CenterMask : Real-Time Anchor-Free Instance Segmentation

TL;DR

CenterMask introduces a real-time, anchor-free instance segmentation method with a novel spatial attention-guided mask, combined with improved backbone networks, achieving state-of-the-art accuracy and speed.

Contribution

The paper presents a new anchor-free segmentation approach with SAG-Mask and improved VoVNetV2 backbone, outperforming previous methods in accuracy and efficiency.

Findings

CenterMask achieves 38.3% AP with ResNet-101-FPN, surpassing previous methods.

CenterMask-Lite runs at over 35fps, outperforming state-of-the-art real-time methods.

The proposed VoVNetV2 backbone improves feature extraction for vision tasks.

Abstract

We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise. We also present an improved backbone networks, VoVNetV2, with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNet \cite{lee2019energy} and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of original SE. With SAG-Mask and VoVNetV2, we deign CenterMask and CenterMask-Lite that are targeted to large and small models, respectively. Using the same ResNet-101-FPN backbone, CenterMask achieves 38.3%, surpassing all previous state-of-the-art methods while at a much faster speed. CenterMask-Lite also outperforms the state-of-the-art by large margins at over 35fps on Titan Xp. We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively. The Code is available at https://github.com/youngwanLEE/CenterMask.