The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Towards Diverse and Natural Image Descriptions via a Conditional GAN
Open accessAbstract
Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect. Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This issue is related to a learning principle widely used in practice, that is, to maximize the likelihood of training samples. This principle encourages high resemblance to the “ground-truth” captions, while suppressing other reasonable descriptions. Conventional evaluation metrics, e.g. BLEU and METEOR, also favor such restrictive methods. In this paper, we explore an alternative approach, with the aim to improve the naturalness and diversity - two essential properties of human expression. Specifically, we propose a new framework based on Conditional Generative Adversarial Networks (CGAN), which jointly learns a generator to produce descriptions conditioned on images and an evaluator to assess how well a description fits the visual content. It is noteworthy that training a sequence generator is nontrivial. We overcome the difficulty by Policy Gradient, a strategy stemming from Reinforcement Learning, which allows the generator to receive early feedback along the way. We tested our method on two large datasets, where it performed competitively against real people in our user study and outperformed other methods on various tasks.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
(2004) · Cited by 9,718
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Cited by
Generative adversarial network in medical imaging: A review
Yi, X., Walia, E., & Babyn, P. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101552 · Cited by 1,863
Deep Learning for IoT Big Data and Streaming Analytics: A Survey
Mohammadi, M., Al-Fuqaha, A., Sorour, S., & Guizani, M. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2844341 · Cited by 1,471
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130191 · Cited by 1,231
A Comprehensive Survey of Deep Learning for Image Captioning
Hossain, M. Z., Sohel, F., Shiratuddin, M. F., & Laga, H. (2019) · ACM Computing Surveys · doi:10.1145/3295748 · Cited by 879
“Dai et al. [26] also proposed a GAN based image captioning method.”
MethodScene Graph Generation from Objects, Phrases and Region Captions
Li, Y., Ouyang, W., Zhou, B., Wang, K., & Wang, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.142 · Cited by 500
Durall, R., Keuper, M., & Keuper, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00791 · Cited by 26
Atitallah, S. B., Driss, M., Boulila, W., & Ghézala, H. B. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100303 · Cited by 375
From Show to Tell: A Survey on Deep Learning-Based Image Captioning
Stefanini, M., Cornia, M., Baraldi, L., Cascianelli, S., Fiameni, G., & Cucchiara, R. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3148210 · Cited by 373
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C. C., & Luo, P. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115428 · Cited by 277
Self-citationA Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
pix2code: Generating Code from a Graphical User Interface Screenshot
Beltramelli, T. (2018) · Proceedings of the ACM SIGCHI Symposium on Engineering Interactive Computing Systems · doi:10.1145/3220134.3220135 · Cited by 237
Towards Unsupervised Image Captioning With Shared Multimodal Embeddings
Laina, I., Rupprecht, C., & Navab, N. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00751 · Cited by 111
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning
Sachdeva, E., Agarwal, N., Chundi, S., Roelofs, S., Li, J., Kochenderfer, M., Choi, C., & Dariush, B. (2024) · 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv57701.2024.00734 · Cited by 63
“Although caption diversity has been explored in image datasets in previous works [8, 33, 38], it has rarely been investigated in a video setting, particularly in traffic scenes.”
BackgroundTIGEr: Text-to-Image Grounding for Image Caption Evaluation
Jiang, M., Huang, Q., Zhang, L., Wang, X., Zhang, P., Gan, Z., Diesner, J., & Gao, J. (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/d19-1220 · Cited by 59
EvalAI: Towards Better Evaluation Systems for AI Agents
Yadav, D., Jain, R., Agrawal, H., Chattopadhyay, P., Singh, T., Jain, A., Singh, S. B., Lee, S., & Batra, D. (2019) · arXiv · doi:10.48550/arxiv.1902.03570 · Cited by 42
A Comparative Study of Deepfake Video Detection Method
Ramadhani, K. N., & Munir, R. (2020) · 2020 3rd International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact50329.2020.9331963 · Cited by 42
Measuring Representational Harms in Image Captioning
Wang, A., Barocas, S., Laird, K., & Wallach, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533099 · Cited by 40
“Most image captioning systems are trained using gradient descent with a maximum likelihood objective, although this approach has been shown to generate less diverse captions than GAN-based losses or humans [24, 69].”
BackgroundVisual Question Generation: The State of the Art
Patil, C., & Patwardhan, M. (2021) · ACM Computing Surveys · doi:10.1145/3383465 · Cited by 25
Vision to Language: Methods, Metrics and Datasets
Sharif, N., Nadeem, U., Shah, S. A. A., Bennamoun, M., & Liu, W. (2020) · Learning and Analytics in Intelligent Systems · doi:10.1007/978-3-030-49724-8_2 · Cited by 9
Probabilistic framework for solving visual dialog
Patro, B. N., Anupriy, & Namboodiri, V. P. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107586 · Cited by 4
Metadata
- Authors
- Dai, B., Fidler, S., Urtasun, R., & Lin, D.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2989-2998
- OpenAlex
- W2962968835
- Cited by
- 477
- References
- 36
- FWCI
- 18.61
- 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.