Msmsfnet: a multi-stream and multi-scale fusion net for edge detection
- URL: http://arxiv.org/abs/2404.04856v1
- Date: Sun, 7 Apr 2024 08:03:42 GMT
- Title: Msmsfnet: a multi-stream and multi-scale fusion net for edge detection
- Authors: Chenguang Liu, Chisheng Wang, Feifei Dong, 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.
We study the performance that can be achieved by state-of-the-art deep learning based edge detectors in publicly available datasets when they are trained from scratch.
- Score: 6.4599872230835045
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 the efficiency of these algorithms, their performance, however, relies heavily on the pretrained weights of the backbone network on the ImageNet dataset. This limits heavily 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. In this work, we study the performance that can be achieved by state-of-the-art deep learning based edge detectors 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, out model outperforms state-of-the art deep learning based edge detectors in three publicly available datasets.
Related papers
- Transfer Learning with Point Transformers [3.678615604632945]
Point Transformers are state-of-the-art models for classification, segmentation, and detection on Point Cloud data.
We explore two things: classification performance of these attention based networks on ModelNet10 dataset and then, we use the trained model to classify 3D MNIST dataset after finetuning.
arXiv Detail & Related papers (2024-04-01T01:23:58Z) - 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) - Dense Extreme Inception Network for Edge Detection [0.0]
Edge detection is the basis of many computer vision applications.
Most of the publicly available datasets are not curated for edge detection tasks.
We present a new dataset of edges.
We propose a novel architecture, termed Dense Extreme Inception Network for Edge Detection (DexiNed)
arXiv Detail & Related papers (2021-12-04T05:38:50Z) - 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 [70.64030011999981]
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) - Edge-Detect: Edge-centric Network Intrusion Detection using Deep Neural
Network [0.0]
Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints.
We develop a novel light, fast and accurate 'Edge-Detect' model, which detects Denial of Service attack on edge nodes using DLM techniques.
arXiv Detail & Related papers (2021-02-03T04:24:34Z) - Improving Deep Stereo Network Generalization with Geometric Priors [93.09496073476275]
Large datasets of diverse real-world scenes with dense ground truth are difficult to obtain.
Many algorithms rely on small real-world datasets of similar scenes or synthetic datasets.
We propose to incorporate prior knowledge of scene geometry into an end-to-end stereo network to help networks generalize better.
arXiv Detail & Related papers (2020-08-25T15:24:02Z) - Saliency Enhancement using Gradient Domain Edges Merging [65.90255950853674]
We develop a method to merge the edges with the saliency maps to improve the performance of the saliency.
This leads to our proposed saliency enhancement using edges (SEE) with an average improvement of at least 3.4 times higher on the DUT-OMRON dataset.
The SEE algorithm is split into 2 parts, SEE-Pre for preprocessing and SEE-Post pour postprocessing.
arXiv Detail & Related papers (2020-02-11T14:04:56Z) - Neural Data Server: A Large-Scale Search Engine for Transfer Learning
Data [78.74367441804183]
We introduce Neural Data Server (NDS), a large-scale search engine for finding the most useful transfer learning data to the target domain.
NDS consists of a dataserver which indexes several large popular image datasets, and aims to recommend data to a client.
We show the effectiveness of NDS in various transfer learning scenarios, demonstrating state-of-the-art performance on several target datasets.
arXiv Detail & Related papers (2020-01-09T01:21:30Z)
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.