A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Collaboratively boosting data-driven deep learning and knowledge-guided ontological reasoning for semantic segmentation of remote sensing imagery
[article]
2020
arXiv
pre-print
As one kind of architecture from the deep learning family, deep semantic segmentation network (DSSN) achieves a certain degree of success on the semantic segmentation task and obviously outperforms the ...
In literature, ontological modeling and reasoning is an ideal way to imitate and employ the domain knowledge of human beings, but is still rarely explored and adopted in the RS domain. ...
Along with the rapid development of deep networks such as deep detection networks [9, 10] , deep recognition networks [11] and deep hashing networks [12, 13] , deep semantic segmentation network (DSSN ...
arXiv:2010.02451v1
fatcat:xuplt5paznhvdci7lkdqb5hfha
SimpleMind adds thinking to deep neural networks
[article]
2022
arXiv
pre-print
The SimpleMind framework brings thinking to DNNs by: (1) providing methods for reasoning with the knowledge base about image content, such as spatial inferencing and conditional reasoning to check DNN ...
Example applications are provided that demonstrate how SimpleMind supports and improves deep neural networks by embedding them within a Cognitive AI framework. ...
To improve computer vision accuracy and reliability we embed deep neural networks within a Cognitive AI framework to meld pattern recognition with conceptual knowledge and reasoning. ...
arXiv:2212.00951v1
fatcat:zwi2jqnilfe6rgvajreinvx5he
Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
[article]
2021
arXiv
pre-print
The former extracts the semantic graph in each domain to improve the feature representation learning by propagating information with the graph; the latter exploits the dependencies among the graphs from ...
In particular, Graphonomy learns the global and structured semantic coherency in multiple domains via semantic-aware graph reasoning and transfer, enforcing the mutual benefits of the parsing across domains ...
For panoptic segmentation, we show that explicitly exploiting the underlying semantic configurations with the contextually co-related tasks is a key to improving not only the segmentation performance but ...
arXiv:2101.10620v1
fatcat:hnbuqiugsfhvbc7phn5htmsvcy
Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation
[article]
2021
arXiv
pre-print
We present an initial study adapting the well-established Probabilistic Soft Logic (PSL) framework to validate and improve on the problem of semantic segmentation. ...
In doing so, we improve and robustify existing deep neural networks consuming low-level sensor information. ...
To the best of our knowledge it is the first attempt to combine deep-learningbased semantic segmentation with probabilistic logical reasoning about the environment. ...
arXiv:2104.09254v1
fatcat:udu4x6hqyrg5bbowkkyvrzvlpy
Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
[article]
2020
arXiv
pre-print
Concretely, we design an adversarial graph network that interpolates a symbolic graph reasoning module into a generative adversarial network through embedding prior domain knowledge, achieving semantic ...
segmentation of spinal structures with high complexity and variability. ...
The function of symbolic graph reasoning is to improve the segmentation consistency by embedding useful prior knowledge into neural networks. ...
arXiv:2004.13577v1
fatcat:oh5aka5zr5be3ipd7qqnyhikzy
Bidirectional Graph Reasoning Network for Panoptic Segmentation
[article]
2020
arXiv
pre-print
Recent researches on panoptic segmentation resort to a single end-to-end network to combine the tasks of instance segmentation and semantic segmentation. ...
We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and intermodular relations ...
Bidirectional Graph Reasoning Network
Overview The panoptic segmentation task is to assign each pixel in an image a semantic label and an instance id. ...
arXiv:2004.06272v1
fatcat:hzdz6x2yazaaphghe4uzj3xqj4
Symbolic Graph Reasoning Meets Convolutions
2018
Neural Information Processing Systems
Beyond local convolution networks, we explore how to harness various external human knowledge for endowing the networks with the capability of semantic global reasoning. ...
Extensive experiments show incorporating SGR significantly improves plain ConvNets on three semantic segmentation tasks and one image classification task. ...
Combining multiple SGR layers with distinct knowledge graphs into convolutional networks can lead to hybrid graph reasoning behaviors. ...
dblp:conf/nips/LiangHZLX18
fatcat:ev3i2ub4yjfsfbo6i6vq7vdw3u
Bidirectional Graph Reasoning Network for Panoptic Segmentation
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Recent researches on panoptic segmentation resort to a single end-to-end network to combine the tasks of instance segmentation and semantic segmentation. ...
We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and intermodular relations ...
Inspired by this, we introduce a new Bidirectional Graph Reasoning Network (named BGRNet) that incorpo- rates graph structure into the conventional panoptic segmentation network to encode the semantic ...
doi:10.1109/cvpr42600.2020.00910
dblp:conf/cvpr/WuZ0DGLL20
fatcat:wplfpjnqdrfldpdppc3ft6ueky
M-FasterSeg: An Efficient Semantic Segmentation Network Based on Neural Architecture Search
[article]
2022
arXiv
pre-print
First, a neural network search method NAS (Neural Architecture Search) is used to find a semantic segmentation network with multiple resolution branches. ...
This paper proposes an improved structure of a semantic segmentation network based on a deep learning network that combines self-attention neural network and neural network architecture search methods. ...
Through knowledge distillation technology, the network model with a few parameters is used as the algorithm model of the fast semantic segmentation method, so as to realize the fast semantic segmentation ...
arXiv:2112.07918v3
fatcat:lst6ub3ccrfj5npvpmad32n56a
Low-cost Multispectral Scene Analysis with Modality Distillation
2022
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
The proposed framework distils the knowledge from a high thermal resolution two-stream network with featurelevel fusion to a low thermal resolution one-stream network with image-level fusion. ...
We show on different multispectral scene analysis benchmarks that our method can effectively allow the use of low-resolution thermal sensors with more compact one-stream networks. ...
structured knowledge for a semantic segmentation task. ...
doi:10.1109/wacv51458.2022.00339
fatcat:3ngmltcgdrbmpfcma25uefxaxi
Integrating Image Segmentation and Classification for Fuzzy Knowledge-Based Multimedia Indexing
[chapter]
2009
Lecture Notes in Computer Science
In this paper we propose a methodology for semantic indexing of images, based on techniques of image segmentation, classification and fuzzy reasoning. ...
as color and shape, ii) mid-level semantics, such as concurrent image segmentation and object detection, region-based classification and, iii) rich semantics, i.e. fuzzy reasoning for extraction of implicit ...
simultaneously with region merging that improves extraction of semantic objects. ...
doi:10.1007/978-3-540-92892-8_29
fatcat:yijkpn2gknhi7emlrgssanania
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
[article]
2023
arXiv
pre-print
All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. ...
To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual ...
Then, a reasoning module is utilized to enrich the anchor frames with the aggregated semantic knowledge. ...
arXiv:2301.00514v1
fatcat:psh7ovydhbgttpev5hq2cmzoiq
A Survey of Semantic Construction and Application of Satellite Remote Sensing Images and Data
2021
Journal of Organizational and End User Computing
Through the semantic research of remote sensing data, the processing ability of remote sensing data is greatly improved. ...
, for remote sensing big data, the technical progress in the study field of semantic construction is analyzed from four aspects: semantic description and understanding, semantic segmentation, semantic ...
With good knowledge expression, communication, sharing and reasoning ability, it has been widely recognized in many industries and fields. ...
doi:10.4018/joeuc.20211101oa06
fatcat:qrxy6plef5f7fkgvfk6f5sbkwu
A Survey of Semantic Construction and Application of Satellite Remote Sensing Images and Data
2021
Journal of Organizational and End User Computing
Through the semantic research of remote sensing data, the processing ability of remote sensing data is greatly improved. ...
, for remote sensing big data, the technical progress in the study field of semantic construction is analyzed from four aspects: semantic description and understanding, semantic segmentation, semantic ...
With good knowledge expression, communication, sharing and reasoning ability, it has been widely recognized in many industries and fields. ...
doi:10.4018/joeuc.20211101.oa6
fatcat:mxuhgviitff3nldf2gzrfiog7e
Automatic Image Labelling at Pixel Level
[article]
2020
arXiv
pre-print
A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from a source domain, and such GFN then transfers such segmentation knowledge to generate coarse object masks in the ...
The performance of deep networks for semantic image segmentation largely depends on the availability of large-scale training images which are labelled at the pixel level. ...
Some researches [7] , [8] used the training images with image-level labellings to learn the semantic segmentation networks. ...
arXiv:2007.07415v2
fatcat:mqcqkrn65beghjaspwvutlf35u
« Previous
Showing results 1 — 15 out of 84,046 results