تقرير
The revenge of BiSeNet: Efficient Multi-Task Image Segmentation
العنوان: | The revenge of BiSeNet: Efficient Multi-Task Image Segmentation |
---|---|
المؤلفون: | Rosi, Gabriele, Cuttano, Claudia, Cavagnero, Niccolò, Averta, Giuseppe, Cermelli, Fabio |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | Recent advancements in image segmentation have focused on enhancing the efficiency of the models to meet the demands of real-time applications, especially on edge devices. However, existing research has primarily concentrated on single-task settings, especially on semantic segmentation, leading to redundant efforts and specialized architectures for different tasks. To address this limitation, we propose a novel architecture for efficient multi-task image segmentation, capable of handling various segmentation tasks without sacrificing efficiency or accuracy. We introduce BiSeNetFormer, that leverages the efficiency of two-stream semantic segmentation architectures and it extends them into a mask classification framework. Our approach maintains the efficient spatial and context paths to capture detailed and semantic information, respectively, while leveraging an efficient transformed-based segmentation head that computes the binary masks and class probabilities. By seamlessly supporting multiple tasks, namely semantic and panoptic segmentation, BiSeNetFormer offers a versatile solution for multi-task segmentation. We evaluate our approach on popular datasets, Cityscapes and ADE20K, demonstrating impressive inference speeds while maintaining competitive accuracy compared to state-of-the-art architectures. Our results indicate that BiSeNetFormer represents a significant advancement towards fast, efficient, and multi-task segmentation networks, bridging the gap between model efficiency and task adaptability. Comment: Accepted to ECV workshop at CVPR2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2404.09570 |
رقم الأكسشن: | edsarx.2404.09570 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |