# Prime Sample Attention in Object Detection

arXiv: https://arxiv.org/abs/1904.04821 · HTML: https://mlsanity.com/paper/1904.04821/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 55)

- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [FocalFormer3D : Focusing on Hard Instance for 3D Object Detection](https://mlsanity.com/paper/2308.04556/) (2023)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training](https://mlsanity.com/paper/2107.05031/) (2021)
- [A Dual Weighting Label Assignment Scheme for Object Detection](https://mlsanity.com/paper/2203.09730/) (2022)
- [A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2109.12848/) (2021)
- [Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification](https://mlsanity.com/paper/2111.00928/) (2021)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [YOLO-FaceV2: A Scale and Occlusion Aware Face Detector](https://mlsanity.com/paper/2208.02019/) (2022)
- [Reconcile Prediction Consistency for Balanced Object Detection](https://mlsanity.com/paper/2108.10809/) (2021)
- [Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images](https://mlsanity.com/paper/2407.19696/) (2024)
- [Mutual Supervision for Dense Object Detection](https://mlsanity.com/paper/2109.05986/) (2021)
- [Ranking-Based Siamese Visual Tracking](https://mlsanity.com/paper/2205.11761/) (2022)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [One-to-Few Label Assignment for End-to-End Dense Detection](https://mlsanity.com/paper/2303.11567/) (2023)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://mlsanity.com/paper/2211.08248/) (2022)
- [Zone Evaluation: Revealing Spatial Bias in Object Detection](https://mlsanity.com/paper/2310.13215/) (2023)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)
- [SCD: A Stacked Carton Dataset for Detection and Segmentation](https://mlsanity.com/paper/2102.12808/) (2021)
- [Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning](https://mlsanity.com/paper/2112.07015/) (2021)
- [An Empirical Study of Adder Neural Networks for Object Detection](https://mlsanity.com/paper/2112.13608/) (2021)
- [Adaptive Instance Distillation for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2201.11097/) (2022)
- [Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategies](https://mlsanity.com/paper/2403.07113/) (2024)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection](https://mlsanity.com/paper/2104.14082/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)

## Abstract (arXiv)

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.