VOCSegmentation
E431001
VOCSegmentation is a semantic segmentation dataset class in Torchvision that provides access to the PASCAL VOC image dataset with pixel-level object annotations.
All labels observed (1)
| Label | Occurrences |
|---|---|
| VOCSegmentation canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4325992 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VOCSegmentation Context triple: [torchvision, dataset, VOCSegmentation]
-
A.
VOC
VOC is the abbreviation for the Dutch East India Company, a powerful 17th-century trading corporation that dominated European-Asian maritime trade and helped shape early global capitalism.
-
B.
Visible Speech alphabet
The Visible Speech alphabet is a 19th-century phonetic writing system that represents the physical positions and movements of the speech organs to visually depict spoken sounds.
-
C.
Viterbi algorithm
The Viterbi algorithm is a dynamic programming method used to find the most likely sequence of hidden states in probabilistic models such as Hidden Markov Models, widely applied in fields like digital communications, speech recognition, and bioinformatics.
-
D.
VOG
VOG is the IATA airport code for Volgograd International Airport, a regional air transport hub serving the city of Volgograd in Russia.
-
E.
Visible Speech
Visible Speech is a 19th-century phonetic notation system devised by Alexander Melville Bell to visually represent the position and movement of speech organs for any spoken sound.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: VOCSegmentation Target entity description: VOCSegmentation is a semantic segmentation dataset class in Torchvision that provides access to the PASCAL VOC image dataset with pixel-level object annotations.
-
A.
VOC
VOC is the abbreviation for the Dutch East India Company, a powerful 17th-century trading corporation that dominated European-Asian maritime trade and helped shape early global capitalism.
-
B.
Visible Speech alphabet
The Visible Speech alphabet is a 19th-century phonetic writing system that represents the physical positions and movements of the speech organs to visually depict spoken sounds.
-
C.
Viterbi algorithm
The Viterbi algorithm is a dynamic programming method used to find the most likely sequence of hidden states in probabilistic models such as Hidden Markov Models, widely applied in fields like digital communications, speech recognition, and bioinformatics.
-
D.
VOG
VOG is the IATA airport code for Volgograd International Airport, a regional air transport hub serving the city of Volgograd in Russia.
-
E.
Visible Speech
Visible Speech is a 19th-century phonetic notation system devised by Alexander Melville Bell to visually represent the position and movement of speech organs for any spoken sound.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
semantic segmentation dataset class
ⓘ
torchvision.datasets.VisionDataset subclass ⓘ |
| canDownload | PASCAL VOC data when download=True ⓘ |
| defaultValue |
image_set='train'
ⓘ
year='2012' ⓘ |
| ecosystem | PyTorch NERFINISHED ⓘ |
| hasAnnotationGranularity | pixel-level ⓘ |
| hasAnnotationType | segmentation masks ⓘ |
| imageType | PIL.Image.Image ⓘ |
| implementsMethod |
__getitem__
ⓘ
__len__ ⓘ |
| inheritsFrom | torchvision.datasets.VisionDataset ⓘ |
| language | Python NERFINISHED ⓘ |
| maskEncoding | class index per pixel ⓘ |
| modulePath | torchvision.datasets.voc ⓘ |
| operatesOn | PASCAL VOC dataset NERFINISHED ⓘ |
| parameter |
download
ⓘ
image_set ⓘ root ⓘ target_transform ⓘ transform ⓘ transforms ⓘ year ⓘ |
| parameterType |
download: bool
ⓘ
image_set: str ⓘ root: str ⓘ target_transform: callable or None ⓘ transform: callable or None ⓘ transforms: callable or None ⓘ year: str ⓘ |
| providedBy | torchvision.datasets NERFINISHED ⓘ |
| provides |
RGB images
ⓘ
object class labels per pixel ⓘ pixel-level segmentation masks ⓘ |
| requires | PASCAL VOC directory structure ⓘ |
| returnsFromGetItem | (image, target) ⓘ |
| supportsDataset |
PASCAL VOC 2007
NERFINISHED
ⓘ
PASCAL VOC 2012 NERFINISHED ⓘ |
| supportsSplit |
test
ⓘ
train ⓘ trainval ⓘ val ⓘ |
| supportsYear |
2007
ⓘ
2012 ⓘ |
| targetType | PIL.Image.Image mask ⓘ |
| usedFor |
pixel-level object recognition
ⓘ
semantic segmentation ⓘ |
| usedIn |
deep learning research
ⓘ
semantic segmentation benchmarks ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: VOCSegmentation Description of subject: VOCSegmentation is a semantic segmentation dataset class in Torchvision that provides access to the PASCAL VOC image dataset with pixel-level object annotations.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
torchvision