# CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching

arXiv: https://arxiv.org/abs/2303.13076 · HTML: https://mlsanity.com/paper/2303.13076/

## Key facts

- Cited by 133 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Open-Vocabulary DETR with Conditional Matching](https://mlsanity.com/paper/2203.11876/) (2022)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection](https://mlsanity.com/paper/2207.03482/) (2022)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Exploiting Unlabeled Data with Vision and Language Models for Object Detection](https://mlsanity.com/paper/2207.08954/) (2022)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)

## Built on by (most cited first, 30 of 133)

- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively](https://mlsanity.com/paper/2401.02955/) (2024)
- [A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future](https://mlsanity.com/paper/2307.09220/) (2023)
- [Aligning and Prompting Everything All at Once for Universal Visual Perception](https://mlsanity.com/paper/2312.02153/) (2023)
- [DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM](https://mlsanity.com/paper/2403.12488/) (2024)
- [The Double-Ellipsoid Geometry of CLIP](https://mlsanity.com/paper/2411.14517/) (2024)
- [Described Object Detection: Liberating Object Detection with Flexible Expressions](https://mlsanity.com/paper/2307.12813/) (2023)
- [ViTamin: Designing Scalable Vision Models in the Vision-Language Era](https://mlsanity.com/paper/2404.02132/) (2024)
- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2505.04410/) (2025)
- [LP-OVOD: Open-Vocabulary Object Detection by Linear Probing](https://mlsanity.com/paper/2310.17109/) (2023)
- [The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding](https://mlsanity.com/paper/2311.17518/) (2023)
- [Generative Region-Language Pretraining for Open-Ended Object Detection](https://mlsanity.com/paper/2403.10191/) (2024)
- [ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2502.08391/) (2025)
- [InstaGen: Enhancing Object Detection by Training on Synthetic Dataset](https://mlsanity.com/paper/2402.05937/) (2024)
- [Taming Self-Training for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2308.06412/) (2023)
- [Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection](https://mlsanity.com/paper/2406.00510/) (2024)
- [Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning](https://mlsanity.com/paper/2311.11646/) (2023)
- [OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision](https://mlsanity.com/paper/2405.17913/) (2024)
- [Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments](https://mlsanity.com/paper/2403.13556/) (2024)
- [Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head](https://mlsanity.com/paper/2403.06892/) (2024)
- [Retrieval-Augmented Open-Vocabulary Object Detection](https://mlsanity.com/paper/2404.05687/) (2024)
- [ChEX: Interactive Localization and Region Description in Chest X-rays](https://mlsanity.com/paper/2404.15770/) (2024)
- [LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction](https://mlsanity.com/paper/2407.11335/) (2024)
- [TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation](https://mlsanity.com/paper/2307.05134/) (2023)
- [Simple Image-level Classification Improves Open-vocabulary Object Detection](https://mlsanity.com/paper/2312.10439/) (2023)
- [Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach](https://mlsanity.com/paper/2404.11732/) (2024)
- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)

## Abstract (arXiv)

Open-vocabulary detection (OVD) is an object detection task aiming at detecting objects from novel categories beyond the base categories on which the detector is trained. Recent OVD methods rely on large-scale visual-language pre-trained models, such as CLIP, for recognizing novel objects. We identify the two core obstacles that need to be tackled when incorporating these models into detector training: (1) the distribution mismatch that happens when applying a VL-model trained on whole images to region recognition tasks; (2) the difficulty of localizing objects of unseen classes. To overcome these obstacles, we propose CORA, a DETR-style framework that adapts CLIP for Open-vocabulary detection by Region prompting and Anchor pre-matching. Region prompting mitigates the whole-to-region distribution gap by prompting the region features of the CLIP-based region classifier. Anchor pre-matching helps learning generalizable object localization by a class-aware matching mechanism. We evaluate CORA on the COCO OVD benchmark, where we achieve 41.7 AP50 on novel classes, which outperforms the previous SOTA by 2.4 AP50 even without resorting to extra training data. When extra training data is available, we train CORA^+ on both ground-truth base-category annotations and additional pseudo bounding box labels computed by CORA. CORA^+ achieves 43.1 AP50 on the COCO OVD benchmark and 28.1 box APr on the LVIS OVD benchmark.