Msmsfnet: a multi-stream and multi-scale fusion net for edge detection

• URL: http://arxiv.org/abs/2404.04856v2
• Date: Wed, 20 Nov 2024 02:32:23 GMT
• Title: Msmsfnet: a multi-stream and multi-scale fusion net for edge detection
• Authors: Chenguang Liu, Chisheng Wang, Feifei Dong, Xiayang Xiao, Xin Su, Chuanhua Zhu, Dejin Zhang, Qingquan Li,
• Abstract summary: Edge detection is a long-standing problem in computer vision. Recent deep learning based algorithms achieve state-of-the-art performance in publicly available datasets. However, their performance relies heavily on the pre-trained weights of the backbone network on the ImageNet dataset.
• Score: 6.1932429715357165
• License:
• Abstract: Edge detection is a long-standing problem in computer vision. Recent deep learning based algorithms achieve state-of-the-art performance in publicly available datasets. Despite their efficiency, their performance, however, relies heavily on the pre-trained weights of the backbone network on the ImageNet dataset. This significantly limits the design space of deep learning based edge detectors. Whenever we want to devise a new model, we have to train this new model on the ImageNet dataset first, and then fine-tune the model using the edge detection datasets. The comparison would be unfair otherwise. However, it is usually not feasible for many researchers to train a model on the ImageNet dataset due to the limited computation resources. Besides, if these methods need to be trained to detect edges in a different kind of data, Synthetic Aperture Radar (SAR) images for instance, the pre-trained weights on the ImageNet dataset are unlikely to improve the edge detection accuracy due to the strong differences in the statistics between optical and SAR images. In the meantime, no dataset for SAR image processing matches the size of the ImageNet dataset. In this work, we study the performance achievable by existing methods in publicly available datasets when they are trained from scratch, and devise a new network architecture, the multi-stream and multi-scale fusion net (msmsfnet), for edge detection. We show in our experiments that by training all models from scratch to ensure the fairness of comparison, our model outperforms state-of-the-art deep learning based edge detectors in three publicly available datasets. The efficiency of our model is further demonstrated by the experiments for edge detection in SAR images, which serves as an important evidence showing the meaningfulness of this work as no useful pre-trained weight is available for edge detection in SAR images.

Related papers

• Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery [78.43828998065071]
  Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities.
  arXiv  Detail & Related papers  (2024-03-08T16:18:04Z)
• Dataset Quantization [72.61936019738076]
  We present dataset quantization (DQ), a new framework to compress large-scale datasets into small subsets. DQ is the first method that can successfully distill large-scale datasets such as ImageNet-1k with a state-of-the-art compression ratio.
  arXiv  Detail & Related papers  (2023-08-21T07:24:29Z)
• Tiny and Efficient Model for the Edge Detection Generalization [0.0]
  We present Tiny and Efficient Edge Detector (TEED), a light convolutional neural network with only $58K$ parameters. Training on the BIPED dataset takes $less than 30 minutes$, with each epoch requiring $less than 5 minutes$. Our proposed model is easy to train and it quickly converges within very first few epochs, while the predicted edge-maps are crisp and of high quality.
  arXiv  Detail & Related papers  (2023-08-12T05:23:36Z)
• Robustifying Deep Vision Models Through Shape Sensitization [19.118696557797957]
  We propose a simple, lightweight adversarial augmentation technique that explicitly incentivizes the network to learn holistic shapes. Our augmentations superpose edgemaps from one image onto another image with shuffled patches, using a randomly determined mixing proportion. We show that our augmentations significantly improve classification accuracy and robustness measures on a range of datasets and neural architectures.
  arXiv  Detail & Related papers  (2022-11-14T11:17:46Z)
• Out of Distribution Detection on ImageNet-O [0.0]
  Out of distribution (OOD) detection is a crucial part of making machine learning systems robust. The ImageNet-O dataset is an important tool in testing the robustness of ImageNet trained deep neural networks. We aim to perform a comparative analysis of OOD detection methods on ImageNet-O.
  arXiv  Detail & Related papers  (2022-01-23T20:02:08Z)
• Change Detection from Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network [36.41983596642354]
  We propose a Graph-based Knowledge Supplement Network (GKSNet) for image change detection. To be more specific, we extract discriminative information from the existing labeled dataset as additional knowledge. To validate the proposed method, we conducted extensive experiments on four SAR datasets.
  arXiv  Detail & Related papers  (2022-01-22T02:50:50Z)
• Efficient deep learning models for land cover image classification [0.29748898344267777]
  This work experiments with the BigEarthNet dataset for land use land cover (LULC) image classification. We benchmark different state-of-the-art models, including Convolution Neural Networks, Multi-Layer Perceptrons, Visual Transformers, EfficientNets and Wide Residual Networks (WRN) Our proposed lightweight model has an order of magnitude less trainable parameters, achieves 4.5% higher averaged f-score classification accuracy for all 19 LULC classes and is trained two times faster with respect to a ResNet50 state-of-the-art model that we use as a baseline.
  arXiv  Detail & Related papers  (2021-11-18T00:03:14Z)
• Pixel Difference Networks for Efficient Edge Detection [71.03915957914532]
  We propose a lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue datasets are provided to demonstrate its effectiveness. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
  arXiv  Detail & Related papers  (2021-08-16T10:42:59Z)
• Self-supervised Audiovisual Representation Learning for Remote Sensing Data [96.23611272637943]
  We propose a self-supervised approach for pre-training deep neural networks in remote sensing. By exploiting the correspondence between geo-tagged audio recordings and remote sensing, this is done in a completely label-free manner. We show that our approach outperforms existing pre-training strategies for remote sensing imagery.
  arXiv  Detail & Related papers  (2021-08-02T07:50:50Z)
• Stereo Matching by Self-supervision of Multiscopic Vision [65.38359887232025]
  We propose a new self-supervised framework for stereo matching utilizing multiple images captured at aligned camera positions. A cross photometric loss, an uncertainty-aware mutual-supervision loss, and a new smoothness loss are introduced to optimize the network. Our model obtains better disparity maps than previous unsupervised methods on the KITTI dataset.
  arXiv  Detail & Related papers  (2021-04-09T02:58:59Z)
• From ImageNet to Image Classification: Contextualizing Progress on Benchmarks [99.19183528305598]
  We study how specific design choices in the ImageNet creation process impact the fidelity of the resulting dataset. Our analysis pinpoints how a noisy data collection pipeline can lead to a systematic misalignment between the resulting benchmark and the real-world task it serves as a proxy for.
  arXiv  Detail & Related papers  (2020-05-22T17:39:16Z)

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.