Contour-based instance segmentation methods are attractive due to their efficiency.
However, existing contour-based methods either suffer from lossy representation, complex …

This paper introduces a novel contour-based approach named deep snake for real-time
instance segmentation. Unlike some recent methods that directly regress the coordinates of …

We present a high-performance method that can achieve mask-level instance segmentation
with only bounding-box annotations for training. While this setting has been studied in the …

Current state-of-the-art instance segmentation methods are not suited for real-time
applications like autonomous driving, which require fast execution times at high accuracy …

We propose a simple yet effective instance segmentation framework, termed CondInst
(conditional convolutions for instance segmentation). Top-performing instance segmentation …

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework
for real-time instance segmentation. Previously, most instance segmentation methods …

Contour-based instance segmentation methods have developed rapidly recently but feature
rough and handcrafted front-end contour initialization, which restricts the model …

We propose a simple yet efficient anchor-free instance segmentation, called CenterMask,
that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one …

The key to a successful cascade architecture for precise instance segmentation is to fully
leverage the relationship between bounding box detection and mask segmentation across …

Instance segmentation requires a large number of training samples to achieve satisfactory
performance and benefits from proper data augmentation. To enlarge the training set and …