High resolution image segmentation with deep learning models

Vladislav Ofitserov, Anton Konushin

Abstract


The work addresses the issue of interactive image segmentation, relevant to modern computer vision applications. The aim of the work is to improve the resolution of interactive segmentation models under limited resources. The work provides a review of existing segmentation methods and proposes an enhanced basic method, which improved the NoC N @ 90 bIoU metric from 16.97 to 12.25 on the HQSeg44k dataset. The results demonstrate that the new method enhances segmentation map resolution and improves object delineation accuracy with limited computational resources, confirming its potential for applications in various fields requiring precise image segmentation with minimal resources.


Full Text:

PDF (Russian)

References


Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18 (pp. 234-241). Springer International Publishing.

Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.

Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 801-818).

He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969).

Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).

Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587).

Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.

Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022). Masked-attention mask transformer for universal image segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 1290-1299).

Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., ... & Xiao, B. (2020). Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 43(10), 3349-3364.

Sofiiuk, K., Petrov, I. A., & Konushin, A. (2022, October). Reviving iterative training with mask guidance for interactive segmentation. In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 3141-3145). IEEE.

Lin, Z., Duan, Z. P., Zhang, Z., Guo, C. L., & Cheng, M. M. (2022). Focuscut: Diving into a focus view in interactive segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2637-2646).

Liu, Q., Xu, Z., Bertasius, G., & Niethammer, M. (2023). Simpleclick: Interactive image segmentation with simple vision transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 22290-22300).

Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., ... & Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.

Shi, B., Gai, S., Darrell, T., & Wang, X. (2023). Toast: Transfer learning via attention steering. arXiv preprint arXiv:2305.15542, 5(7), 13.

Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988).

Aleem, S., Dietlmeier, J., Arazo, E., & Little, S. (2024). ConvLoRA and AdaBN based Domain Adaptation via Self-Training. arXiv preprint arXiv:2402.04964.

Kervadec, H., Bouchtiba, J., Desrosiers, C., Granger, E., Dolz, J., & Ayed, I. B. (2019, May). Boundary loss for highly unbalanced segmentation. In International conference on medical imaging with deep learning (pp. 285-296). PMLR.

Ke, L., Ye, M., Danelljan, M., Tai, Y. W., Tang, C. K., & Yu, F. (2024). Segment anything in high quality. Advances in Neural Information Processing Systems, 36.

Qin, X., Dai, H., Hu, X., Fan, D. P., Shao, L., & Van Gool, L. (2022, October). Highly accurate dichotomous image segmentation. In European Conference on Computer Vision (pp. 38-56). Cham: Springer Nature Switzerland.

Liew, J. H., Cohen, S., Price, B., Mai, L., & Feng, J. (2021). Deep interactive thin object selection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 305-314).

Li, X., Wei, T., Chen, Y. P., Tai, Y. W., & Tang, C. K. (2020). Fss-1000: A 1000-class dataset for few-shot segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 2869-2878).

Shi, J., Yan, Q., Xu, L., & Jia, J. (2015). Hierarchical image saliency detection on extended CSSD. IEEE transactions on pattern analysis and machine intelligence, 38(4), 717-729.

Cheng, M. M., Mitra, N. J., Huang, X., Torr, P. H., & Hu, S. M. (2014). Global contrast based salient region detection. IEEE transactions on pattern analysis and machine intelligence, 37(3), 569-582.

Yang, C., Zhang, L., Lu, H., Ruan, X., & Yang, M. H. (2013). Saliency detection via graph-based manifold ranking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3166-3173).

Cheng, B., Girshick, R., Dollár, P., Berg, A. C., & Kirillov, A. (2021). Boundary IoU: Improving object-centric image segmentation evaluation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 15334-15342).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162