|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Ranked #3 on Dense Object Detection on SKU-110K
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #28 on Object Detection on COCO test-dev
In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature.
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #11 on Object Detection on COCO test-dev
During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions.
We train a standard object detector on a small, normally packed dataset with data augmentation techniques.
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks.
Ranked #4 on Video Object Detection on ImageNet VID
We realize the framework for object detection and human pose estimation.
To grasp the essential feature of the densely packed scenes, we analysis the stages of a detector and investigate the bottleneck which limits the performance.
Ranked #1 on Dense Object Detection on SKU-110K