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| Paper | Code | Results | Date | Stars |
|---|
Multi-Label Classification
Object Localization
Interactive Segmentation
Cross-Modal Retrieval
Unsupervised Semantic Segmentation with Language-image Pre-training
Unsupervised Object Detection
Object Counting
Graph Matching
Single-object discovery
Knowledge Distillation
Single-object colocalization
Zero-Shot Semantic Segmentation
Unsupervised Object Localization
Weakly-supervised instance segmentation
Multi-object discovery
Image-level Supervised Instance Segmentation
Point-Supervised Instance Segmentation
Multi-object colocalization
Overlapped 10-1
Box-supervised Instance Segmentation
Overlapped 19-1
Overlapped 15-5
Overlapped 15-1
Disjoint 15-1
Disjoint 10-1
Disjoint 15-5
Weakly-Supervised Object Segmentation
Overlapped 5-3