Pith. sign in

REVIEW 2 minor 50 references

A target-guided module dynamically weights text and image prompts to align modalities in open-set object detection.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-29 13:42 UTC pith:SJFYFZNY

load-bearing objection This paper defines LV-OSD as mixed text-image prompt open-set detection and offers a dual-branch model with TPDW weighting and PRM masking, but the abstract supplies no numbers to check whether it works.

arxiv 2605.28271 v1 pith:SJFYFZNY submitted 2026-05-27 cs.CV

LV-OSD: Language-Vision-Complementary Open-Set Object Detection

Yupeng Zhang , Ruize Han , Wei Feng , Song Wang , Liang Wan This is my paper
classification cs.CV
keywords open-set object detectionmulti-modal promptstext and image promptsdynamic weightingprompt maskinglanguage vision complementaryobject detection
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper defines LV-OSD as open-set object detection that accepts text descriptions, image examples, or both to specify categories. It introduces the LVDor dual-branch framework that first assembles multi-modal prompts for each category and then applies the TPDW module to adjust the contribution of each prompt type according to information drawn from the input image itself. This dynamic adjustment is meant to close the semantic gap between the modalities and support any combination of prompts at test time through a random masking step in training. A reader would care because real applications often supply mixed or incomplete prompts rather than clean single-modality lists.

Core claim

The authors establish that the Target-guided Prompt Dynamic Weighting module, guided by prior information extracted from the target image, dynamically produces the text and image prompts that best align with the target semantics, achieving precise alignment and effectively reducing the discrepancy between the two modalities, thereby accommodating the LV-OSD setting.

What carries the argument

Target-guided Prompt Dynamic Weighting (TPDW) module that uses target-image priors to set dynamic weights on text and image prompts for modality alignment.

Load-bearing premise

Prior information extracted from the target image is sufficient to determine weights that optimally align text and image prompts.

What would settle it

An ablation experiment in which fixed or uniform prompt weights produce detection accuracy equal to or higher than the full TPDW module on LV-OSD benchmarks would show that the dynamic weighting step does not deliver the claimed alignment benefit.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • The dual-branch architecture accepts text prompts, image prompts, or both at the same time.
  • Prompt random masking during training prepares the model for arbitrary prompt combinations at inference.
  • The weighting step reduces semantic discrepancy among the input image, text prompts, and image prompts.
  • Experiments confirm the formulation and the method work on the proposed LV-OSD task.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same image-prior weighting idea could be tested on other vision-language tasks that fuse separate prompt sources.
  • Image content might serve as a general reference signal for deciding how much to trust language versus visual prompts.
  • Performance when one prompt type is missing or low-quality would reveal whether the dynamic mechanism still functions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

0 major / 2 minor

Summary. The paper introduces LV-OSD, a new open-set object detection setting allowing flexible text-based and/or image-based prompts to specify object categories. It proposes the LVDor dual-branch framework that accepts both modalities, constructs Multi-modal Prompts (MPr) per category, introduces the Target-guided Prompt Dynamic Weighting (TPDW) module that uses target-image priors to dynamically weight and align text and image prompts, and adds a Prompt Random Masking (PRM) mechanism during training to simulate arbitrary prompt combinations at test time. The authors assert that extensive experiments confirm both the problem formulation's practicality and the method's effectiveness, with code and prompts to be released.

Significance. If the experimental claims hold, the work addresses a practically relevant extension of open-set detection by supporting mixed language-vision prompts. The TPDW design offers a concrete mechanism for reducing cross-modal discrepancy via target-guided dynamic weighting, and the PRM training strategy is a straightforward way to handle prompt variability. Public release of prompts and code would strengthen reproducibility. The contribution is primarily architectural and engineering-oriented rather than theoretical.

minor comments (2)
  1. [Abstract] Abstract: the sentence fragment 'which aims to detect the objects of interest. through the given category list' contains a typographical error (extraneous period and incorrect capitalization).
  2. [Abstract] Abstract: the claim of 'extensive experimental results' is stated without any numerical values, tables, or baseline comparisons in the provided abstract; the full experimental section should be checked for quantitative support of the central effectiveness claim.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our LV-OSD problem setting and the LVDor framework, including the TPDW and PRM components, and for recommending minor revision. The summary accurately reflects the manuscript's focus on practical mixed-modality prompting for open-set detection.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper introduces LV-OSD as a new problem formulation and presents LVDor as a dual-branch architecture with MPr construction, the TPDW module (guided by target-image priors for dynamic prompt weighting), and PRM for training. These are described as engineering design choices whose effectiveness is asserted via experiments. No equations, derivations, fitted parameters renamed as predictions, or self-citation chains appear in the provided text that reduce any claimed result to its inputs by construction. The central claims remain independent of tautological definitions or load-bearing self-references.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

The work rests on standard deep-learning assumptions for feature alignment and prompt fusion; no free parameters or invented physical entities are described in the abstract.

axioms (1)
  • domain assumption Neural networks can learn cross-modal alignments when guided by target-image features.
    Implicit in the design of the TPDW module.
invented entities (2)
  • TPDW module no independent evidence
    purpose: Dynamically weight text and image prompts using target-image guidance.
    New component introduced to bridge modality gap.
  • PRM mechanism no independent evidence
    purpose: Randomly mask prompts during training to simulate test-time combinations.
    New training strategy for the LV-OSD setting.

pith-pipeline@v0.9.1-grok · 5781 in / 1228 out tokens · 41654 ms · 2026-06-29T13:42:00.542547+00:00 · methodology

0 comments
read the original abstract

Object detection is an important task in computer vision, which aims to detect the objects of interest. through the given category list or query images. In this work, we propose a new problem of language-visual-complementary open-set object detection (LV-OSD), i.e., using the flexible text-based and/or image-based prompts to specify the desired object categories. This setting is more common and practical in real-world applications. For this purpose, we design a dual-branch detection framework, LVDor, which can simultaneously accept both text and image prompts. Specifically, we first build the Multi-modal Prompts (MPr) containing various text descriptions and image samples for each category. Subsequently, to bridge the semantic gap among the input image, text prompts, and image prompts, we design a Target-guided Prompt Dynamic Weighting (TPDW) module. Guided by the prior information of the target image, this module dynamically produces the text and image prompts that best align with the target semantics, achieving precise alignment and effectively reducing the discrepancy between the two modalities, thereby accommodating the LV-OSD setting. We also propose a simple Prompt Random Masking (PRM) mechanism during training to simulate the arbitrary combination of text and/or image prompts in testing. Extensive experimental results verify our problem formulation's reasonability and our method's effectiveness. Prompts and code will be released publicly.

Figures

Figures reproduced from arXiv: 2605.28271 by Liang Wan, Ruize Han, Song Wang, Wei Feng, Yupeng Zhang.

Figure 1
Figure 1. Figure 1: Illustration of the Language-Vision-Complementary Open-Set Object [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of our method. We employ a LLM to generate category descriptions and collect representative images to construct a comprehensive set [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustration of the modality gap in OVD with different modality [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visualization of detection results. traits, semantic attributes, and potential variations. The com￾plete generation process is detailed in the subsection Text￾based category description generation. Meanwhile, [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Category descriptions of the OV-LVIS dataset. [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Image examples for each category of the OV-LVIS dataset. [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

50 extracted references · 9 canonical work pages · 2 internal anchors

  1. [1]

    You only look once: Unified, real-time object detection

    Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , IN SUBMISSION 10 Airplane Ambulance Artichoke Avocado Armchair Flamin...

    2016

  2. [2]

    Faster r-cnn: Towards real-time object detection with region proposal networks.IEEE transactions on pattern analysis and machine intelligence, 39(6):1137– 1149, 2016

    Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks.IEEE transactions on pattern analysis and machine intelligence, 39(6):1137– 1149, 2016

    2016

  3. [3]

    Towards open-set object detection and discovery

    Jiyang Zheng, Weihao Li, Jie Hong, Lars Petersson, and Nick Barnes. Towards open-set object detection and discovery. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3961–3970, 2022

    2022

  4. [4]

    Open-vocabulary object detection using captions

    Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu, and Shih-Fu Chang. Open-vocabulary object detection using captions. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14393–14402, 2021

    2021

  5. [5]

    Few-shot object detection via improved classification features

    Xinyu Jiang, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, and Duoqian Miao. Few-shot object detection via improved classification features. InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 5386–5395, 2023

    2023

  6. [6]

    Fine-grained prototypes distillation for few-shot object detection

    Zichen Wang, Bo Yang, Haonan Yue, and Zhenghao Ma. Fine-grained prototypes distillation for few-shot object detection. InProceedings of the AAAI conference on artificial intelligence, pages 5859–5866, 2024

    2024

  7. [7]

    Balanced and hierarchical relation learning for one-shot object detection

    Hanqing Yang, Sijia Cai, Hualian Sheng, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Yong Tang, and Yu Zhang. Balanced and hierarchical relation learning for one-shot object detection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7591–7600, 2022

    2022

  8. [8]

    Exploring base-class suppression with prior guidance for bias-free one-shot object detection

    Wenwen Zhang, Yun Hu, Hangguan Shan, and Eryun Liu. Exploring base-class suppression with prior guidance for bias-free one-shot object detection. InProceedings of the AAAI Conference on Artificial Intelli- gence, pages 7314–7322, 2024

    2024

  9. [9]

    Toward generalized few-shot open-set object detection.IEEE Transactions on Image Processing, 33:1389–1402, 2024

    Binyi Su, Hua Zhang, Jingzhi Li, and Zhong Zhou. Toward generalized few-shot open-set object detection.IEEE Transactions on Image Processing, 33:1389–1402, 2024

    2024

  10. [10]

    Open-vocabulary detr with conditional matching

    Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, and Chen Change Loy. Open-vocabulary detr with conditional matching. InEuropean Conference on Computer Vision, pages 106–122. Springer, 2022

    2022

  11. [11]

    Multi-modal classi- fiers for open-vocabulary object detection

    Prannay Kaul, Weidi Xie, and Andrew Zisserman. Multi-modal classi- fiers for open-vocabulary object detection. InInternational Conference on Machine Learning, pages 15946–15969, 2023

    2023

  12. [12]

    Learning transferable visual models from natural language supervision

    Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. InInternational conference on machine learning, pages 8748–8763, 2021

    2021

  13. [13]

    Contrastive feature masking open-vocabulary vision transformer

    Dahun Kim, Anelia Angelova, and Weicheng Kuo. Contrastive feature masking open-vocabulary vision transformer. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 15602– 15612, 2023

    2023

  14. [14]

    Detection-oriented image-text pretraining for open-vocabulary detection.arXiv preprint arXiv:2310.00161, 2023

    Dahun Kim, Anelia Angelova, and Weicheng Kuo. Detection-oriented image-text pretraining for open-vocabulary detection.arXiv preprint arXiv:2310.00161, 2023

    work page arXiv 2023

  15. [15]

    Region-aware pre- training for open-vocabulary object detection with vision transformers

    Dahun Kim, Anelia Angelova, and Weicheng Kuo. Region-aware pre- training for open-vocabulary object detection with vision transformers. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11144–11154, 2023

    2023

  16. [16]

    Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching

    Xiaoshi Wu, Feng Zhu, Rui Zhao, and Hongsheng Li. Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7031–7040, 2023

    2023

  17. [17]

    Prompt-guided transformers for end-to-end open-vocabulary object detection.arXiv preprint arXiv:2303.14386, 2023

    Hwanjun Song and Jihwan Bang. Prompt-guided transformers for end-to-end open-vocabulary object detection.arXiv preprint arXiv:2303.14386, 2023

    work page arXiv 2023

  18. [18]

    Detecting twenty-thousand classes using image-level supervision

    Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Kr ¨ahenb¨uhl, and Ishan Misra. Detecting twenty-thousand classes using image-level supervision. InEuropean Conference on Computer Vision, pages 350– 368, 2022

    2022

  19. [19]

    Regionclip: Region-based language-image pretraining

    Yiwu Zhong, Jianwei Yang, Pengchuan Zhang, Chunyuan Li, Noel Codella, Liunian Harold Li, Luowei Zhou, Xiyang Dai, Lu Yuan, Yin Li, et al. Regionclip: Region-based language-image pretraining. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16793–16803, 2022

    2022

  20. [20]

    Proxydet: Synthesizing proxy novel classes via classwise mixup for open-vocabulary object detection

    Joonhyun Jeong, Geondo Park, Jayeon Yoo, Hyungsik Jung, and Heesu Kim. Proxydet: Synthesizing proxy novel classes via classwise mixup for open-vocabulary object detection. InProceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 2462–2470, 2024

    2024

  21. [21]

    Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection.Advances in neural information processing systems, 36, 2024

    Chuofan Ma, Yi Jiang, Xin Wen, Zehuan Yuan, and Xiaojuan Qi. Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection.Advances in neural information processing systems, 36, 2024

    2024

  22. [22]

    Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

    Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. Open-vocabulary object detection via vision and language knowledge distillation.arXiv preprint arXiv:2104.13921, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  23. [23]

    Lp-ovod: Open-vocabulary object detection by linear probing

    Chau Pham, Truong Vu, and Khoi Nguyen. Lp-ovod: Open-vocabulary object detection by linear probing. InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 779–788, 2024

    2024

  24. [24]

    Bridging the gap between object and image-level representations for open-vocabulary detection

    Hanoona Bangalath, Muhammad Maaz, Muhammad Uzair Khattak, Salman H Khan, and Fahad Shahbaz Khan. Bridging the gap between object and image-level representations for open-vocabulary detection. Advances in Neural Information Processing Systems, 35:33781–33794, 2022

    2022

  25. [25]

    Distilling detr with visual-linguistic knowledge for open-vocabulary object detection

    Liangqi Li, Jiaxu Miao, Dahu Shi, Wenming Tan, Ye Ren, Yi Yang, and Shiliang Pu. Distilling detr with visual-linguistic knowledge for open-vocabulary object detection. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 6501–6510, 2023

    2023

  26. [26]

    Learning to prompt for open-vocabulary object detection with vision-language model

    Yu Du, Fangyun Wei, Zihe Zhang, Miaojing Shi, Yue Gao, and Guoqi Li. Learning to prompt for open-vocabulary object detection with vision-language model. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14084–14093, 2022

    2022

  27. [27]

    F-vlm: Open-vocabulary object detection upon frozen vision and language models.arXiv preprint arXiv:2209.15639, 2022

    Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni, and Anelia Angelova. F-vlm: Open-vocabulary object detection upon frozen vision and language models.arXiv preprint arXiv:2209.15639, 2022

    work page arXiv 2022

  28. [28]

    Minderer, A

    M Minderer, A Gritsenko, A Stone, M Neumann, D Weissenborn, A Dosovitskiy, A Mahendran, A Arnab, M Dehghani, Z Shen, et al. Simple open-vocabulary object detection with vision transformers. arxiv 2022.arXiv preprint arXiv:2205.06230, 2, 2022

    work page arXiv 2022

  29. [29]

    CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

    Size Wu, Wenwei Zhang, Lumin Xu, Sheng Jin, Xiangtai Li, Wentao Liu, and Chen Change Loy. Clipself: Vision transformer distills itself for open-vocabulary dense prediction.arXiv preprint arXiv:2310.01403, 2023

    work page Pith review arXiv 2023

  30. [30]

    Dst-det: Open-vocabulary object detection via dynamic self-training.IEEE Transactions on Circuits and Systems for Video Technology, 2024

    Shilin Xu, Xiangtai Li, Size Wu, Wenwei Zhang, Yunhai Tong, and Chen Change Loy. Dst-det: Open-vocabulary object detection via dynamic self-training.IEEE Transactions on Circuits and Systems for Video Technology, 2024

    2024

  31. [31]

    Declip: Decoupled learning for open-vocabulary dense percep- tion

    Junjie Wang, Bin Chen, Yulin Li, Bin Kang, Yichi Chen, and Zhuotao Tian. Declip: Decoupled learning for open-vocabulary dense percep- tion. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 14824–14834, 2025

    2025

  32. [32]

    Integrally migrating pre-trained trans- former encoder-decoders for visual object detection

    Feng Liu, Xiaosong Zhang, Zhiliang Peng, Zonghao Guo, Fang Wan, Xiangyang Ji, and Qixiang Ye. Integrally migrating pre-trained trans- former encoder-decoders for visual object detection. InProceedings of the IEEE/CVF international conference on computer vision, pages 6825–6834, 2023. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , IN SUBM...

    2023

  33. [33]

    Snida: Unlocking few-shot object detection with non-linear semantic decoupling augmentation

    Yanjie Wang, Xu Zou, Luxin Yan, Sheng Zhong, and Jiahuan Zhou. Snida: Unlocking few-shot object detection with non-linear semantic decoupling augmentation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12544–12553, 2024

    2024

  34. [34]

    Temporal speciation network for few- shot object detection.IEEE Transactions on Multimedia, 25:8267–8278, 2023

    Xiaowei Zhao, Xianglong Liu, Yuqing Ma, Shihao Bai, Yifan Shen, Zeyu Hao, and Aishan Liu. Temporal speciation network for few- shot object detection.IEEE Transactions on Multimedia, 25:8267–8278, 2023

    2023

  35. [35]

    Binary similarity few-shot object detection with modeling of hard negative samples.IEEE Transactions on Multimedia, 26:4805–4818, 2024

    Yue Lu, Xingyu Chen, Zhengxing Wu, Min Tan, and Junzhi Yu. Binary similarity few-shot object detection with modeling of hard negative samples.IEEE Transactions on Multimedia, 26:4805–4818, 2024

    2024

  36. [36]

    Tung-I Chen, Yueh-Cheng Liu, Hung-Ting Su, Yu-Cheng Chang, Yu- Hsiang Lin, Jia-Fong Yeh, Wen-Chin Chen, and Winston H. Hsu. Dual- awareness attention for few-shot object detection.IEEE Transactions on Multimedia, 25:291–301, 2023

    2023

  37. [37]

    Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022

    Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022

    2022

  38. [38]

    DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

    Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforce- ment learning.arXiv preprint arXiv:2501.12948, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  39. [39]

    arXiv preprint arXiv:2104.10972 , year=

    Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, and Lihi Zelnik- Manor. Imagenet-21k pretraining for the masses.arXiv preprint arXiv:2104.10972, 2021

    work page arXiv 2021

  40. [40]

    Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning

    Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2556–2565, 2018

    2018

  41. [41]

    Mdetr-modulated detection for end- to-end multi-modal understanding

    Aishwarya Kamath, Mannat Singh, Yann LeCun, Gabriel Synnaeve, Ishan Misra, and Nicolas Carion. Mdetr-modulated detection for end- to-end multi-modal understanding. InProceedings of the IEEE/CVF international conference on computer vision, pages 1780–1790, 2021

    2021

  42. [42]

    Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123:32–73, 2017

    Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A Shamma, et al. Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123:32–73, 2017

    2017

  43. [43]

    Scaling up visual and vision-language representation learning with noisy text supervision

    Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. Scaling up visual and vision-language representation learning with noisy text supervision. InInternational conference on machine learning, pages 4904–4916, 2021

    2021

  44. [44]

    Learning background prompts to discover implicit knowledge for open vocabulary object detection

    Jiaming Li, Jiacheng Zhang, Jichang Li, Ge Li, Si Liu, Liang Lin, and Guanbin Li. Learning background prompts to discover implicit knowledge for open vocabulary object detection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16678–16687, 2024

    2024

  45. [45]

    Ov-dquo: Open-vocabulary detr with denoising text query training and open-world unknown objects supervision

    Junjie Wang, Bin Chen, Bin Kang, Yulin Li, Weizhi Xian, Yichi Chen, and Yong Xu. Ov-dquo: Open-vocabulary detr with denoising text query training and open-world unknown objects supervision. InProceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 7762–7770, 2025

    2025

  46. [46]

    Object-aware distillation pyramid for open-vocabulary object detection

    Luting Wang, Yi Liu, Penghui Du, Zihan Ding, Yue Liao, Qiaosong Qi, Biaolong Chen, and Si Liu. Object-aware distillation pyramid for open-vocabulary object detection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11186– 11196, 2023

    2023

  47. [47]

    Taming self-training for open-vocabulary object detection

    Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Yumin Suh, Manmohan Chandraker, Dimitris N Metaxas, et al. Taming self-training for open-vocabulary object detection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13938– 13947, 2024

    2024

  48. [48]

    Yolo-world: Real-time open-vocabulary object detection

    Tianheng Cheng, Lin Song, Yixiao Ge, Wenyu Liu, Xinggang Wang, and Ying Shan. Yolo-world: Real-time open-vocabulary object detection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16901–16911, 2024

    2024

  49. [49]

    Yoloe: Real-time seeing anything.arXiv preprint arXiv:2503.07465, 2025

    Ao Wang, Lihao Liu, Hui Chen, Zijia Lin, Jungong Han, and Guiguang Ding. Yoloe: Real-time seeing anything.arXiv preprint arXiv:2503.07465, 2025

    work page arXiv 2025

  50. [50]

    Objects365: A large-scale, high- quality dataset for object detection

    Shuai Shao, Zeming Li, Tianyuan Zhang, Chao Peng, Gang Yu, Xiangyu Zhang, Jing Li, and Jian Sun. Objects365: A large-scale, high- quality dataset for object detection. InProceedings of the IEEE/CVF international conference on computer vision, pages 8430–8439, 2019

    2019