Deep Level Set for Box-supervised Instance Segmentation in Aerial Images

by   Wentong Li, et al.

Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object collections, aerial objects have large intra-class variances and inter-class similarity with complex background. Moreover, there are many tiny objects in the high-resolution satellite images. This makes the recent pairwise affinity modeling method inevitably to involve the noisy supervision with the inferior results. To tackle these problems, we propose a novel aerial instance segmentation approach, which drives the network to learn a series of level set functions for the aerial objects with only box annotations in an end-to-end fashion. Instead of learning the pairwise affinity, the level set method with the carefully designed energy functions treats the object segmentation as curve evolution, which is able to accurately recover the object's boundaries and prevent the interference from the indistinguishable background and similar objects. The experimental results demonstrate that the proposed approach outperforms the state-of-the-art box-supervised instance segmentation methods. The source code is available at



page 1

page 3

page 7

page 8


Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...

Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

Instance segmentation is of great importance for many biological applica...

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Aerial Image Segmentation is a particular semantic segmentation problem ...

iShape: A First Step Towards Irregular Shape Instance Segmentation

In this paper, we introduce a brand new dataset to promote the study of ...

Layered Embeddings for Amodal Instance Segmentation

The proposed method extends upon the representational output of semantic...

Natural Image Matting via Guided Contextual Attention

Over the last few years, deep learning based approaches have achieved ou...

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

Open-world instance segmentation is the task of grouping pixels into obj...

Code Repositories


The code for "Deep Level Set for Box-supervised Instance Segmentation in Aerial Images".

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.