# DeepBox: Learning Objectness with Convolutional Networks

arXiv: https://arxiv.org/abs/1505.02146 · HTML: https://mlsanity.com/paper/1505.02146/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2015.

## Built on by (most cited first, 14 of 14)

- [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)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2206.06363/) (2022)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues](https://mlsanity.com/paper/2201.06696/) (2022)
- [Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision](https://mlsanity.com/paper/2303.05503/) (2023)
- [Superpixel-based Refinement for Object Proposal Generation](https://mlsanity.com/paper/2101.04574/) (2021)
- [RSG-Net: Towards Rich Sematic Relationship Prediction for Intelligent Vehicle in Complex Environments](https://mlsanity.com/paper/2207.12321/) (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)
- [Improving Open-World Object Localization by Discovering Background](https://mlsanity.com/paper/2504.17626/) (2025)
- [ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation](https://mlsanity.com/paper/2606.23835/) (2026)
- [Background-Free Objectness Learning for Class-Agnostic Detection](https://mlsanity.com/paper/2608.29232/) (2026)

## Abstract (arXiv)

Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object proposals. Our framework, which we call DeepBox, uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method. We use a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster. We show that DeepBox significantly improves over the bottom-up ranking, achieving the same recall with 500 proposals as achieved by bottom-up methods with 2000. This improvement generalizes to categories the CNN has never seen before and leads to a 4.5-point gain in detection mAP. Our implementation achieves this performance while running at 260 ms per image.