Building instance segmentation models that are data-efficient and can handle rare object
categories is an important challenge in computer vision. Leveraging data augmentations is a …

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 …

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 …

Copy-Paste is a simple and effective data augmentation strategy for instance segmentation.
By randomly pasting object instances onto new background images, it creates new training …

Instance segmentation is an active topic in computer vision that is usually solved by using
supervised learning approaches over very large datasets composed of object level masks …

Abstract We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask
auto-labeling framework for instance segmentation using only box annotations. MAL takes …

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

Recently, proposal-free instance segmentation has received increasing attention due to its
concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic …

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

Open-world instance segmentation is the task of grouping pixels into object instances
without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely …