Pith. sign in

REVIEW

A Broad Dataset is All You Need for One-Shot 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 2011.04267 v2 pith:445RHXKY submitted 2020-11-09 cs.CV cs.LG

A Broad Dataset is All You Need for One-Shot Object Detection

classification cs.CV cs.LG
keywords categoriesnumberobjectdetectiongeneralizationtrainingdatasetsduring
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Is it possible to detect arbitrary objects from a single example? A central problem of all existing attempts at one-shot object detection is the generalization gap: Object categories used during training are detected much more reliably than novel ones. We here show that this generalization gap can be nearly closed by increasing the number of object categories used during training. Doing so allows us to improve generalization from seen to unseen classes from 45% to 89% and improve the state-of-the-art on COCO by 5.4 %AP50 (from 22.0 to 27.5). We verify that the effect is caused by the number of categories and not the number of training samples, and that it holds for different models, backbones and datasets. This result suggests that the key to strong few-shot detection models may not lie in sophisticated metric learning approaches, but instead simply in scaling the number of categories. We hope that our findings will help to better understand the challenges of few-shot learning and encourage future data annotation efforts to focus on wider datasets with a broader set of categories rather than gathering more samples per category.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.