We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method.
RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)
Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed.
Ranked #1 on Multi-Person Pose Estimation on COCO-WholeBody
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method.
The noise added to the original image is defined as the gradient of the cost function of the model.
Convolutional neural networks (CNNs) are able to attain better visual recognition performance than fully connected neural networks despite having much less parameters due to their parameter sharing principle.
Panoptic Quality (PQ), a measure proposed for evaluating panoptic segmentation (Kirillov et al., 2019), does not suffer from these limitations but is limited to panoptic segmentation.
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection.
Ranked #49 on Object Detection on COCO test-dev
In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors.
Ranked #79 on Object Detection on COCO test-dev
We further validate the effectiveness of our proposal in another task, namely, "labels to photo" image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases.
Ranked #40 on Object Detection on COCO minival
To address this problem, we propose a new framework for the quantitative evaluation of image-to-illustration models, where both content and style are taken into account using separate classifiers.
Using our generator as an analysis tool, we show that (i) IoU imbalance has an adverse effect on performance, (ii) hard positive example mining improves the performance only for certain input IoU distributions, and (iii) the imbalance among the foreground classes has an adverse effect on performance and that it can be alleviated at the batch level.
Ranked #131 on Object Detection on COCO minival
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.
Ranked #5 on Multi-Person Pose Estimation on COCO
Moreover, we present LRP results of a simple online video object detector which uses a SOTA still image object detector and show that the class-specific optimized thresholds increase the accuracy against the common approach of using a general threshold for all classes.