OmniVec: Learning robust representations with cross modal sharing
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Majority of research in learning based methods has been towards designing and training networks for specific tasks. However, many of the learning based tasks, across modalities, share commonalities and could be potentially tackled in a joint framework. We present an approach in such direction, to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We first pre-train it by self-supervised masked training, followed by sequential training for the different tasks. We train the network on all major modalities, e.g. visual, audio, text and 3D, and report results on 22 diverse and challenging public benchmarks. We demonstrate empirically that, using a joint network to train across modalities leads to meaningful information sharing and this allows us to achieve state-of-the-art results on most of the benchmarks. We also show generalization of the trained network on cross-modal tasks as well as unseen datasets and 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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 1×
“Notably, our method offers enhanced depth discernment for objects such as the bus shelter (highlighted in the top and middle images) as well as houses (depicted in the bottom image).”
MethodIndoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
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
Places: A 10 Million Image Database for Scene Recognition
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2723009 · Cited by 4,042
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965 · cited 1×
“…datasets, we compare the results against state-of-the-art methods on Oxford-IIIT Pets (image classification) [11], UCF-101 [15], HMDB51 (video action recognition) [7], ScanObjectNN (3D point cloud classification) [17], NYU v2 seg (point cloud segmentation) [14] and SamSum (text summarization) [5].”
MethodTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595 · cited 1×
“The input to the network is the respective modality (text, image, point cloud, audio etc.).”
BackgroundTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2101.01169 · Cited by 3,594
Audio Set: An ontology and human-labeled dataset for audio events
Gemmeke, J. F., Ellis, D. P. W., Freedman, D., Jansen, A., Lawrence, W., Moore, R. C., Plakal, M., & Ritter, M. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952261 · Cited by 3,134 · cited 1×
“98.71 OmniVec(FT) 99.6 Method Pets (top-1) Pets (top-5) Omnivore [4] 95.1 99.1 IELT [21] 95.28 - DINOv2 [10] 96.70 - EffNet-L2 [3] 97.10 - OmniVec(Pre.)”
InfluentialA Survey on Multi-Task Learning
Zhang, Y., & Yang, Q. (2017) · arXiv · doi:10.48550/arxiv.1707.08114 · Cited by 2,910
ViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767 · cited 1×
“92.10 OmniVec(FT.) 96.10”
InfluentialVision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373 · cited 1×
“92.10 OmniVec(FT.) 96.10”
InfluentialUNITER: UNiversal Image-TExt Representation Learning
Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., & Liu, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58577-8_7 · Cited by 2,055 · cited 1×
“We obtain results on standard test sets for each of the tasks.”
MethodSUN RGB-D: A RGB-D scene understanding benchmark suite
Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943 · cited 1×
“98.71 OmniVec(FT) 99.6 Method Pets (top-1) Pets (top-5) Omnivore [4] 95.1 99.1 IELT [21] 95.28 - DINOv2 [10] 96.70 - EffNet-L2 [3] 97.10 - OmniVec(Pre.)”
InfluentialThe “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.622 · Cited by 1,471 · cited 3×
“VATT [1] 87.6 Omnivore [4] 98.2 Text4Vis [20] 98.2 SMART [6] 98.6 VideoMAE V2-g [18] 99.6 OmniVec(Pre.)”
InfluentialThe iNaturalist Species Classification and Detection Dataset
Van Horn, G., Mac Aodha, O., Song, Y., Cui, Y., Sun, C., Shepard, A., Adam, H., Perona, P., & Belongie, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00914 · Cited by 1,451
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2022) · AI Open · doi:10.1016/j.aiopen.2022.10.001 · Cited by 1,422
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2021) · arXiv · doi:10.48550/arxiv.2106.04554 · Cited by 1,420
AST: Audio Spectrogram Transformer
Gong, Y., Chung, Y.-A., & Glass, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-698 · Cited by 1,159
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080
Multimodal learning with transformers: A survey
Xu, P., Zhu, X., & Clifton, D. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275156 · Cited by 1,072
Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., & Geiger, A. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00012 · Cited by 924
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers
Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., & Stiefelhagen, R. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3300537 · Cited by 731 · cited 1×
“NYUv2 Omnivore [4] 56.8 CMN [8] 56.9 OmniVec(Pre.)”
InfluentialMasked Feature Prediction for Self-Supervised Visual Pre-Training
Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01426 · Cited by 587
Sharpness-Aware Minimization for Efficiently Improving Generalization
Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020) · arXiv · doi:10.48550/arxiv.2010.01412 · Cited by 521 · cited 1×
“98.71 OmniVec(FT) 99.6 Method Pets (top-1) Pets (top-5) Omnivore [4] 95.1 99.1 IELT [21] 95.28 - DINOv2 [10] 96.70 - EffNet-L2 [3] 97.10 - OmniVec(Pre.)”
InfluentialSAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
Gliwa, B., Mochol, I., Biesek, M., & Wawer, A. (2019) · Proceedings of the 2nd Workshop on New Frontiers in Summarization · doi:10.18653/v1/d19-5409 · Cited by 424
Perceiver: General Perception with Iterative Attention
Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., & Carreira, J. (2021) · arXiv · doi:10.48550/arxiv.2103.03206 · Cited by 414 · cited 5×
“We fine-tune the network in an end-to-end manner.”
BackgroundMethodInfluentialSymbolic Discovery of Optimization Algorithms
Chen, X., Liang, C., Huang, D., Real, E., Wang, K., Liu, Y., Pham, H., Dong, X., Luong, T., Hsieh, C.-J., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.06675 · Cited by 303
UniT: Multimodal Multitask Learning with a Unified Transformer
Hu, R., & Singh, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00147 · Cited by 303
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
Chen, K., Du, X., Zhu, B., Ma, Z., Berg-Kirkpatrick, T., & Dubnov, S. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9746312 · Cited by 294
Kaiser, L., Gomez, A. N., Shazeer, N., Vaswani, A., Parmar, N., Jones, L., & Uszkoreit, J. (2017) · arXiv · doi:10.48550/arxiv.1706.05137 · Cited by 253 · cited 1×
“For segmentation and summarization, we use the same networks as described in Section 4-Task Heads (main manuscript).”
MethodSocratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Zeng, A., Attarian, M., Ichter, B., Choromanski, K., Wong, A., Welker, S., Tombari, F., Purohit, A., Ryoo, M., Sindhwani, V., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.00598 · Cited by 205
A Practical Survey on Faster and Lighter Transformers
Fournier, Q., Caron, G. M., & Aloise, D. (2023) · ACM Computing Surveys · doi:10.1145/3586074 · Cited by 145 · cited 1×
“It is encoded with the respective encoders for these modalities as described in Table 1 (main manuscript) irrespective of the task.”
MethodULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding
Xue, L., Yu, N., Zhang, S., Panagopoulou, A., Li, J., Martín-Martín, R., Wu, J., Xiong, C., Xu, R., Niebles, J. C., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02558 · Cited by 144 · cited 1×
“97.36 99.3 OmniVec(FT) 99.2 99.7 91.3 ULIP-2 [22] 91.5 PointGPT [2] 93.4 OmniVec(Pre.)”
InfluentialCalibrating Sequence likelihood Improves Conditional Language Generation
Zhao, Y., Khalman, M., Joshi, R., Narayan, S., Saleh, M., & Liu, P. J. (2022) · arXiv · doi:10.48550/arxiv.2210.00045 · Cited by 42 · cited 1×
“58.6 OmniVec(FT) 60.8 Method R-1 R-2 R-L Pegasus [24] 54.37 29.88 45.89 MoCa [23] 55.13”
Influential
Cited by
MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain
Chase, T., & Dantu, K. (2024) · arXiv · doi:10.48550/arxiv.2410.05182 · Cited by 5
Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra
Lapin, J., Nilsson, A., Wilhelm, M., & Käll, L. (2025) · Journal of Proteome Research · doi:10.1021/acs.jproteome.5c00063 · Cited by 4
Single-neuron encoding of rapidly learned visual information reshapes human perception
Armendariz, M., Blumberg, J., Singer, J., Aiple, F., Kim, J., Domínguez-Iturza, N., Brandt, A., Reinacher, P., Schulze-Bonhage, A., & Kreiman, G. (2026) · Nature Neuroscience · doi:10.1038/s41593-026-02496-6
Metadata
- Authors
- Srivastava, S., & Sharma, G.
- Venue
- 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2024-01-03
- Pages
- 1225-1237
- OpenAlex
- W4394597798
- Cited by
- 73
- References
- 38
- FWCI
- 15.94
- 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.