ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification

• URL: http://arxiv.org/abs/2606.09360v1
• Date: Mon, 08 Jun 2026 11:34:32 GMT
• Title: ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
• Abstract summary: open-domain open-vocabulary detection requires detectors to generalize to both novel categories and unseen domains.<n>We propose ExDet, a lightweight category-domain collaborative generalization framework for ODOVD.<n>ExDet consists of Text-Guided Extrapolation (TGE), a Detector lightweight- Rectification (DCR) module, and ExRPN.
• Score: 36.08597733817782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-domain open-vocabulary detection (ODOVD) requires detectors to generalize to both novel categories and unseen domains, making it more challenging than open-vocabulary detection. Existing methods typically train open-vocabulary detectors together with domain generalization modules from scratch, leading to high training cost. we propose ExDet, a lightweight category-domain collaborative generalization framework for ODOVD that enhances the cross-category and cross-domain generalization of existing detectors. ExDet consists of Text-Guided Extrapolation (TGE), a lightweight Detector-Compatible Rectification (DCR) module, and ExRPN. Specifically, TGE exploits the DeltaSpace property of vision-language models (VLMs) to infer category- and domain-aware proxy visual prototypes from text. DCR is learned from the TGE-generated prototypes in a detector training-free and real-data-free manner, and is inserted after the classification head at inference to rectify representations toward a detector-compatible source-domain visual distribution, thereby enhancing classification for targets from novel categories and unseen domains. ExRPN recalibrates proposal scores by combining semantic similarity with RPN confidence, improving recall for novel and domain-shifted objects while providing better support for subsequent classification and DCR. ExDet achieves SOTA performance on OD-LVIS, OV-LVIS, Objects365, and MSOSB.

Related papers

• LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation [43.56251979741165]
  Domain Generalization Semantic (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains.<n>Style randomization distorts the underlying feature manifold due to its coarse-grained nature.<n>Feature normalization suppresses discnative, domain-sensitive semantic details owing to its rigid design.
  arXiv  Detail & Related papers  (2026-08-09T16:43:04Z)
• Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining [54.999230823851384]
  Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories.<n>We propose a category-level collaboration knowledge mining strategy that exploits both inter-class and intra-class relationships across domains.<n>Our method consistently surpasses state-of-the-art AOOD methods by 1.1-5.5 mAP.
  arXiv  Detail & Related papers  (2026-04-13T08:51:01Z)
• Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection [33.35667602014138]
  HSA-DINO is a parameter-efficient semantic augmentation framework for enhancing open-vocabulary object detection.<n>We introduce a semantic-aware router that dynamically selects the appropriate semantic augmentation strategy during inference.<n>We evaluate HSA-DINO on OV-COCO, several vertical domain datasets, and modified benchmark settings.
  arXiv  Detail & Related papers  (2026-04-06T05:41:33Z)
• Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection [25.15191353465313]
  Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel classes in unseen target domains given only a few labeled examples.<n>We propose a dual-branch detector that Learns Multi-modal Prototypes, dubbed LMP, by coupling textual guidance with visual exemplars drawn from the target domain.
  arXiv  Detail & Related papers  (2026-02-21T12:10:48Z)
• LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection [53.988759250627425]
  We introduce training-free one-shot domain generalization for object detection.<n>We project each exemplar into a descriptive text that conditions and guides a frozen detector.<n>We evaluate on UODD (underwater) and NEU-DET (industrial defects)
  arXiv  Detail & Related papers  (2026-02-06T08:03:04Z)
• Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection [7.768332621617199]
  Single-source domain generalization aims to develop a detector using only source domain data that generalizes well to unseen target domains.<n>Existing methods are primarily CNN-based and improve robustness through data augmentation combined with feature alignment.<n>We propose Style-Adaptive DEtection TRansformer (SA-DETR), a DETR-based detector tailored for single-source domain generalization.
  arXiv  Detail & Related papers  (2025-04-29T07:38:37Z)
• DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment [7.768332621617199]
  We introduce a strong DETR-based detector named Domain Adaptive detection TRansformer ( DATR) for unsupervised domain adaptation of object detection. Our proposed DATR incorporates a mean-teacher based self-training framework, utilizing pseudo-labels generated by the teacher model to further mitigate domain bias. Experiments demonstrate superior performance and generalization capabilities of our proposed DATR in multiple domain adaptation scenarios.
  arXiv  Detail & Related papers  (2024-05-20T03:48:45Z)
• Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation [30.606689882397223]
  Unsupervised domain adaptation (UDA) techniques are vital for semantic segmentation in geosciences. Most existing UDA methods, which focus on domain alignment at the high-level feature space, struggle to simultaneously retain local spatial details and global contextual semantics. A novel decomposition scheme is proposed to guide domain-invariant representation learning.
  arXiv  Detail & Related papers  (2024-04-06T07:13:49Z)
• Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector [72.05791402494727]
  This paper studies the challenging cross-domain few-shot object detection (CD-FSOD) It aims to develop an accurate object detector for novel domains with minimal labeled examples.
  arXiv  Detail & Related papers  (2024-02-05T15:25:32Z)
• MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection [80.83725644958633]
  Current deepfake generation methods leave discriminative artifacts in the frequency spectrum of fake images and videos. We present a novel approach, termed as MD-CSDNetwork, for combining the features in the spatial and frequency domains to mine a shared discriminative representation.
  arXiv  Detail & Related papers  (2021-09-15T14:11:53Z)
• Cross-domain Detection via Graph-induced Prototype Alignment [114.8952035552862]
  We propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment. In addition, in order to alleviate the negative effect of class-imbalance on domain adaptation, we design a Class-reweighted Contrastive Loss. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-03-28T17:46:55Z)
• Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN [117.80737222754306]
  We present a novel universal object detector called Universal-RCNN. We first generate a global semantic pool by integrating all high-level semantic representation of all the categories. An Intra-Domain Reasoning Module learns and propagates the sparse graph representation within one dataset guided by a spatial-aware GCN.
  arXiv  Detail & Related papers  (2020-02-18T07:57:45Z)

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.