Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift

10/13/2022
by   Sharat Agarwal, et al.
16

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between supervised and unsupervised DA techniques, ADA allows for an excellent trade-off between annotation cost and performance. Prior art makes use of measures of uncertainty or disagreement of models to identify `regions' to be annotated by the human oracle. However, these regions frequently comprise of pixels at object boundaries which are hard and tedious to annotate. Hence, even if the fraction of image pixels annotated reduces, the overall annotation time and the resulting cost still remain high. In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame. We show that these set of `hard' classes are context-dependent and typically vary across frames, and when annotated help the model generalize better. We propose two ADA techniques: the Anchor-based and Augmentation-based approaches to select complementary and diverse regions in the context of the current training set. Our approach achieves 66.6 mIoU on GTA to Cityscapes dataset with an annotation budget of 4.7 can also be used as a decorator for any existing frame-based AL technique, e.g., we report 1.5 approach.

READ FULL TEXT

page 1

page 3

page 5

page 7

research
10/16/2020

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Generalizing deep neural networks to new target domains is critical to t...
research
03/10/2023

Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D c...
research
07/21/2023

Divide and Adapt: Active Domain Adaptation via Customized Learning

Active domain adaptation (ADA) aims to improve the model adaptation perf...
research
06/19/2023

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

For the task of semantic segmentation (SS) under domain shift, active le...
research
03/09/2023

Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images

Accurate segmentation of tissue in histopathological images can be very ...
research
05/09/2023

Unsupervised Domain Adaptation for Semantic Segmentation via Feature-space Density Matching

Semantic segmentation is a critical step in automated image interpretati...
research
12/29/2016

From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example

Supervised learning tends to produce more accurate classifiers than unsu...

Please sign up or login with your details

Forgot password? Click here to reset