Pith. sign in

Prime Sample Attention in Object Detection

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to the overall performance measured in terms of mAP. Our study suggests that the samples in each mini-batch are neither independent nor equally important, and therefore a better classifier on average does not necessarily mean higher mAP. Motivated by this study, we propose the notion of Prime Samples, those that play a key role in driving the detection performance. We further develop a simple yet effective sampling and learning strategy called PrIme Sample Attention (PISA) that directs the focus of the training process towards such samples. Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector. Particularly, On the MSCOCO dataset, PISA outperforms the random sampling baseline and hard mining schemes, e.g., OHEM and Focal Loss, consistently by around 2% on both single-stage and two-stage detectors, even with a strong backbone ResNeXt-101.

citation-role summary

method 1

citation-polarity summary

fields

cs.CV 1

years

2019 1

verdicts

ACCEPT 1

roles

method 1

polarities

support 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Imbalance Problems in Object Detection: A Review cs.CV · 2019-08-31 · accept · none · ref 30 · internal anchor

    A taxonomy and critical review organizing eight object-detection imbalance problems under class, scale, spatial, and objective imbalance.