paper-with-me

홈 › Papers

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

2025-12-13 · Shenghao Fu, Yukun Su, Fengyun Rao, Jing Lyu, Xiaohua Xie, Wei-Shi Zheng arxiv

Open-vocabulary object detection aims to detect arbitrary classes via text prompts. Methods without cross-modal fusion layers (non-fusion) offer faster inference by treating recognition as a retrieval problem, \ie, matching regions to text queries in a shared embedding space. In this work, we fully explore this retrieval philosophy and demonstrate its unique advantages in efficiency and versatility through a model family named WeDetect: (1) State-of-the-art performance. WeDetect is a real-time detector with a dual-tower architecture. We show that, with well-curated data and full training, the non-fusion WeDetect surpasses other fusion models and establishes a strong open-vocabulary foundation. (2) Fast backtrack of historical data. WeDetect-Uni is a universal proposal generator based on WeDetect. We freeze the entire detector and only finetune an objectness prompt to retrieve generic object proposals across categories. Importantly, the proposal embeddings are class-specific and enable a new application, object retrieval, supporting retrieval objects in historical data. (3) Integration with LMMs for referring expression comprehension (REC). We further propose WeDetect-Ref, an LMM-based object classifier to handle complex referring expressions, which retrieves target objects from the proposal list extracted by WeDetect-Uni. It discards next-token prediction and classifies objects in a single forward pass. Together, the WeDetect family unifies detection, proposal generation, object retrieval, and REC under a coherent retrieval framework, achieving state-of-the-art performance across 15 benchmarks with high inference efficiency.

📄 PDF Abstract BibTeX arXiv:2512.12309

Code (0)

등록된 구현이 없습니다.

Tasks

Referring ExpressionObject Detection

Similar Papers 제목 키워드 기반

Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection

2023-03-25 · Hwanjun Song, Jihwan Bang

Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classe…

Decoderobject-detectionObject DetectionOpen-vocabulary object detection+3

Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

2024-12-23 · Yitong Chen, Wenhao Yao, Lingchen Meng, Sihong Wu 외

Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recog…

object-detectionObject DetectionObject RecognitionOpen-vocabulary object detection+1

OVA-DETR: Open Vocabulary Aerial Object Detection Using Image-Text Alignment and Fusion

2024-08-22 · Guoting Wei, Xia Yuan, Yu Liu, Zhenhao Shang 외

Aerial object detection has been a hot topic for many years due to its wide application requirements. However, most existing approaches can only handle predefined categories, which limits their applicability for the open…

Decoderobject-detectionObject Detection

Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation

2017-11-27 · EMNLP 2018 10 · Ryota Hinami, Shin'ichi Satoh

Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can o…

Objectobject-detectionObject DetectionRetrieval

Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation

2024-06-04 · Mohamed El Amine Boudjoghra, Angela Dai, Jean Lahoud, Hisham Cholakkal 외

Recent works on open-vocabulary 3D instance segmentation show strong promise, but at the cost of slow inference speed and high computation requirements. This high computation cost is typically due to their heavy reliance…

2D Object Detection3D Instance Segmentation3D Open-Vocabulary Instance SegmentationInstance Segmentation+4