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

• URL: http://arxiv.org/abs/2608.12698v1
• Date: Thu, 13 Aug 2026 01:20:47 GMT
• Title: Class Geometry as Supervision for Sample-Efficient Open-World Detection
• Abstract summary: Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time.<n> Prototype-based detectors are natural for this regime, but they typically learn class prototypes as independent anchors.<n>We propose class-geometry supervision (CGS), a general framework that constrains learned prototype or class-grained spaces.
• Score: 6.8386326664004855
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection [6.732071883787906]
  We present FSP-DETR, a unified detection framework that enables robust few-shot detection, open-set recognition, and generalization to unseen biomedical tasks.<n>Built upon a class-agnostic DETR backbone, our approach constructs class prototypes from original support images and learns an embedding space using augmented views and a lightweight transformer decoder.<n>Tests across ova, blood cell, and malaria detection tasks demonstrate that FSP-DETR significantly outperforms prior few-shot and prototype-based detectors.
  arXiv  Detail & Related papers  (2025-10-10T17:38:40Z)
• Towards Effective Open-set Graph Class-incremental Learning [4.286860874195651]
  Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge.<n>Existing GCIL methods primarily focus on a closed-set assumption, where all test samples are presumed to belong to previously known classes.<n>We propose a more challenging open-set graph class-incremental learning scenario with two intertwined challenges: catastrophic forgetting of old classes, and inadequate open-set recognition.
  arXiv  Detail & Related papers  (2025-07-23T16:51:23Z)
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
  Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
  arXiv  Detail & Related papers  (2024-04-16T17:38:26Z)
• DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection [39.937724871284665]
  Generalized few-shot object detection aims to achieve precise detection on both base classes with abundant annotations and novel classes with limited training data. Existing approaches enhance few-shot generalization with the sacrifice of base-class performance. We propose a new training framework, DiGeo, to learn Geometry-aware features of inter-class separation and intra-class compactness.
  arXiv  Detail & Related papers  (2023-03-16T22:37:09Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Latent-Insensitive Autoencoders for Anomaly Detection and Class-Incremental Learning [0.0]
  We introduce Latent-Insensitive Autoencoder (LIS-AE) where unlabeled data from a similar domain is utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder. We treat class-incremental learning as multiple anomaly detection tasks by adding a different latent layer for each class and use other available classes in task as negative examples to shape each latent layer.
  arXiv  Detail & Related papers  (2021-10-25T16:53:49Z)
• Structure-Aware Feature Generation for Zero-Shot Learning [108.76968151682621]
  We introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to account for the topological structure in learning both the latent space and the generative networks. Our method significantly enhances the generalization capability on unseen-classes and consequently improve the classification performance.
  arXiv  Detail & Related papers  (2021-08-16T11:52:08Z)
• Conditional Variational Capsule Network for Open Set Recognition [64.18600886936557]
  In open set recognition, a classifier has to detect unknown classes that are not known at training time. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition. In our proposal, during training, capsules features of the same known class are encouraged to match a pre-defined gaussian, one for each class.
  arXiv  Detail & Related papers  (2021-04-19T09:39:30Z)
• UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation [52.487469544343305]
  Methods for object detection and segmentation rely on large scale instance-level annotations for training. We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
  arXiv  Detail & Related papers  (2020-06-12T22:45:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.