# IQDet: Instance-wise Quality Distribution Sampling for Object Detection

arXiv: https://arxiv.org/abs/2104.06936 · HTML: https://mlsanity.com/paper/2104.06936/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 17 of 17)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://mlsanity.com/paper/2007.03496/) (2020)
- [Region Proposal by Guided Anchoring](https://mlsanity.com/paper/1901.03278/) (2019)
- [End-to-End Object Detection with Fully Convolutional Network](https://mlsanity.com/paper/2012.03544/) (2020)
- [Soft Anchor-Point Object Detection](https://mlsanity.com/paper/1911.12448/) (2019)
- [BorderDet: Border Feature for Dense Object Detection](https://mlsanity.com/paper/2007.11056/) (2020)
- [Fine-Grained Dynamic Head for Object Detection](https://mlsanity.com/paper/2012.03519/) (2020)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)

## Built on by (most cited first, 20 of 20)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2208.08738/) (2022)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [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)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [Prediction-Guided Distillation for Dense Object Detection](https://mlsanity.com/paper/2203.05469/) (2022)
- [R(Det)^2: Randomized Decision Routing for Object Detection](https://mlsanity.com/paper/2204.00794/) (2022)
- [DaDe: Delay-adaptive Detector for Streaming Perception](https://mlsanity.com/paper/2212.11558/) (2022)
- [Task-Specific Context Decoupling for Object Detection](https://mlsanity.com/paper/2303.01047/) (2023)
- [DiT: Efficient Vision Transformers with Dynamic Token Routing](https://mlsanity.com/paper/2308.03409/) (2023)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection](https://mlsanity.com/paper/2112.08902/) (2021)
- [YOLOSA: Object detection based on 2D local feature superimposed self-attention](https://mlsanity.com/paper/2206.11825/) (2022)
- [RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration](https://mlsanity.com/paper/2309.13257/) (2023)

## Abstract (arXiv)

We propose a dense object detector with an instance-wise sampling strategy, named IQDet. Instead of using human prior sampling strategies, we first extract the regional feature of each ground-truth to estimate the instance-wise quality distribution. According to a mixture model in spatial dimensions, the distribution is more noise-robust and adapted to the semantic pattern of each instance. Based on the distribution, we propose a quality sampling strategy, which automatically selects training samples in a probabilistic manner and trains with more high-quality samples. Extensive experiments on MS COCO show that our method steadily improves baseline by nearly 2.4 AP without bells and whistles. Moreover, our best model achieves 51.6 AP, outperforming all existing state-of-the-art one-stage detectors and it is completely cost-free in inference time.