Osprey: Pixel Understanding with Visual Instruction Tuning
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs primarily focus on image-level or box-level understanding, falling short in achieving fine-grained vision-language alignment at pixel level. Besides, the lack of mask-based instruction data limits their ad-vancements. In this paper, we propose Osprey, a mask-text instruction tuning approach, to extend MLLMs by incor-porating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual understanding. To achieve this goal, we first meticulously curate a mask-based region-text dataset with 724K samples, and then design a vision-language model by injecting pixel-level representation into LLM. Specifically, Osprey adopts a convolutional CLIP backbone as the vision encoder and employs a mask-aware visual extractor to extract precise visual mask features from high resolution input. Experimen-tal results demonstrate Osprey's superiority in various region understanding tasks, showcasing its new capability for pixel-level instruction tuning. In particular, Osprey can be integrated with Segment Anything Model (SAM) seamlessly to obtain multi-granularity semantics. The source code, dataset and demo can be found at https://github.com/CircleRadon/Osprey.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0981-7 · Cited by 5,107 · cited 1×
“Besides, Visual Genome (VG) [20] and Visual Commonsense Reasoning (VCR) [52] datasets are employed to add more multiple region understanding data.”
MethodLLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1516 · Cited by 2,428
Improved Baselines with Visual Instruction Tuning
Liu, H., Li, C., Li, Y., & Lee, Y. J. (2023) · arXiv · doi:10.48550/arxiv.2310.03744 · Cited by 1,733
Flamingo: a Visual Language Model for Few-Shot Learning
Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.14198 · Cited by 1,555
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · cited 1×
“Large language models (LLMs), such as GPT-3 [3], Flan-T5 [9], PaLM [8] and LLaMA [45], have significantly advanced the research on Natural Language Processing (NLP).”
BackgroundLVIS: A Dataset for Large Vocabulary Instance Segmentation
Gupta, A., Dollar, P., & Girshick, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00550 · Cited by 1,274 · cited 4×
“On LVIS [15], which has more than 1,200 object categories, our Osprey obtains 65.24% SS and 38.19% S-IoU, outperforming the state-of-the-art method by 1.46% and 1.62%, respectively.”
MethodInfluential(2016) · doi:10.1007/978-3-319-46475-6_5 · Cited by 1,081
Li, J., Li, D., Savarese, S., & Hoi, S. (2023) · arXiv · doi:10.48550/arxiv.2301.12597 · Cited by 908 · cited 1×
“The great successes of LLMs and MLLMs have also inspired the research on computer vision, enabling multimodal in-context learning [1, 26].”
BackgroundFrom Recognition to Cognition: Visual Commonsense Reasoning
Zellers, R., Bisk, Y., Farhadi, A., & Choi, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00688 · Cited by 769 · cited 1×
“Besides, Visual Genome (VG) [20] and Visual Commonsense Reasoning (VCR) [52] datasets are employed to add more multiple region understanding data.”
MethodLiu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · arXiv · doi:10.48550/arxiv.2304.08485 · Cited by 682
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., & Yuille, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.254 · Cited by 605
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023) · arXiv · doi:10.48550/arxiv.2304.10592 · Cited by 469 · cited 4×
“Prominent examples include LLaVA [33], MiniGPT-4 [55], mPLUG-Owl [48], Otter [22], Instruct-BLIP [12], Qwen-VL [2] and LLaVA-1.”
MethodInfluentialLISA: Reasoning Segmentation via Large Language Model
Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., & Jia, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00915 · Cited by 466
Self-citationQwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., & Zhou, J. (2023) · arXiv · doi:10.48550/arxiv.2308.12966 · Cited by 193 · cited 2×
“Prominent examples include LLaVA [33], MiniGPT-4 [55], mPLUG-Owl [48], Otter [22], Instruct-BLIP [12], Qwen-VL [2] and LLaVA-1.”
MethodPACO: Parts and Attributes of Common Objects
Ramanathan, V., Kalia, A., Petrovic, V., Wen, Y., Zheng, B., Guo, B., Wang, R., Marquez, A., Kovvuri, R., Kadian, A., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00690 · Cited by 79
Cited by
A survey on multimodal large language models
Yin, S., Fu, C., Zhao, S., Li, K., Sun, X., Xu, T., & Chen, E. (2024) · National Science Review · doi:10.1093/nsr/nwae403 · Cited by 893
Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349
Li, G., Xu, J., Zhao, Y., & Peng, Y. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.00850 · Cited by 12
“These include models that improve regional comprehension with additional data and training phrase [3, 57, 59], LLMs employing multi-tool combinations to extend visual capabilities [10, 50, 54], closed-source commercial chatbot systems (GPT-4V [28], Gemini Pro [41], Bard[8]), and visual search…”
UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation
Wu, L., Nie, Y., He, S., Zhuang, J., Luo, L., Li, T., Xie, Z., Chen, D., Zhao, Y., Mahboobani, N., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.21336 · Cited by 6
“Specifically, we extract bounding boxes from segmentation masks to indicate the ROIs following previous methods [14, 44–46].”
Zhu, M., Tian, Y., Chen, H., Zhou, C., Guo, Q., Liu, Y., Yang, M., & Shen, C. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.00349 · Cited by 5
“Following the implementation in [69], we adopted a ConvNeXt-L [34] CLIP model as the vision encoder, extracting image features from the ”res4” stage.”
Metadata
- Authors
- Yuan, Y., Li, W., Liu, J., Tang, D., Luo, X., Qin, C., Zhang, L., & Zhu, J.
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 28202-28211
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402727558
- Cited by
- 65
- References
- 22
- FWCI
- 14.19
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.