.
arXiv Detail & Related papers (2021-12-21T10:48:34Z) - CE-FPN: Enhancing Channel Information for Object Detection [12.954675966833372]
Feature pyramid network (FPN) has been an effective framework to extract multi-scale features in object detection.
We present a novel channel enhancement network (CE-FPN) with three simple yet effective modules to alleviate these problems.
Our experiments show that CE-FPN achieves competitive performance compared to state-of-the-art FPN-based detectors on MS COCO benchmark.
arXiv Detail & Related papers (2021-03-19T05:51:53Z) - Multi-scale Interactive Network for Salient Object Detection [91.43066633305662]
We propose the aggregate interaction modules to integrate the features from adjacent levels.
To obtain more efficient multi-scale features, the self-interaction modules are embedded in each decoder unit.
Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches.
arXiv Detail & Related papers (2020-07-17T15:41:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.