REVIEW 3 cited by
Scale-Aware Trident Networks for Object Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.
Forward citations
Cited by 3 Pith papers
-
Instance Scale Normalization for image understanding
ISN filters extreme-scale objects during multi-scale training and testing, improving COCO object detection, instance segmentation, and human pose estimation.
-
Matrix Nets: A New Deep Architecture for Object Detection
The paper introduces Matrix Nets, a feature-pyramid-like architecture with separate layers for scale and aspect ratio, and shows a keypoint-based detector built on it reaches 47.8 mAP on MS COCO.
-
Recent Advances in Deep Learning for Object Detection
A structured survey of deep learning object detection covering two-stage and one-stage detectors, feature learning, training strategies, applications, and benchmarks up to 2019.
Discussion (0). Continue with ORCID to comment.