TensorMask: A Foundation for Dense Object Segmentation

by   Xinlei Chen, et al.

Sliding-window object detectors that generate bounding-box object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN. In this work, we investigate the paradigm of dense sliding-window instance segmentation, which is surprisingly under-explored. Our core observation is that this task is fundamentally different than other dense prediction tasks such as semantic segmentation or bounding-box object detection, as the output at every spatial location is itself a geometric structure with its own spatial dimensions. To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors. We demonstrate that the tensor view leads to large gains over baselines that ignore this structure, and leads to results comparable to Mask R-CNN. These promising results suggest that TensorMask can serve as a foundation for novel advances in dense mask prediction and a more complete understanding of the task. Code will be made available.


page 1

page 2

page 7

page 10

page 11


SOLO: A Simple Framework for Instance Segmentation

Compared to many other dense prediction tasks, e.g., semantic segmentati...

Mask R-CNN

We present a conceptually simple, flexible, and general framework for ob...

Semi-convolutional Operators for Instance Segmentation

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

Non-local RoIs for Instance Segmentation

We introduce the concept of Non-Local RoI (NL-RoI) Block as a generic an...

Oriented Boxes for Accurate Instance Segmentation

State-of-the-art instance-aware semantic segmentation algorithms use axi...

Towards Bounding-Box Free Panoptic Segmentation

In this work we introduce a new bounding-box free network (BBFNet) for p...

Intelligent Debris Mass Estimation Model for Autonomous Underwater Vehicle

Marine debris poses a significant threat to the survival of marine wildl...

Code Repositories


Instance Segmentation, TensorMask

view repo

Please sign up or login with your details

Forgot password? Click here to reset