ECT: Fine-grained Edge Detection with Learned Cause Tokens
- URL: http://arxiv.org/abs/2308.03092v1
- Date: Sun, 6 Aug 2023 11:37:55 GMT
- Title: ECT: Fine-grained Edge Detection with Learned Cause Tokens
- Authors: Shaocong Xu, Xiaoxue Chen, Yuhang Zheng, Guyue Zhou, Yurong Chen,
Hongbin Zha and Hao Zhao
- Abstract summary: We propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges.
We evaluate our method on the public benchmark BSDS-RIND and several newly derived benchmarks, and achieve new state-of-the-art results.
- Score: 19.271691951077617
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this study, we tackle the challenging fine-grained edge detection task,
which refers to predicting specific edges caused by reflectance, illumination,
normal, and depth changes, respectively. Prior methods exploit multi-scale
convolutional networks, which are limited in three aspects: (1) Convolutions
are local operators while identifying the cause of edge formation requires
looking at far away pixels. (2) Priors specific to edge cause are fixed in
prediction heads. (3) Using separate networks for generic and fine-grained edge
detection, and the constraint between them may be violated. To address these
three issues, we propose a two-stage transformer-based network sequentially
predicting generic edges and fine-grained edges, which has a global receptive
field thanks to the attention mechanism. The prior knowledge of edge causes is
formulated as four learnable cause tokens in a cause-aware decoder design.
Furthermore, to encourage the consistency between generic edges and
fine-grained edges, an edge aggregation and alignment loss is exploited. We
evaluate our method on the public benchmark BSDS-RIND and several newly derived
benchmarks, and achieve new state-of-the-art results. Our code, data, and
models are publicly available at https://github.com/Daniellli/ECT.git.
Related papers
- Graph Anomaly Detection with Noisy Labels by Reinforcement Learning [13.135788402192215]
We propose a novel framework REGAD, i.e., REinforced Graph Anomaly Detector.
Specifically, we aim to maximize the performance improvement (AUC) of a base detector by cutting noisy edges approximated through the nodes with high-confidence labels.
arXiv Detail & Related papers (2024-07-08T13:41:21Z) - Learning to utilize image second-order derivative information for crisp edge detection [13.848361661516595]
Edge detection is a fundamental task in computer vision.
Recent top-performing edge detection methods tend to generate thick and noisy edge lines.
We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately.
We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue.
In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for edge detection.
arXiv Detail & Related papers (2024-06-09T13:25:02Z) - Revisiting Edge Perturbation for Graph Neural Network in Graph Data
Augmentation and Attack [58.440711902319855]
Edge perturbation is a method to modify graph structures.
It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs)
We propose a unified formulation and establish a clear boundary between two categories of edge perturbation methods.
arXiv Detail & Related papers (2024-03-10T15:50:04Z) - Edge-Aware Mirror Network for Camouflaged Object Detection [5.032585246295627]
We propose a novel Edge-aware Mirror Network (EAMNet) to model edge detection and camouflaged object segmentation.
EAMNet has a two-branch architecture, where a segmentation-induced edge aggregation module and an edge-induced integrity aggregation module are designed to cross-guide the segmentation branch and edge detection branch.
Experiment results show that EAMNet outperforms existing cutting-edge baselines on three widely used COD datasets.
arXiv Detail & Related papers (2023-07-08T08:14:49Z) - The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge
Detector [70.43599299422813]
Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators.
We propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations.
UAED achieves superior performance consistently across multiple edge detection benchmarks.
arXiv Detail & Related papers (2023-03-21T13:14:36Z) - Refined Edge Usage of Graph Neural Networks for Edge Prediction [51.06557652109059]
We propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE)
We first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision.
In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences.
arXiv Detail & Related papers (2022-12-25T23:19:56Z) - 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) - RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination,
Normal and Depth [70.25160895688464]
We propose a novel neural network solution, RINDNet, to jointly detect all four types of edges.
RINDNet learns effective representations for each of them and works in three stages.
In our experiments, RINDNet yields promising results in comparison with state-of-the-art methods.
arXiv Detail & Related papers (2021-08-02T03:30:01Z) - Unsupervised Object Detection with LiDAR Clues [70.73881791310495]
We present the first practical method for unsupervised object detection with the aid of LiDAR clues.
In our approach, candidate object segments based on 3D point clouds are firstly generated.
Then, an iterative segment labeling process is conducted to assign segment labels and to train a segment labeling network.
The labeling process is carefully designed so as to mitigate the issue of long-tailed and open-ended distribution.
arXiv Detail & Related papers (2020-11-25T18:59:54Z) - 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)
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.