A comparative study of attention mechanism and generative adversarial network in facade damage segmentation

• URL: http://arxiv.org/abs/2209.13283v1
• Date: Tue, 27 Sep 2022 09:59:32 GMT
• Title: A comparative study of attention mechanism and generative adversarial network in facade damage segmentation
• Abstract summary: Attention mechanism and generative adversarial networks are two of the most popular strategies to improve the quality of semantic segmentation. This paper adopts U-net, a representative convolutional neural network, as the primary network and presents a comparative study in two steps.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic segmentation profits from deep learning and has shown its possibilities in handling the graphical data from the on-site inspection. As a result, visual damage in the facade images should be detected. Attention mechanism and generative adversarial networks are two of the most popular strategies to improve the quality of semantic segmentation. With specific focuses on these two strategies, this paper adopts U-net, a representative convolutional neural network, as the primary network and presents a comparative study in two steps. First, cell images are utilized to respectively determine the most effective networks among the U-nets with attention mechanism or generative adversarial networks. Subsequently, selected networks from the first test and their combination are applied for facade damage segmentation to investigate the performances of these networks. Besides, the combined effect of the attention mechanism and the generative adversarial network is discovered and discussed.

Related papers

• Contrastive Network Representation Learning [20.236657764682715]
  Network representation learning seeks to embed networks into a low-dimensional space while preserving the structural and semantic properties.<n>We propose a novel contrastive learning-based statistical approach for network edge embedding.<n>We show that our method achieves the minimax optimal convergence rate for edge representation learning.
  arXiv  Detail & Related papers  (2025-09-14T15:25:59Z)
• Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation [4.02487511510606]
  Weakly supervised semantic segmentation (WSSS) is a fundamental computer vision task, which aims to segment out the object within only class-level labels. Traditional methods adopt the CNN-based network and utilize the class activation map (CAM) strategy to discover the object regions. An alternative is to explore vision transformers (ViT) to encode the image to acquire the global semantic information. We propose a dual network with both CNN-based and transformer networks for mutually complementary learning.
  arXiv  Detail & Related papers  (2023-09-30T08:41:11Z)
• An Empirical Study of Attention Networks for Semantic Segmentation [11.000308726481236]
  Recently, the decoders based on attention achieve state-of-the-art (SOTA) performance on various datasets. This paper first conducts experiments to analyze their computation complexity and compare their performance.
  arXiv  Detail & Related papers  (2023-09-19T00:07:57Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• BraidNet: procedural generation of neural networks for image classification problems using braid theory [0.0]
  We propose the approach to procedural optimization of a neural network, based on the combination of information theory and braid theory. The network studied in the article implemented with the intersections between the braid strands, as well as simplified networks, are used to solve various problems of multiclass image classification. The simulation results showed BraidNet's comparative advantage in learning speed and classification accuracy.
  arXiv  Detail & Related papers  (2021-04-20T14:40:30Z)
• Variational Structured Attention Networks for Deep Visual Representation Learning [49.80498066480928]
  We propose a unified deep framework to jointly learn both spatial attention maps and channel attention in a principled manner. Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework. We implement the inference rules within the neural network, thus allowing for end-to-end learning of the probabilistic and the CNN front-end parameters.
  arXiv  Detail & Related papers  (2021-03-05T07:37:24Z)
• Adversarial Attack on Network Embeddings via Supervised Network Poisoning [20.583791500831147]
  We study network embedding algorithms from an adversarial point of view and observe the effect of poisoning the network on downstream tasks. We propose VIKING, a supervised network poisoning strategy that outperforms the state-of-the-art poisoning methods by upto 18% on the original network structure.
  arXiv  Detail & Related papers  (2021-02-14T14:47:39Z)
• Attribution Preservation in Network Compression for Reliable Network Interpretation [81.84564694303397]
  Neural networks embedded in safety-sensitive applications rely on input attribution for hindsight analysis and network compression to reduce its size for edge-computing. We show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions. This phenomenon arises due to the fact that conventional network compression methods only preserve the predictions of the network while ignoring the quality of the attributions.
  arXiv  Detail & Related papers  (2020-10-28T16:02:31Z)
• Pairwise Relation Learning for Semi-supervised Gland Segmentation [90.45303394358493]
  We propose a pairwise relation-based semi-supervised (PRS2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net) We evaluate our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset.
  arXiv  Detail & Related papers  (2020-08-06T15:02:38Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• An End-to-End Network for Co-Saliency Detection in One Single Image [47.35448093528382]
  Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. This study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. We construct a new dataset of 2,019 natural images with co-saliency in each image to evaluate the proposed method.
  arXiv  Detail & Related papers  (2019-10-25T16:00:44Z)

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.