Prompt-aligned Gradient for Prompt Tuning
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
Thanks to the large pre-trained vision-language models (VLMs) like CLIP [37], we can craft a zero-shot classifier by discrete prompt design, e.g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided similarity between the image and the prompt sentence "a photo of a [CLASS]". Furthermore, prompting shows great potential for fast adaptation of VLMs to downstream tasks if we fine-tune the soft prompts with few samples. However, we find a common failure that improper fine-tuning or learning with extremely few-shot samples may even under-perform the zero-shot prediction. Existing methods still address this problem by using traditional anti-overfitting techniques such as early stopping and data augmentation, which lack a principled solution specific to prompting. In this paper, we present Prompt-aligned Gradient, dubbed ProGrad to prevent prompt tuning from forgetting the general knowledge learned from VLMs. In particular, ProGrad only updates the prompt whose gradient is aligned (or non-conflicting) to the general knowledge, which is represented as the optimization direction offered by the pre-defined prompt predictions. Extensive experiments under the few-shot learning, domain generalization, base-to-new generalization and cross-dataset transfer settings demonstrate the stronger few-shot generalization ability of ProGrad over state-of-the-art prompt tuning methods.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Ucf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · cited 1×
“, prompt [22, 51, 17], to query the general knowledge via human-unreadable model parameters.”
BackgroundLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352 · cited 1×
“, prompt [22, 51, 17], to query the general knowledge via human-unreadable model parameters.”
BackgroundLi, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988
3D Object Representations for Fine-Grained Categorization
Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013) · 2013 IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.77 · Cited by 3,496
Automated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442
Learning to Prompt for Vision-Language Models
Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01653-1 · Cited by 3,304 · cited 10×
“In CV community, CoOp [53] uses a continuous prompt optimization from downstream data instead of hand-craft design.”
BackgroundMethodInfluentialSUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283 · cited 2×
“For few-shot learning, base-to-new generalization and cross-dataset transfer, we use 11 datasets, i.e ., Ima-geNet [6] and Caltech101 [9] for generic object classification, OxfordPets [33], StanfordCars [22], Flowers102 [32], Food101 [2] and FGVCAircraft [30] for fine-grained image recognition, EuroSAT [13] for satell…”
BackgroundThe Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
Describing Textures in the Wild
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.461 · Cited by 2,438
Fei-Fei, L., Fergus, R., & Perona, P. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.09.012 · Cited by 2,359
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (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/d19-1514 · Cited by 2,319 · cited 1×
“VLM can be adapted for various down-stream tasks, e.g ., visual question answering [21, 48], visual grounding [51], image retrieval [28] and semantic segmentation [39].”
BackgroundViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
Food-101 – Mining Discriminative Components with Random Forests
Bossard, L., Guillaumin, M., & Van Gool, L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10599-4_29 · Cited by 2,072
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2918242 · Cited by 1,951
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
Bartlett, P. L., & Mendelson, S. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-44581-1_15 · Cited by 1,949
Conditional Prompt Learning for Vision-Language Models
Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01631 · Cited by 1,796
Parkhi, O. M., Vedaldi, A., Zisserman, A., & Jawahar, C. V. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248092 · Cited by 1,533
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380 · cited 1×
“To the best of our knowledge, existing methods still adopt the conventional anti-overfitting techniques such as early stopping and data augmentation [53, 54, 8, 35], which lacks a principled solution to the nature of improper prompt tuning.”
MethodThe Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., Guo, M., et al. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00823 · Cited by 1,250
CLIP-Adapter: Better Vision-Language Models with Feature Adapters
Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Y. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-023-01891-x · Cited by 1,197
Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01501 · Cited by 1,090 · cited 1×
“For domain generalization, we use ImageNet as the source dataset and select ImageNet-V2 [41], ImageNet-Sketch [49], ImageNet-A [15], ImageNet-R [14] as the target datasets.”
MethodFine-Grained Visual Classification of Aircraft
Maji, S., Rahtu, E., Kannala, J., Blaschko, M. B., & Vedaldi, A. (2013) · INRIA a CCSD electronic archive server · doi:10.48550/arxiv.1306.5151 · Cited by 1,084
Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2019) · arXiv · doi:10.48550/arxiv.1907.07174 · Cited by 1,058
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Kim, W., Son, B., & Kim, I. (2021) · arXiv · doi:10.48550/arxiv.2102.03334 · Cited by 951 · cited 2×
“, visual question answering [18, 47], visual grounding [51, 25], image retrieval [18, 25] and image classification [53, 54].”
BackgroundMethodMaPLe: Multi-modal Prompt Learning
Khattak, M. U., Rasheed, H., Maaz, M., Khan, S., & Khan, F. S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01832 · Cited by 925
Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., & Tang, J. (2021) · arXiv · doi:10.48550/arxiv.2103.10385 · Cited by 908 · cited 2×
“Recently, NLP community has introduced a "prompt-based learning" paradigm that fine-tunes the prompt using a "fill-in-the-blank" cloze test to maximize the ground-truth token [23, 26].”
BackgroundMulti-Task Learning as Multi-Objective Optimization
Sener, O., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1810.04650 · Cited by 852
Do ImageNet Classifiers Generalize to ImageNet?
Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019) · arXiv · doi:10.48550/arxiv.1902.10811 · Cited by 790
Gradient Surgery for Multi-Task Learning
Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., & Finn, C. (2020) · arXiv · doi:10.48550/arxiv.2001.06782 · Cited by 755 · cited 1×
“The image-class matching score is measured based on the cosine similarity < w i , f > between the image feature f and the class-extended text feature w i for i -th class.”
MethodDenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
Rao, Y., Zhao, W., Chen, G., Tang, Y., Zhu, Z., Huang, G., Zhou, J., & Lu, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01755 · Cited by 631
Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., & Tang, J. (2024) · AI Open · doi:10.1016/j.aiopen.2023.08.012 · Cited by 596
Integral Probability Metrics and Their Generating Classes of Functions
Müller, A. (1997) · Advances in Applied Probability · doi:10.1017/s000186780002807x · Cited by 548
Learning Robust Global Representations by Penalizing Local Predictive Power
Wang, H., Ge, S., Xing, E. P., & Lipton, Z. C. (2019) · arXiv · doi:10.48550/arxiv.1905.13549 · Cited by 337
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting
Liu, Y., Su, Y., Liu, A.-A., Schiele, B., & Sun, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01226 · Cited by 309
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting
LIU, Y., SU, Y., LIU, A.-A., Schiele, B., & SUN, Q. (2020) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · Cited by 278
Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationPreprint
Ramé, A., Dancette, C., & Cord, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.02934 · Cited by 255
Lu, Y., Liu, J., Zhang, Y., Liu, Y., & Tian, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00514 · Cited by 246
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language ModelsPreprint
Shu, M., Nie, W., Huang, D.-A., Yu, Z., Goldstein, T., Anandkumar, A., & Xiao, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.07511 · Cited by 233
Distributions of Angles in Random Packing on Spheres
Cai, T., Fan, J., & Jiang, T. (2013) · Journal of Machine Learning Research · doi:10.48550/arxiv.1306.0256 · Cited by 231
Distilling Causal Effect of Data in Class-Incremental Learning
Hu, X., Tang, K., Miao, C., Hua, X.-S., & Zhang, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00395 · Cited by 167
Self-citationCPT: Colorful Prompt Tuning for pre-trained vision-language models
Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T.-S., & Sun, M. (2024) · AI Open · doi:10.1016/j.aiopen.2024.01.004 · Cited by 167
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2020) · arXiv · doi:10.48550/arxiv.2012.15723 · Cited by 124
Jin, W., Cheng, Y., Shen, Y., Chen, W., & Ren, X. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.197 · Cited by 116
Generalization Bounds for Domain Adaptation
Zhang, C., Zhang, L., & Ye, J. (2013) · PubMed · doi:10.48550/arxiv.1304.1574 · Cited by 92
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
Qin, C., & Joty, S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.198 · Cited by 68
Debiased Fine-Tuning for Vision-Language Models by Prompt Regularization
Zhu, B., Niu, Y., Lee, S., Hur, M., & Zhang, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25496 · Cited by 45
Self-citation
Cited by
Vision-Language Models for Vision Tasks: A Survey
Zhang, J., Huang, J., Jin, S., & Lu, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3369699 · Cited by 1,051
“ProGrad [136] [code] TPT Few-shot Sup.”
MaPLe: Multi-modal Prompt Learning
Khattak, M. U., Rasheed, H., Maaz, M., Khan, S., & Khan, F. S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01832 · Cited by 925
End-Edge-Cloud Collaborative Computing for Deep Learning: A Comprehensive Survey
Wang, Y., Yang, C., Lan, S., Zhu, L., & Zhang, Y. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3393230 · Cited by 237
“Recent advancements explore how soft prompts could be used for few-shot [231], pre-training [232], or multitask [233].”
Metadata
- Authors
- Zhu, B., Niu, Y., Han, Y., Wu, Y., & Zhang, H.
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 15613-15623
- OpenAlex
- W4390873714
- Cited by
- 298
- References
- 55
- FWCI
- 56.33
- 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.