近年來語意圖像分割已經擁有很亮眼的表現。但因為語意圖像分割的目的是給予每一個像素相對應的類別標籤，於是現在有更多的目光投注在除了給予每一個像素相對應的類別標籤外，更要從相同的類別中去區分不同的個體物件。這種任務被稱作實例感知語意分割。在現有的處理實例分割的方法中，大多需要事先偵測物件位置或是使用滑行窗尋找物件。在本篇論文中，我們在語意圖像分割的結果上更進一步地從相同的類別中去區分不同的個體物件。我們提出了一種像素級個體特徵來區分不同的個體物件。並且因為所有類別都是利用該像素個體特徵來區分實例，於是我們提出了一個類別共享的網路模型來結合語意圖像分割的結果跟我們的像素級個體特徵來達到實例感知語意分割的結果。我們的方法不需要事先偵測任何物件提案或使用滑行窗。實驗結果證明，即使不事先偵測物件提案，我們的方法在Pascal VOC 2012 及 MSCOCO 資料集中依舊達到了不錯的表現。

Recently, semantic segmentation has rapidly achieved high performance. Because the goal of semantic segmentation is to densely label each pixel with the corresponding category label, more efforts are now devoted to further differentiate instances belonging to the same category label. To achieve instance-aware semantic segmentation, most of existing methods need to use sliding windows or object proposals to locate instances. In this thesis, we utilize the semantic segmentation results to further differentiate instances in the same category. We propose a pixel-wise instance feature to identify different instance. Then, we propose a Class-shared net to aggregate the semantic segmentation results using our pixel-wise instance feature to achieve instance segmentation. The proposed method needs no external object proposal generator or any sliding windows to achieve instance segmentation. Experimental results demonstrate that the proposed method is efficient and achieve comparable results on Pascal VOC 2012 and MSCOCO datasets.

[1] B. Hariharan, P. Arbelaez, R. Girshick, and J. Malik. Hypercolumns for object segmentation and fine-grained localization. In Proc. CVPR, 2015.
[2] B. Hariharan, P. Arbelaez, L. Bourdev, S.Maji, and J.Malik. Semantic contours from inverse detectors. In Proc. ICCV, 2011.
[3] B. Hariharan, P. Arbelaez, R. B. Girshick, and J. Malik. Simultaneous detection and segmentation. In Proc. ECCV, 2014.
[4] J. Dai, K. He, and J. Sun. Convolutional feature masking for joint object and stuff segmentation. In Proc. CVPR, 2015.
[5] J. Dai, K. He, and J. Sun. Instance-aware semantic segmentation via multi-task network cascades. In Proc. CVPR, 2016
[6] J. Dai, K. He, Y. Li, S. Ren, and J. Sun. Instance-sensitive fully convolutional networks. In Proc. ECCV, 2016.
[7] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Semantic image segmentation with deep convolutional nets and fully connected crfs. In Proc. ICLR, 2015.
[8] S. Liu, X. Qi, J. Shi, H. Zhang, and J. Jia. Multi-scale patch aggregation (MPA) for simultaneous detection and segmentation. In Proc. CVPR, 2016
[9] Z. Jie, X. Liang, J. Feng, W. F. Lu, E. H. F. Tay, and S. Yan. Scale-aware Pixel-wise Object Proposal Networks. IEEE TIP 2016
[10] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proc. CVPR, 2014.
[11] X. Li, Z. Liu, P. Luo, C. L. Chen, X. Tang. Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade. In arXiv, 2017
[12] J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In Proc. CVPR, 2015.
[13] S. Zheng, S. Jayasumana, B. Romera-Paredes, V. Vineet, Z. Su, D. Du, C. Huang, and P. Torr. Conditional random fields as recurrent neural networks. In Proc. ICCV, 2015.
[14] Z. Liu, X. Li, P. Luo, C. C. Loy, and X. Tang. Semantic image segmentation via deep parsing network. In Proc. ICCV, 2015.
[15] G. Lin, C. Shen, A. van den Hengel, and I. Reid. Efficient piecewise training of deep structured models for semantic segmentation. In Proc. CVPR, 2016
[16] M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn and A. Zisserman. The PASCAL visual object classes (VOC) challenge. In Proc. IJCV, 2010.
[17] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick. Microsoft COCO: Common objects in context. In Proc. ECCV, 2014.
[18] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. In arXiv, 2014.
[19] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In Proc. ICLR, 2015.
[20] P. Arbelaez, J. Pont-Tuset, J. Barron, F. Marques, and J. Malik. Multiscale combinatorial grouping. In Proc. CVPR, 2014
[21] Y. Li, H. Qi, J. Dai, X. Ji, and Y. Wei. Fully convolutional instance-aware semantic segmentation. In Proc. CVPR, 2017
[22] K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition. In Proc. CVPR, 2017