Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection

• URL: http://arxiv.org/abs/2604.23344v1
• Date: Sat, 25 Apr 2026 15:06:07 GMT
• Title: Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
• Abstract summary: We propose a novel pseudo labeling framework for open-vocabulary object detection (OVD)<n>Our approach introduces a hierarchical confidence calibration (HCC) technique, which ensures reliable class label estimation.<n>We also present LoCLIP, a parameter-efficient adaptation of CLIP that incorporates an objectness token to mitigate base class bias problem.
• Score: 38.31141459207419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during training. Open-vocabulary object detection (OVD) addresses this limitation by leveraging vision-language models (VLMs) to generate pseudo labels for novel object classes. However, existing OVD methods suffer from two critical drawbacks: (1) inaccurate class label assignments, as VLMs are optimized for image-level predictions rather than the region-level predictions required for pseudo labeling, and (2) unreliable objectness scores from region proposal networks (RPNs) trained exclusively on base object classes. To address these issues, we propose a novel pseudo labeling framework for OVD. Our approach introduces a hierarchical confidence calibration (HCC) technique, which ensures reliable class label estimation by assessing consistency across hierarchical semantic levels (class, super- and sub-category). We also present LoCLIP, a parameter-efficient adaptation of CLIP that incorporates an objectness token to mitigate base class bias problem of RPNs and provide reliable objectness estimations for novel object classes. Extensive experiments on standard OVD benchmarks, including COCO and LVIS, demonstrate that our approach clearly sets a new state of the art, validating the effectiveness of our approach. Project site: https://cvlab.yonsei.ac.kr/projects/HCC

Related papers

• SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection [19.35154888756369]
  A consistent trend throughout the research of oriented object detection has been the pursuit of maintaining comparable performance with fewer and weaker annotations.<n>This is particularly crucial in the remote sensing domain, where the dense object distribution and a wide variety of categories contribute to prohibitively high costs.<n>We introduce the first Sparse Partial Weakly-Supervised Oriented Object Detection framework, designed to efficiently leverage only a few weakly-labeled data and plenty of unlabeled data.
  arXiv  Detail & Related papers  (2026-02-03T15:21:01Z)
• Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models [86.53246292425699]
  We present BCA+, a training-free framework for TTA for both object recognition and detection.<n>We formulate adaptation as a Bayesian inference problem, where final predictions are generated by fusing the initial VLM output with a cache-based prediction.<n>BCA+ achieves state-of-the-art performance on both recognition and detection benchmarks.
  arXiv  Detail & Related papers  (2025-10-03T06:27:33Z)
• Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection [20.748630029722257]
  Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes.<n>Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness recognition and foreground classification within shared feature spaces.<n>We propose a Uniform Orthogonal Feature Space (UOFS) optimization framework to transfer class-agnostic objectness knowledge from base classes to novel classes.
  arXiv  Detail & Related papers  (2025-06-27T12:17:04Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes.<n>Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes.<n>We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation [3.0899016152680754]
  Open-vocabulary object detection (OVOD) aims at localizing and recognizing visual objects from novel classes unseen at the training time. This paper systematically investigates this problem with the commonly-adopted two-stage OVOD paradigm. To alleviate this problem, this paper introduces two advanced measures to adjust confidence scores and conserve erroneously dismissed objects.
  arXiv  Detail & Related papers  (2024-04-12T17:02:56Z)
• Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning [13.667326007851674]
  We propose CastDet, a CLIP-activated student-teacher open-vocabulary object detection framework. Our approach boosts not only novel object proposals but also classification. Experimental results demonstrate our CastDet achieving superior open-vocabulary detection performance.
  arXiv  Detail & Related papers  (2023-11-20T10:26:04Z)
• DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection [72.25697820290502]
  This work introduces a straightforward and efficient strategy to identify potential novel classes through zero-shot classification. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance.
  arXiv  Detail & Related papers  (2023-10-02T17:52:24Z)
• EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment [28.983503845298824]
  We propose Early Dense Alignment (EDA) to bridge the gap between generalizable local semantics and object-level prediction. In EDA, we use object-level supervision to learn the dense-level rather than object-level alignment to maintain the local fine-grained semantics.
  arXiv  Detail & Related papers  (2023-09-03T12:04:14Z)
• Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
  We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels. ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
  arXiv  Detail & Related papers  (2023-03-27T07:46:58Z)
• UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation [84.16372642822495]
  We propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called textbfUDA-COPE. Inspired by the recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain labels.
  arXiv  Detail & Related papers  (2021-11-24T16:00:48Z)
• Aligning Pretraining for Detection via Object-Level Contrastive Learning [57.845286545603415]
  Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task. Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection.
  arXiv  Detail & Related papers  (2021-06-04T17:59:52Z)

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.