Name
Title | ||
|---|---|---|
Instance Segmentation By Jointly Optimizing Spatial Embeddings And Clustering Bandwidth |
Abstract | ||
|---|---|---|
Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy, they are slow and generate masks at a fixed and low resolution. Proposal-free methods, by contrast, can generate masks at high resolution and are often faster, but fail to reach the same accuracy as the proposal-based methods. In this work we propose a new clustering loss function for proposal-free instance segmentation. The loss function pulls the spatial embeddings of pixels belonging to the same instance together and jointly learns an instance-specific clustering bandwidth, maximizing the intersection-over-union of the resulting instance mask. When combined with a fast architecture, the network can perform instance segmentation in real-time while maintaining a high accuracy. We evaluate our method on the challenging Cityscapes benchmark and achieve top results (5% improvement over Mask R-CNN) at more than 10 fps on 2MP images.(1) |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.00904 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
DocType | Volume | ISSN |
Conference | abs/1906.11109 | 1063-6919 |
Citations | PageRank | References |
11 | 0.48 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Davy Neven | 1 | 32 | 2.11 |
| Bert De Brabandere | 2 | 54 | 3.89 |
| Marc Proesmans | 3 | 277 | 34.37 |
| Luc Van Gool | 4 | 27566 | 1819.51 |