paper-with-me

PASCAL VOC

PASCAL Visual Object Classes Challenge

홈페이지 · 논문 198편

The PASCAL Visual Object Classes (VOC) 2012 dataset contains 20 object categories including vehicles, household, animals, and other: aeroplane, bicycle, boat, bus, car, motorbike, train, bottle, chair, dining table, potted plant, sofa, TV/monitor, bird, cat, cow, dog, horse, sheep, and person. Each image in this dataset has pixel-level segmentation annotations, bounding box annotations, and object class annotations. This dataset has been widely used as a benchmark for object detection, semantic segmentation, and classification tasks. The PASCAL VOC dataset is split into three subsets: 1,464 images for training, 1,449 images for validation and a private testing set. Source: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey Image Source: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/examples/images/sheep_06.jpg

Images

벤치마크

Graph Matching on PASCAL VOC 결과 31개

Unsupervised Semantic Segmentation with Language-image Pre-training on PASCAL VOC 결과 30개

Unsupervised Semantic Segmentation with Language-image Pre-training on PascalVOC-20 결과 30개

Node Classification on PascalVOC-SP 결과 21개

Open Vocabulary Semantic Segmentation on PascalVOC-20 결과 20개

3D Face Animation on VOCASET 결과 14개

Zero-Shot Semantic Segmentation on PASCAL VOC 결과 13개

Object Detection on PASCAL VOC 10% 결과 10개

Object Counting on Pascal VOC 2007 count-test 결과 8개

Image Segmentation on PASCAL VOC 결과 6개

Object Detection on PASCAL VOC 결과 5개

Semantic Segmentation on PASCAL VOC 결과 5개

Open Vocabulary Semantic Segmentation on PascalVOC-20b 결과 4개

Object Counting on PASCAL VOC 결과 3개

Single-object discovery on VOC_all 결과 3개

Interactive Segmentation on PASCAL VOC 결과 2개

Knowledge Distillation on PASCAL VOC 결과 2개

Multi-object discovery on VOC_all 결과 2개

Single-object discovery on VOC_6x2 결과 2개

Multi-object colocalization on VOC_all 결과 1개