SOLO: Segmenting Objects by Locations

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.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) mask AP 40.4% # 67
AP50 62.7% # 18
AP75 43.3% # 16
APS 17.6% # 31
APM 43.3% # 13
APL 58.9% # 13
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) mask AP 40.4 # 67
AP50 62.7 # 18
AP75 43.3 # 16
APS 17.6 # 31
APM 43.3 # 13
APL 58.9 # 13