BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN. To date, almost all such approaches fall behind the two-stage Mask R-CNN method in mask precision when models have similar computation complexity, leaving great room for improvement. In this work, we achieve improved mask prediction by effectively combining instance-level information with semantic information with lower-level fine-granularity. Our main contribution is a blender module which draws inspiration from both top-down and bottom-up instance segmentation approaches. The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference. BlendMask can be easily incorporated with the state-of-the-art one-stage detection frameworks and outperforms Mask R-CNN under the same training schedule while being 20% faster. A light-weight version of BlendMask achieves $ 34.2% $ mAP at 25 FPS evaluated on a single 1080Ti GPU card. Because of its simplicity and efficacy, we hope that our BlendMask could serve as a simple yet strong baseline for a wide range of instance-wise prediction tasks. Code is available at

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Instance Segmentation COCO test-dev BlendMask (ResNet-101 + DCN interval=3) mask AP 41.3 # 57
AP50 63.1 # 17
AP75 44.6 # 14
APS 22.7 # 14
APM 44.1 # 12
APL 54.5 # 18
Real-time Instance Segmentation MSCOCO BlendMask-512 (DLA_34) Frame (fps) 33.3 # 6
mask AP 35.2 # 13