The Pascal Visual Object Classes (VOC) Challenge

In the citing paper

“It combines various sources of information, such as vision, language, depth data, lidar, and speech, to enhance the capability of scene semantic understanding [35,36,37].”

In the citing paper

“The architecture, benchmarked on the VOC Pascal Dataset 2007 and 2012 [29], exploited the Darknet framework for training.”

In the citing paper

“Most object detection models use generalpurpose datasets, such as COCO [12], ImageNet [13], and VOC [14]), where vehicle (i.e., cars) images are usually taken from a lateral or frontal view instead of a cenital plane.”

In the citing paper

“We comprehensively evaluate our method on the PASCAL VOC detection benchmarks [11] where RPNs with Fast R-CNNs produce detection accuracy better than the strong baseline of Selective Search with Fast R-CNNs.”

In the citing paper

“For FSCIOD tasks, the data partitioning strategy by PerezRua et al. [62] is commonly used. This approach utilizes 20 classes overlapping with the PASCAL VOC dataset [63] as new incremental classes and the remaining 60 as base data. FSCIOD models under this setup are evaluated using K ∈ 1 , 5 , 10 bounding boxes per new class.”

In the citing paper

“The PASCAL Visual Object Classes (VOC) dataset, widely used for object detection tasks, includes 20 common object classes like people, animals, vehicles, and household items [63].”

In the citing paper

“On the other hand, one one-stage approach has better ongoing execution exactness and speed on MS COCO and PASCAL VOC datasets [24,25].”

In the citing paper

“To the best of our knowledge, for the evaluation of generic object detection algorithms, it is bounding boxes which are most widely used in the current literature (Everingham et al. 2010;Russakovsky et al. 2015), and therefore this is also the approach we adopt in this survey.”

In the citing paper

“In practice, current detectors focus mainly on structured object categories, such as the 20, 200 and 91 object classes in PASCAL VOC (Everingham et al. 2010), ILSVRC (Russakovsky et al. 2015) and MS COCO (Lin et al. 2014) respectively.”

In the citing paper

“PASCAL VOC Everingham et al. (2010, 2015) is a multiyear effort devoted to the creation and maintenance of a series of benchmark datasets for classification and object detection, creating the precedent for standardized evaluation of recognition algorithms in the form of annual competitions.”

In the citing paper

“For generic object detection, there are four famous datasets: PASCAL VOC (Everingham et al. 2010(Everingham et al. , 2015)), ImageNet (Deng et al. 2009), MS COCO (Lin et al. 2014) and Open Images (Kuznetsova et al. 2018).”

In the citing paper

“Current detection datasets (Everingham et al. 2010;Russakovsky et al. 2015;Lin et al. 2014) contain only a few dozen to hundreds of categories, significantly fewer than those which can be recognized by humans.”

In the citing paper

“Likewise semantic labeling of pixels in a variety of scene types reaches performance levels of around 80% accuracy or more [74].”

In the citing paper

“regions without bounding box annotations are simply considered as background during training in currently popular detection frameworks [18], [19]”