The Pascal Visual Object Classes (VOC) Challenge¶
Why this mattered¶
TBD
Abstract¶
(no abstract available)
Related¶
- cite → Distinctive Image Features from Scale-Invariant Keypoints — The PASCAL VOC Challenge cites SIFT as a standard local image descriptor used by object-recognition systems evaluated on the benchmark.
- cite → Histograms of Oriented Gradients for Human Detection — The PASCAL VOC Challenge cites HOG as an influential gradient-feature method for pedestrian and object detection within benchmarked recognition pipelines.
- cite → Robust Real-Time Face Detection — The PASCAL VOC Challenge cites Viola-Jones face detection as a canonical real-time sliding-window detection method related to VOC object-detection evaluation.
- enables → Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — PASCAL VOC provided object-recognition benchmark practices that helped frame ImageNet-era evaluation for deep rectifier networks.
- enables → Deep Residual Learning for Image Recognition — PASCAL VOC helped standardize visual-recognition benchmarking and detection tasks that residual networks later improved through very deep convolutional features.
- enables → Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks — PASCAL VOC standardized object-detection benchmarks and evaluation metrics, giving Faster R-CNN a common dataset and mAP target for measuring region proposal networks.
- enables → Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation — PASCAL VOC provided the object-detection benchmark and evaluation protocol on which R-CNN demonstrated region-based CNN detection gains.
- enables → ImageNet Large Scale Visual Recognition Challenge — PASCAL VOC enables ILSVRC by providing the object-recognition challenge format and evaluation culture that ImageNet scaled up.
- enables → Momentum Contrast for Unsupervised Visual Representation Learning — PASCAL VOC provided standard object-recognition benchmarks and evaluation practice that helped define downstream transfer tests for MoCo visual representations.
- cite ← Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — The rectifier-network paper uses PASCAL VOC as an object-recognition benchmark for evaluating transfer from ImageNet-trained convolutional features.
- cite ← Deep Residual Learning for Image Recognition — ResNet cites the PASCAL VOC benchmark to evaluate residual features on object detection and segmentation transfer tasks.
- cite ← Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks — Faster R-CNN uses the Pascal VOC benchmark to evaluate object detection accuracy and compare against prior detectors.
- cite ← Selective Search for Object Recognition — Selective Search evaluates object-proposal quality on the PASCAL VOC object-detection benchmark.
- cite ← Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation — R-CNN evaluates object detection and segmentation performance on the PASCAL VOC benchmark introduced by the VOC Challenge.
- cite ← ImageNet Large Scale Visual Recognition Challenge — ILSVRC cites PASCAL VOC as an earlier benchmark that shaped object classification and detection challenge design.
- cite ← Momentum Contrast for Unsupervised Visual Representation Learning — MoCo evaluates learned visual representations by transfer to object detection on the PASCAL VOC benchmark.
- enables ← Distinctive Image Features from Scale-Invariant Keypoints — SIFT provided a robust local-feature baseline for object recognition systems evaluated on the PASCAL VOC benchmark.
- enables ← Robust Real-Time Face Detection — Real-time face detection helped establish sliding-window object-detection methodology that PASCAL VOC generalized across visual object classes.