|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates.
To this end, we devise a general loss function to cover most region-based object detectors with various sampling strategies, and then based on it we propose a unified sample weighting network to predict a sample's task weights.
By aggregating similar images into clusters, our novel approach to image annotation increases consistency, multiplies the throughput of an annotator and allows experts to adapt the granularity of their sorting scheme to the structure in the data.
From the experimental analysis, it is observed that the YOLO v3 with Deepsort tracking scheme displayed best results with balanced mAP and FPS score to monitor the social distancing in real-time.
Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
In this paper, we propose a supervised mixing augmentation method, termed SuperMix, which exploits the knowledge of a teacher to mix images based on their salient regions.
Making a precise annotation in a large dataset is crucial to the performance of object detection.