Spatial Pyramid Pooling Networks For Image Processing


Ontology type: sgo:Patent     


Patent Info

DATE

2017-10-04T00:00

AUTHORS

HE, KAIMING , SUN, JIAN , ZHANG, Xiangyu , REN, Shaoqing

ABSTRACT

Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels,and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting. More... »

Related SciGraph Publications

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2746", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "HE, KAIMING", 
        "type": "Person"
      }, 
      {
        "name": "SUN, JIAN", 
        "type": "Person"
      }, 
      {
        "name": "ZHANG, Xiangyu", 
        "type": "Person"
      }, 
      {
        "name": "REN, Shaoqing", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-319-10578-9_23", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030406568", 
          "https://doi.org/10.1007/978-3-319-10578-9_23"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2017-10-04T00:00", 
    "description": "

Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels,and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting.

", "id": "sg:patent.EP-3204888-A4", "keywords": [ "image processing", "pyramid", "spp", "layer", "partition", "input image", "division", "finer", "coarser", "local feature", "fixed length", "input", "multi-level", "robustness", "deformation", "feature", "variable", "Pliability", "image representation", "network", "scale", "scale invariance", "risk", "fitting" ], "name": "SPATIAL PYRAMID POOLING NETWORKS FOR IMAGE PROCESSING", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.419815.0", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/EP-3204888-A4" ], "sdDataset": "patents", "sdDatePublished": "2019-04-18T10:21", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com-uberresearch-data-patents-target-20190320-rc/data/sn-export/402f166718b70575fb5d4ffe01f064d1/0000100128-0000352499/json_export_01555.jsonl", "type": "Patent" } ]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/patent.EP-3204888-A4'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.EP-3204888-A4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.EP-3204888-A4'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.EP-3204888-A4'


 

This table displays all metadata directly associated to this object as RDF triples.

62 TRIPLES      15 PREDICATES      39 URIs      32 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.EP-3204888-A4 schema:about anzsrc-for:2746
2 schema:author Nd712f3bff6cd475d8499594a4d334033
3 schema:citation sg:pub.10.1007/978-3-319-10578-9_23
4 schema:datePublished 2017-10-04T00:00
5 schema:description <p num="0000">Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels,and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting.</p>
6 schema:keywords Pliability
7 coarser
8 deformation
9 division
10 feature
11 finer
12 fitting
13 fixed length
14 image processing
15 image representation
16 input
17 input image
18 layer
19 local feature
20 multi-level
21 network
22 partition
23 pyramid
24 risk
25 robustness
26 scale
27 scale invariance
28 spp
29 variable
30 schema:name SPATIAL PYRAMID POOLING NETWORKS FOR IMAGE PROCESSING
31 schema:recipient https://www.grid.ac/institutes/grid.419815.0
32 schema:sameAs https://app.dimensions.ai/details/patent/EP-3204888-A4
33 schema:sdDatePublished 2019-04-18T10:21
34 schema:sdLicense https://scigraph.springernature.com/explorer/license/
35 schema:sdPublisher Nc732ad9147764d8b9bb05cc571ce92a6
36 sgo:license sg:explorer/license/
37 sgo:sdDataset patents
38 rdf:type sgo:Patent
39 N145a7ce9b2cf4e62959db605571a25b4 rdf:first Nde4532b518714fa7b2b8386643128712
40 rdf:rest N5f18bfad3a184126b4a7475b276fc2c5
41 N3477922c34fa490db9ba77ebea926524 schema:name SUN, JIAN
42 rdf:type schema:Person
43 N5f18bfad3a184126b4a7475b276fc2c5 rdf:first Ne6858b6677dd4282be1f6c29267fe58e
44 rdf:rest rdf:nil
45 Na23c8da0fe5b4923800f18603831efe2 rdf:first N3477922c34fa490db9ba77ebea926524
46 rdf:rest N145a7ce9b2cf4e62959db605571a25b4
47 Nc732ad9147764d8b9bb05cc571ce92a6 schema:name Springer Nature - SN SciGraph project
48 rdf:type schema:Organization
49 Nd712f3bff6cd475d8499594a4d334033 rdf:first Ne71f8021db7748cab3bd7ddb074dbe5a
50 rdf:rest Na23c8da0fe5b4923800f18603831efe2
51 Nde4532b518714fa7b2b8386643128712 schema:name ZHANG, Xiangyu
52 rdf:type schema:Person
53 Ne6858b6677dd4282be1f6c29267fe58e schema:name REN, Shaoqing
54 rdf:type schema:Person
55 Ne71f8021db7748cab3bd7ddb074dbe5a schema:name HE, KAIMING
56 rdf:type schema:Person
57 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
58 rdf:type schema:DefinedTerm
59 sg:pub.10.1007/978-3-319-10578-9_23 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030406568
60 https://doi.org/10.1007/978-3-319-10578-9_23
61 rdf:type schema:CreativeWork
62 https://www.grid.ac/institutes/grid.419815.0 schema:Organization
 




Preview window. Press ESC to close (or click here)


...