# What leads to generalization of object proposals?

arXiv: https://arxiv.org/abs/2008.05700 · HTML: https://mlsanity.com/paper/2008.05700/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

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

- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models](https://mlsanity.com/paper/2209.15639/) (2022)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/2104.10719/) (2021)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Extending One-Stage Detection with Open-World Proposals](https://mlsanity.com/paper/2201.02302/) (2022)
- [Tunable Hybrid Proposal Networks for the Open World](https://mlsanity.com/paper/2208.11050/) (2022)
- [Generalized Open-World Semi-Supervised Object Detection](https://mlsanity.com/paper/2307.15710/) (2023)

## Abstract (arXiv)

Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help scaling detection models to larger number of classes with fewer annotations. Motivated by this, we study how a detection model trained on a small set of source classes can provide proposals that generalize to unseen classes. We systematically study the properties of the dataset - visual diversity and label space granularity - required for good generalization. We show the trade-off between using fine-grained labels and coarse labels. We introduce the idea of prototypical classes: a set of sufficient and necessary classes required to train a detection model to obtain generalized proposals in a more data-efficient way. On the Open Images V4 dataset, we show that only 25% of the classes can be selected to form such a prototypical set. The resulting proposals from a model trained with these classes is only 4.3% worse than using all the classes, in terms of average recall (AR). We also demonstrate that Faster R-CNN model leads to better generalization of proposals compared to a single-stage network like RetinaNet.