# Extending One-Stage Detection with Open-World Proposals

arXiv: https://arxiv.org/abs/2201.02302 · HTML: https://mlsanity.com/paper/2201.02302/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 7 Jan 2022.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation](https://mlsanity.com/paper/1503.00848/) (2015)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [DenseBox: Unifying Landmark Localization with End to End Object Detection](https://mlsanity.com/paper/1509.04874/) (2015)
- [Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution](https://mlsanity.com/paper/1909.06720/) (2019)
- [Object Detection as a Positive-Unlabeled Problem](https://mlsanity.com/paper/2002.04672/) (2020)
- [Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization](https://mlsanity.com/paper/1606.04446/) (2016)
- [MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection](https://mlsanity.com/paper/2009.11528/) (2020)
- [What leads to generalization of object proposals?](https://mlsanity.com/paper/2008.05700/) (2020)
- [An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches](https://mlsanity.com/paper/1804.09003/) (2018)

## Built on by (most cited first, 9 of 9)

- [Open-vocabulary Panoptic Segmentation with Embedding Modulation](https://mlsanity.com/paper/2303.11324/) (2023)
- [Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection](https://mlsanity.com/paper/2203.13903/) (2022)
- [GOOD: Exploring Geometric Cues for Detecting Objects in an Open World](https://mlsanity.com/paper/2212.11720/) (2022)
- [Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization](https://mlsanity.com/paper/2208.09023/) (2022)
- [OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation](https://mlsanity.com/paper/2303.15859/) (2023)
- [Tunable Hybrid Proposal Networks for the Open World](https://mlsanity.com/paper/2208.11050/) (2022)
- [OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery](https://mlsanity.com/paper/2404.10865/) (2024)
- [UNCOVER: Unknown Class Object Detection for Autonomous Vehicles in Real-time](https://mlsanity.com/paper/2412.03986/) (2024)
- [Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary](https://mlsanity.com/paper/2609.36426/) (2026)

## Abstract (arXiv)

In many applications, such as autonomous driving, hand manipulation, or robot navigation, object detection methods must be able to detect objects unseen in the training set. Open World Detection(OWD) seeks to tackle this problem by generalizing detection performance to seen and unseen class categories. Recent works have seen success in the generation of class-agnostic proposals, which we call Open-World Proposals(OWP), but this comes at the cost of a big drop on the classification task when both tasks are considered in the detection model. These works have investigated two-stage Region Proposal Networks (RPN) by taking advantage of objectness scoring cues; however, for its simplicity, run-time, and decoupling of localization and classification, we investigate OWP through the lens of fully convolutional one-stage detection network, such as FCOS. We show that our architectural and sampling optimizations on FCOS can increase OWP performance by as much as 6% in recall on novel classes, marking the first proposal-free one-stage detection network to achieve comparable performance to RPN-based two-stage networks. Furthermore, we show that the inherent, decoupled architecture of FCOS has benefits to retaining classification performance. While two-stage methods worsen by 6% in recall on novel classes, we show that FCOS only drops 2% when jointly optimizing for OWP and classification.