# Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection

arXiv: https://arxiv.org/abs/2212.05706 · HTML: https://mlsanity.com/paper/2212.05706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 15 of 15)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Adaptive NMS: Refining Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1904.03629/) (2019)
- [SeGAN: Segmenting and Generating the Invisible](https://mlsanity.com/paper/1703.10239/) (2017)
- [Robust Instance Segmentation through Reasoning about Multi-Object Occlusion](https://mlsanity.com/paper/2012.02107/) (2020)
- [MT-ORL: Multi-Task Occlusion Relationship Learning](https://mlsanity.com/paper/2108.05722/) (2021)

## Abstract (arXiv)

In object detection, post-processing methods like Non-maximum Suppression (NMS) are widely used. NMS can substantially reduce the number of false positive detections but may still keep some detections with low objectness scores. In order to find the exact number of objects and their labels in the image, we propose a post processing method called Detection Selection Algorithm (DSA) which is used after NMS or related methods. DSA greedily selects a subset of detected bounding boxes, together with full object reconstructions that give the interpretation of the whole image with highest likelihood, taking into account object occlusions. The algorithm consists of four components. First, we add an occlusion branch to Faster R-CNN to obtain occlusion relationships between objects. Second, we develop a single reconstruction algorithm which can reconstruct the whole appearance of an object given its visible part, based on the optimization of latent variables of a trained generative network which we call the decoder. Third, we propose a whole reconstruction algorithm which generates the joint reconstruction of all objects in a hypothesized interpretation, taking into account occlusion ordering. Finally we propose a greedy algorithm that incrementally adds or removes detections from a list to maximize the likelihood of the corresponding interpretation. DSA with NMS or Soft-NMS can achieve better results than NMS or Soft-NMS themselves, as is illustrated in our experiments on synthetic images with mutiple 3d objects.