Hybrid Task Cascade for Instance Segmentation

Abstract

Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks 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. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4 and 1.5 improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at: https://github.com/open-mmlab/mmdetection.

CVPR 2019 camera ready

Cited by in corpus (17)

• Libra R-CNN: Towards Balanced Learning for Object Detection
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• Learning Modulated Loss for Rotated Object Detection
• PF-Net: Point Fractal Network for 3D Point Cloud Completion
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
• Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
• Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search
• MovieNet: A Holistic Dataset for Movie Understanding
• 1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
• Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
• 2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection
• Object-Guided Instance Segmentation for Biological Images
• Renovating Parsing R-CNN for Accurate Multiple Human Parsing
• AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
• Detecting Reflections by Combining Semantic and Instance Segmentation
• Enforcing Reasoning in Visual Commonsense Reasoning