Pooling Pyramid Network for Object Detection

Pengchong Jin; Vivek Rathod; Xiangxin Zhu

Pooling Pyramid Network for Object Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1807.03284 v1 pith:MSTZKXOR submitted 2018-07-09 cs.CV

Pooling Pyramid Network for Object Detection

Pengchong Jin , Vivek Rathod , Xiangxin Zhu This is my paper

classification cs.CV

keywords scalesmodelacrosspoolingpredictorsqualitysharesize

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

We'd like to share a simple tweak of Single Shot Multibox Detector (SSD) family of detectors, which is effective in reducing model size while maintaining the same quality. We share box predictors across all scales, and replace convolution between scales with max pooling. This has two advantages over vanilla SSD: (1) it avoids score miscalibration across scales; (2) the shared predictor sees the training data over all scales. Since we reduce the number of predictors to one, and trim all convolutions between them, model size is significantly smaller. We empirically show that these changes do not hurt model quality compared to vanilla SSD.

discussion (0)

Forward citations

Cited by 1 Pith paper

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

The Indirect Convolution Algorithm
cs.CV 2019-07 unverdicted novelty 7.0

The Indirect Convolution algorithm avoids im2col by using an indirection buffer, reducing memory overhead proportionally to input channels and outperforming GEMM-based methods by up to 62% for convolutions requiring t...