Hybrid Task Cascade for Instance Segmentation

TL;DR

The paper introduces Hybrid Task Cascade (HTC), a novel framework that interweaves detection and segmentation tasks in a multi-stage process, significantly improving instance segmentation performance on COCO dataset.

Contribution

It proposes a joint multi-stage framework that fully leverages the reciprocal relationship between detection and segmentation tasks, with a convolutional branch for spatial context.

Findings

Achieves 38.4 AP over Cascade Mask R-CNN baseline.

Attains 48.6 mask AP on COCO test-challenge split.

Ranks 1st in COCO 2018 Challenge Object Detection Task.

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.