Pith. sign in

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

arxiv 1901.01892 v2 pith:SI5VJWH2 submitted 2019-01-07 cs.CV

classification cs.CV
keywords objectdetectiontridentnetbranchfieldsparametersreceptivescale
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Instance Scale Normalization for image understanding

    cs.CV 2019-08 conditional novelty 6.0 of 10

    ISN filters extreme-scale objects during multi-scale training and testing, improving COCO object detection, instance segmentation, and human pose estimation.

  2. Matrix Nets: A New Deep Architecture for Object Detection

    cs.CV 2019-08 conditional novelty 6.0 of 10

    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.

  3. Recent Advances in Deep Learning for Object Detection

    cs.CV 2019-08 conditional

    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.

Pith tools