Hybrid Task Cascade

Introduced by Chen et al. in Hybrid Task Cascade for Instance Segmentation

Hybrid Task Cascade, or HTC, is a framework for cascading in instance segmentation. It differs from Cascade Mask R-CNN in two important aspects: (1) instead of performing cascaded refinement on the two tasks of detection and segmentation separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.

Source: Hybrid Task Cascade for Instance Segmentation

Latest Papers

PAPER DATE
Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track
| Zehui ChenQiaofei LiFeng Zhao
2020-09-10
AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
Wenshuo MaTingzhong TianHang XuYimin HuangZhenguo Li
2020-07-18
Development and evaluation of a test setup to investigate distance differences in immersive virtual environments
| Stephan FremereyMuhammad Sami SulemanAbdul Haq Azeem Paracha and Alexander Raake
2020-06-23
Deeply Shape-guided Instance Segmentation
Hao DingSiyuan QiaoAlan YuilleWei Shen
2019-11-25
Hybrid Task Cascade for Instance Segmentation
| Kai ChenJiangmiao PangJiaqi WangYu XiongXiaoxiao LiShuyang SunWansen FengZiwei LiuJianping ShiWanli OuyangChen Change LoyDahua Lin
2019-01-22

Tasks

TASK PAPERS SHARE
Instance Segmentation 3 37.50%
Semantic Segmentation 3 37.50%
Object Detection 2 25.00%

Categories