# Class Geometry as Supervision for Sample-Efficient Open-World Detection

arXiv: https://arxiv.org/abs/2608.12698 · HTML: https://mlsanity.com/paper/2608.12698/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Multi-Modal Classifiers for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.05493/) (2023)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [ProtoKD: Learning from Extremely Scarce Data for Parasite Ova Recognition](https://mlsanity.com/paper/2309.10210/) (2023)
- [FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection](https://mlsanity.com/paper/2510.09583/) (2025)

## Abstract (arXiv)

Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is especially challenging in scarce-data settings such as biomedical and scientific imaging, where rare categories may have only a few annotated examples and fine-grained classes differ by subtle morphology. Prototype-based detectors are natural for this regime, but they typically learn class prototypes as independent anchors, ignoring relational structure among classes. We propose class-geometry supervision (CGS), a general framework that constrains learned prototype or class-representation spaces to preserve visual or semantic class dissimilarities estimated from training data. CGS introduces a dissimilarity-preserving objective that aligns pairwise distances among learned class representations with a target class-geometry matrix while retaining the standard task loss. We instantiate the same objective across prototype recognition, few-shot biomedical object detection, open-set detection, novel-class insertion, and OWOD adaptation on COCO. Experiments show that CGS improves sample efficiency in recognition and ova detection, substantially strengthens novel-class insertion, and improves unknown recall on COCO while retaining much of the known-class detection performance. Ablations show that meaningful visual geometry provides the most reliable gains, while random geometry can help novel separation but is less consistent for few-shot detection. These results suggest that relational class geometry is an effective supervisory signal for building calibrated and extensible open-world detectors under limited supervision.