Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation

10/22/2021
by   Antonio Tavera, et al.
0

In this paper we consider the task of semantic segmentation in autonomous driving applications. Specifically, we consider the cross-domain few-shot setting where training can use only few real-world annotated images and many annotated synthetic images. In this context, aligning the domains is made more challenging by the pixel-wise class imbalance that is intrinsic in the segmentation and that leads to ignoring the underrepresented classes and overfitting the well represented ones. We address this problem with a novel framework called Pixel-By-Pixel Cross-Domain Alignment (PixDA). We propose a novel pixel-by-pixel domain adversarial loss following three criteria: (i) align the source and the target domain for each pixel, (ii) avoid negative transfer on the correctly represented pixels, and (iii) regularize the training of infrequent classes to avoid overfitting. The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images. We demonstrate on standard synthetic-to-real benchmarks that PixDA outperforms previous state-of-the-art methods in (1-5)-shot settings.

READ FULL TEXT

page 1

page 4

page 5

page 8

research
03/10/2020

Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation

Unsupervised domain adaptation enables to alleviate the need for pixel-w...
research
06/04/2021

Few-Shot Segmentation via Cycle-Consistent Transformer

Few-shot segmentation aims to train a segmentation model that can fast a...
research
06/22/2021

Give Me Your Trained Model: Domain Adaptive Semantic Segmentation without Source Data

Benefited from considerable pixel-level annotations collected from a spe...
research
08/01/2023

Adaptive Semantic Consistency for Cross-domain Few-shot Classification

Cross-domain few-shot classification (CD-FSC) aims to identify novel tar...
research
12/15/2020

Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation

Existing techniques to adapt semantic segmentation networks across the s...
research
03/06/2022

Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment

Training a generative adversarial network (GAN) with limited data has be...
research
03/16/2022

CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning

Generating artistic portraits is a challenging problem in computer visio...

Please sign up or login with your details

Forgot password? Click here to reset