CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref: (1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended. We will release data and code for CLEVR-Ref+.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
VQA: Visual Question Answering
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.279 · Cited by 4,487
Film: Visual reasoning with a general conditioning layer
Perez, E., Strub, F., De Vries, H., Dumoulin, V., & Courville, A. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11671 · Cited by 2,490
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., & Parikh, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.670 · Cited by 2,287
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.215 · Cited by 1,781
A simple neural network module for relational reasoning
Santoro, A., Raposo, D., Barrett, D. G. T., Malinowski, M., Pascanu, R., Battaglia, P., & Lillicrap, T. (2017) · arXiv · doi:10.48550/arxiv.1706.01427 · Cited by 1,281 · cited 1×
“Several approaches now achieve near-perfect accuracy on CLEVR [16, 10, 29, 32, 27, 14, 9].”
Background(2016) · doi:10.1007/978-3-319-46475-6_5 · Cited by 1,081
Visual7W: Grounded Question Answering in Images
Zhu, Y., Groth, O., Bernstein, M., & Fei-Fei, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.540 · Cited by 794 · cited 9×
“Note that CLEVR was also adapted towards referring expression in [9], but they focused on facilitating VQA, instead of introducing extensions (Section 3.3), evaluating state-of-the-art models (Section 4.1), and directly facilitating the diagnosis of visual reasoning (Section 4.3).”
BackgroundInfluentialTransparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
Mascharka, D., Tran, P., Soklaski, R., & Majumdar, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00519 · Cited by 203 · cited 2×
“Several approaches now achieve near-perfect accuracy on CLEVR [16, 10, 29, 32, 27, 14, 9].”
Background
Cited by
MDETR - Modulated Detection for End-to-End Multi-Modal Understanding
Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., & Carion, N. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00180 · Cited by 729
Zhao, F., Zhang, C., & Geng, B. (2024) · ACM Computing Surveys · doi:10.1145/3649447 · Cited by 480
RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data
Zhan, Y., Xiong, Z., & Yuan, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3250471 · Cited by 179
“Over the years, various visual grounding datasets [18], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63], [64], [65] based on real-world and computer-generated images have been proposed to study visual grounding.”
BackgroundMethodDeep Nets: What have They Ever Done for Vision?
Yuille, A. L., & Liu, C. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01405-z · Cited by 98
“AND, OR, Filter(red) etc) after joint training (Liu et al., 2019).”
BackgroundSelf-citationVisual Grounding in Remote Sensing Images
Sun, Y., Feng, S., Li, X., Ye, Y., Kang, J., & Huang, X. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548316 · Cited by 81
“Besides, as mentioned in [16], when there is only one instance of the category of the target object in the image, the model will exhibit a strong bias, i.”
BackgroundMethodInfluential
Metadata
- Authors
- Liu, R., Liu, C., Bai, Y., & Yuille, A. L.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 4180-4189
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2907143950
- Cited by
- 109
- References
- 12
- FWCI
- 4.98
- 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.