SOLOv2: Dynamic and Fast Instance Segmentation

Abstract

In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location. Specifically, the mask branch is decoupled into a mask kernel branch and mask feature branch, which are responsible for learning the convolution kernel and the convolved features respectively. Moreover, we propose Matrix NMS (non maximum suppression) to significantly reduce the inference time overhead due to NMS of masks. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate a simple direct instance segmentation system, outperforming a few state-of-the-art methods in both speed and accuracy. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential to serve as a new strong baseline for many instance-level recognition tasks besides instance segmentation. Code is available at: https://git.io/AdelaiDet

Accepted to Proc. Advances in Neural Information Processing Systems (NeurIPS'20). Code is available at: https://git.io/AdelaiDet

References in corpus (4)

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Semantic Instance Segmentation with a Discriminative Loss Function
• How Much Position Information Do Convolutional Neural Networks Encode?

Cited by in corpus (17)

• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
• MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
• A Comprehensive Review of Modern Object Segmentation Approaches
• Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images
• ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
• Video-Based Inpatient Fall Risk Assessment: A Case Study
• Methodology for generating synthetic labeled datasets for visual container inspection
• Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images
• Instance and Panoptic Segmentation Using Conditional Convolutions
• Trapped in texture bias? A large scale comparison of deep instance segmentation
• Joint prototype and coefficient prediction for 3D instance segmentation
• Landmark Policy Optimization for Object Navigation Task
• Novel View Synthesis of Humans using Differentiable Rendering
• Channel-wise Motion Features for Efficient Motion Segmentation
• ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass
• 3rd Place Solution for Short-video Face Parsing Challenge