Learning full pairwise affinities for spectral segmentation

By Tae Hoon Kim, Kyoung Mu Lee, Sang Uk Lee. 2010

177 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Huchuan Lu
4. Lei Zhang
5. Ling Shao
6. Dacheng Tao
7. Xiaogang Wang
8. Ming-Ming Cheng

In Media Technology

1. Lei Zhang
2. Ming-Hsuan Yang
3. David Dapeng Zhang
4. Bo Peng
5. Shih-Fu Chang
6. Yanning Zhang
7. Radu Timofte
8. Shigang Liu

In Optimization & Training

1. Jitendra Malik
2. Xiang Ruan
3. Bo Peng
4. Asoke Kumar Nandi
5. Huchuan Lu
6. Du Tran
7. Ming-Hsuan Yang
8. Yanning Zhang

Citations in the corpus

• Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (2022, background): “The pixel-level pairwise affinity can be either hand-constructed [7, 23, 24] or learned [16, 17, 28, 34, 35,40,50].”
• Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation (2019, methodology): “Since a superpixel image is able to provide better local spatial information than a neighboring window of fixed size and shape, superpixel technologies such as mean-shift [11], simple linear iterative clustering (SLIC) [40], and WT [41], are usually considered as presegmentation algorithms for impro”
• Segmentation of Natural Images by Texture and Boundary Compression (2010, unknown): “C V ] 1 8”
• A survey of graph theoretical approaches to image segmentation (2013, methodology): “To quantitatively evaluate the segmentation results, as in [133,134]) we use five well-known indices: Probabilistic Rand (PR) index [107], Normalized Probabilistic Rand (NPR) index [107], Variation of Information (VI) [131], Global Consistency Error (GCE) [106] and Boundary Displacement Error (BDE) ”
• Saliency Detection via Graph-Based Manifold Ranking (2013, methodology): “To fully capture intrinsic graph structure information and incorporate local grouping cues in graph labelling, we use manifold ranking techniques to learn a ranking function, which is essential to learn an optimal affinity matrix [20].”
• Segmentation using superpixels: A bipartite graph partitioning approach (2012, methodology): “In contrast, MNcut, MLSS, Ncut, and TBES usually take more than 30, 40, 150, and 500 seconds, respectively.”