SOLO: Segmenting Objects by Locations

Abstract

We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-thensegment' strategy as used by Mask R-CNN, or predict category masks first then use clustering techniques to group pixels into individual instances. We view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size, thus nicely converting instance mask segmentation into a classification-solvable problem. Now instance segmentation is decomposed into two classification tasks. We demonstrate a much simpler and flexible instance segmentation framework with strong performance, achieving on par accuracy with Mask R-CNN and outperforming recent singleshot instance segmenters in accuracy. We hope that this very simple and strong framework can serve as a baseline for many instance-level recognition tasks besides instance segmentation.

Accepted to Proc. Eur. Conf. Computer Vision (ECCV) 2020. Code is available at https://git.io/AdelaiDet

References in corpus (7)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Learning to Segment Object Candidates
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Semantic Instance Segmentation with a Discriminative Loss Function
• Hybrid Task Cascade for Instance Segmentation
• How Much Position Information Do Convolutional Neural Networks Encode?
• PolarMask: Single Shot Instance Segmentation with Polar Representation

Cited by in corpus (16)

• Dense RepPoints: Representing Visual Objects with Dense Point Sets
• Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
• Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
• Mask Encoding for Single Shot Instance Segmentation
• Deep Variational Instance Segmentation
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• CASNet: Common Attribute Support Network for image instance and panoptic segmentation
• Industrial Machine Tool Component Surface Defect Dataset
• PointINS: Point-based Instance Segmentation
• Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval
• S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
• Human-centric Relation Segmentation: Dataset and Solution
• Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
• Zero-Shot Instance Segmentation
• Multi-Scale Aligned Distillation for Low-Resolution Detection
• Understanding in Artificial Intelligence