SOLO: A Simple Framework for Instance Segmentation

by   Xinlong Wang, et al.

Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-then-segment' strategy (e.g., Mask R-CNN), or predict embedding vectors first then cluster pixels into individual instances. In this paper, 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. With this notion, we propose segmenting objects by locations (SOLO), a simple, direct, and fast framework for instance segmentation with strong performance. We derive a few SOLO variants (e.g., Vanilla SOLO, Decoupled SOLO, Dynamic SOLO) following the basic principle. Our method directly maps a raw input image to the desired object categories and instance masks, eliminating the need for the grouping post-processing or the bounding box detection. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy, while being considerably simpler than the existing methods. Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation. We further demonstrate the flexibility and high-quality segmentation of SOLO by extending it to perform one-stage instance-level image matting. Code is available at:


page 8

page 12

page 16

page 18

page 19

page 20


SOLO: Segmenting Objects by Locations

We present a new, embarrassingly simple approach to instance segmentatio...

TensorMask: A Foundation for Dense Object Segmentation

Sliding-window object detectors that generate bounding-box object predic...

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

Open-world instance segmentation is the task of grouping pixels into obj...

Semi-convolutional Operators for Instance Segmentation

Object detection and instance segmentation are dominated by region-based...

HistoNet: Predicting size histograms of object instances

We propose to predict histograms of object sizes in crowded scenes direc...

Open-Vocabulary Panoptic Segmentation with MaskCLIP

In this paper, we tackle a new computer vision task, open-vocabulary pan...

Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment

Automatic instance segmentation of glomeruli within kidney Whole Slide I...