# Background-Free Objectness Learning for Class-Agnostic Detection

arXiv: https://arxiv.org/abs/2608.29232 · HTML: https://mlsanity.com/paper/2608.29232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (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)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [Solving Missing-Annotation Object Detection with Background Recalibration Loss](https://mlsanity.com/paper/2002.05274/) (2020)
- [Soft Sampling for Robust Object Detection](https://mlsanity.com/paper/1806.06986/) (2018)
- [Object Detection as a Positive-Unlabeled Problem](https://mlsanity.com/paper/2002.04672/) (2020)
- [Class-agnostic Object Detection](https://mlsanity.com/paper/2011.14204/) (2020)
- [DeepBox: Learning Objectness with Convolutional Networks](https://mlsanity.com/paper/1505.02146/) (2015)
- [Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects](https://mlsanity.com/paper/1811.10862/) (2018)
- [SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining](https://mlsanity.com/paper/2201.04620/) (2022)
- [DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection](https://mlsanity.com/paper/2406.14924/) (2024)
- [GOOD: Exploring Geometric Cues for Detecting Objects in an Open World](https://mlsanity.com/paper/2212.11720/) (2022)
- [Improving Open-World Object Localization by Discovering Background](https://mlsanity.com/paper/2504.17626/) (2025)

## Abstract (arXiv)

Object detectors are typically trained under closed-set supervision, where unlabeled regions are implicitly treated as background. Under incomplete annotations, this assumption introduces objectness bias: visually valid but unlabeled objects are used as negatives, tying objectness to the annotated taxonomy rather than generic object structure. This limitation is particularly problematic for class-agnostic and open-world detection. This paper proposes Background-Free Objectness Learning (B-FOR), a dense class-agnostic detection framework that learns objectness without explicit background supervision on unlabeled regions. B-FOR formulates detection as the prediction of dense multi-scale object-center and scale fields, from which object hypotheses emerge as local spatial structures. Supervision is confined to reliable annotated regions through spatially structured soft targets, avoiding foreground-background discrimination. To support decoding from emergent local maxima, the paper further introduces displacement-aware scale fields that model object extent as a spatially varying property of the learned objectness field. Experiments on PASCAL VOC, MS-COCO, and Open Images demonstrate strong generalization to unseen categories and cross-dataset object distributions. B-FOR improves recall by more than +10 AR points over prior class-agnostic baselines. Ablation studies show that both localized objectness supervision and displacement-aware scale fields are critical for class-agnostic localization under incomplete annotations. Code available at: https://github.com/Daniaawan/B-FOR.