DeepAI AI Chat
Log In Sign Up

Zero-Shot Instance Segmentation

by   Ye Zheng, et al.

Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires high professional skills. We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI). In the training phase of ZSI, the model is trained with seen data, while in the testing phase, it is used to segment all seen and unseen instances. We first formulate the ZSI task and propose a method to tackle the challenge, which consists of Zero-shot Detector, Semantic Mask Head, Background Aware RPN and Synchronized Background Strategy. We present a new benchmark for zero-shot instance segmentation based on the MS-COCO dataset. The extensive empirical results in this benchmark show that our method not only surpasses the state-of-the-art results in zero-shot object detection task but also achieves promising performance on ZSI. Our approach will serve as a solid baseline and facilitate future research in zero-shot instance segmentation.


page 1

page 4

page 8


Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline

Methods for object detection and segmentation often require abundant ins...

SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments

Object instance segmentation is a key challenge for indoor robots naviga...

One-Shot Instance Segmentation

We tackle one-shot visual search by example for arbitrary object categor...

Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation

Recent mask proposal models have significantly improved the performance ...

X-Paste: Revisit Copy-Paste at Scale with CLIP and StableDiffusion

Copy-Paste is a simple and effective data augmentation strategy for inst...

Instance Segmentation based Semantic Matting for Compositing Applications

Image compositing is a key step in film making and image editing that ai...

Deep Semantic Instance Segmentation of Tree-like Structures Using Synthetic Data

Tree-like structures, such as blood vessels, often express complexity at...