Abstract | ||
---|---|---|
Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose Content-Aware ReAssembly of FEatures (CARAFE), a universal, lightweight and highly effective operator to fulfill this goal. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit subpixel neighborhood, CARAFE can aggregate contextual information within a large receptive field. (2) Content-aware handling. Instead of using a fixed kernel for all samples (e.g. deconvolution), CARAFE enables instance-specific content-aware handling, which generates adaptive kernels on-the-fly. (3) Lightweight and fast to compute. CARAFE introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation and in-painting. CARAFE shows consistent and substantial gains across all the tasks (1.2% AP, 1.3% AP, 1.8% mIoU, 1.1dB respectively) with negligible computational overhead. It has great potential to serve as a strong building block for future research. Code and models are available at https://github.com/open-mmlab/mmdetection. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICCV.2019.00310 | 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) |
Field | DocType | Volume |
Computer vision,Computer science,Artificial intelligence | Conference | abs/1905.02188 |
Issue | ISSN | Citations |
1 | 1550-5499 | 7 |
PageRank | References | Authors |
0.44 | 7 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaqi Wang | 1 | 77 | 4.20 |
Kai Chen | 2 | 130 | 8.65 |
Rui Xu | 3 | 20 | 2.66 |
Ziwei Liu | 4 | 1361 | 63.23 |
Chen Change Loy | 5 | 4484 | 178.56 |
Dahua Lin | 6 | 1117 | 72.62 |