Skip to main content

LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15065))

Included in the following conference series:

  • 458 Accesses

Abstract

Given an image and text description, visual grounding will find target region in the image explained by the text. It has two task settings: referring expression comprehension (REC) to estimate bounding-box and referring expression segmentation (RES) to predict segmentation mask. Currently the most promising visual grounding approaches are to learn REC and RES jointly by giving rich ground truth of both bounding-box and segmentation mask of the target object. However, we argue that a very simple but strong constraint has been overlooked by the existing approaches: given an image and a text description, REC and RES refer to the same object. We propose Location Aware Transformer (LoA-Trans) making this constraint explicit by a center prompt, where the system first predicts the center of the target object by Location-Aware Network, and feeds it as a common prompt to both REC and RES. In this way, the system constrains that REC and RES refer to the same object. To mitigate possible inaccuracies in center estimation, we introduce a query selection mechanism. Instead of random initialization queries for bounding-box and segmentation mask decoding, the query selection mechanism generates possible object locations other than the estimated center and use them as location-aware queries as a remedy for possible inaccurate center estimation. We also introduce a TaskSyn Network in the decoder to better coordination between REC and RES. Our method achieved state-of-the-art performance on three commonly used datasets: Refcoco, Refcoco+, and Refcocog. Extensive ablation studies demonstrated the validity of each of the proposed components.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: Transvg: end-to-end visual grounding with transformers. In: ICCV (2021)

    Google Scholar 

  2. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  3. Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: ICCV (2021)

    Google Scholar 

  4. Feng, G., Hu, Z., Zhang, L., Lu, H.: Encoder fusion network with co-attention embedding for referring image segmentation. In: CVPR (2021)

    Google Scholar 

  5. Girshick, R.: Fast r-cnn. In: ICCV (2015)

    Google Scholar 

  6. Hong, R., Liu, D., Mo, X., He, X., Zhang, H.: Learning to compose and reason with language tree structures for visual grounding. In: IEEE TPAMI (2019)

    Google Scholar 

  7. Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: CVPR (2017)

    Google Scholar 

  8. Hu, Z., Feng, G., Sun, J., Zhang, L., Lu, H.: Bi-directional relationship inferring network for referring image segmentation. In: CVPR (2020)

    Google Scholar 

  9. Huang, S., et al.: Referring image segmentation via cross-modal progressive comprehension. In: CVPR (2020)

    Google Scholar 

  10. Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: ICCV (2021)

    Google Scholar 

  11. Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: EMNLP (2014)

    Google Scholar 

  12. Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: NeurIPS (2021)

    Google Scholar 

  13. Liao, Y., Liu, S., Li, G., Wang, F., Chen, Y., Qian, C., Li, B.: A real-time cross-modality correlation filtering method for referring expression comprehension. In: CVPR (2020)

    Google Scholar 

  14. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV (2017)

    Google Scholar 

  15. Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)

    Google Scholar 

  16. Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: CVPR (2023)

    Google Scholar 

  17. Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: ICCV (2017)

    Google Scholar 

  18. Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: ICCV (2019)

    Google Scholar 

  19. Liu, J., et al.: Polyformer: referring image segmentation as sequential polygon generation. In: CVPR (2023)

    Google Scholar 

  20. Liu, X., Wang, Z., Shao, J., Wang, X., Li, H.: Improving referring expression grounding with cross-modal attention-guided erasing. In: CVPR (2019)

    Google Scholar 

  21. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)

    Google Scholar 

  22. Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)

  23. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)

    Google Scholar 

  24. Luo, G., et al.: Cascade grouped attention network for referring expression segmentation. In: ACM MM (2020)

    Google Scholar 

  25. Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: CVPR (2020)

    Google Scholar 

  26. Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)

    Google Scholar 

  27. Margffoy-Tuay, E., Pérez, J.C., Botero, E., Arbeláez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: ECCV (2018)

    Google Scholar 

  28. Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV (2016)

    Google Scholar 

  29. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR (2019)

    Google Scholar 

  30. Su, W., et al.: Language adaptive weight generation for multi-task visual grounding. In: CVPR (2023)

    Google Scholar 

  31. Sun, M., Xiao, J., Lim, E.G.: Iterative shrinking for referring expression grounding using deep reinforcement learning. In: CVPR (2021)

    Google Scholar 

  32. Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)

    Google Scholar 

  33. Vaswani, A.,et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  34. Wang, Z., et al.: Cris: clip-driven referring image segmentation. In: CVPR (2022)

    Google Scholar 

  35. Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: ICCV (2019)

    Google Scholar 

  36. Yang, S., Xia, M., Li, G., Zhou, H.Y., Yu, Y.: Bottom-up shift and reasoning for referring image segmentation. In: CVPR (2021)

    Google Scholar 

  37. Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. In: CVPR (2022)

    Google Scholar 

  38. Yang, Z., Chen, T., Wang, L., Luo, J.: Improving one-stage visual grounding by recursive sub-query construction. In: ECCV (2020)

    Google Scholar 

  39. Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: ICCV (2019)

    Google Scholar 

  40. Ye, J., et al.: Shifting more attention to visual backbone: query-modulated refinement networks for end-to-end visual grounding. In: CVPR (2022)

    Google Scholar 

  41. Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: CVPR (2019)

    Google Scholar 

  42. Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: CVPR (2018)

    Google Scholar 

  43. Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: ECCV (2016)

    Google Scholar 

  44. Zhang, H., Niu, Y., Chang, S.F.: Grounding referring expressions in images by variational context. In: CVPR (2018)

    Google Scholar 

  45. Zhou, Y., et al.: A real-time global inference network for one-stage referring expression comprehension. In: IEEE TNNLS (2021)

    Google Scholar 

  46. Zhu, C., et al.: Seqtr: a simple yet universal network for visual grounding. In: ECCV (2022)

    Google Scholar 

  47. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)

Download references

Acknowledgement

This work is partly supported by JSPS KAKENHI Grant Number JP23K24876 and JST ASPIRE Program Grant Number JPMJAP2303.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ziling Huang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1333 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Huang, Z., Satoh, S. (2025). LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15065. Springer, Cham. https://doi.org/10.1007/978-3-031-72667-5_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72667-5_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72666-8

  • Online ISBN: 978-3-031-72667-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics