Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation

02/09/2022
by   Jogendra Nath Kundu, et al.
0

Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled target data in order to generalize better on novel unseen domains. We hypothesize that an improved disentanglement of domain-related and task-related factors of dense intermediate layer features can greatly aid OCDA. Prior-arts attempt this indirectly by employing adversarial domain discriminators on the spatial CNN output. However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CNN features hold a more tractable mapping with domain discrimination. Motivated by this, we propose a novel feature space Amplitude Spectrum Transformation (AST). During adaptation, we employ the AST auto-encoder for two purposes. First, carefully mined source-target instance pairs undergo a simulation of cross-domain feature stylization (AST-Sim) at a particular layer by altering the AST-latent. Second, AST operating at a later layer is tasked to normalize (AST-Norm) the domain content by fixing its latent to a mean prototype. Our simplified adaptation technique is not only clustering-free but also free from complex adversarial alignment. We achieve leading performance against the prior arts on the OCDA scene segmentation benchmarks.

READ FULL TEXT

page 3

page 4

page 9

page 11

research
08/25/2021

Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation

Unsupervised domain adaptation (DA) has gained substantial interest in s...
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
04/17/2018

Cross-Domain Adversarial Auto-Encoder

In this paper, we propose the Cross-Domain Adversarial Auto-Encoder (CDA...
research
08/06/2021

Adapting Segmentation Networks to New Domains by Disentangling Latent Representations

Deep learning models achieve outstanding accuracy in semantic segmentati...
research
11/24/2021

SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning

Although there is significant progress in supervised semantic segmentati...
research
06/16/2022

Balancing Discriminability and Transferability for Source-Free Domain Adaptation

Conventional domain adaptation (DA) techniques aim to improve domain tra...
research
04/12/2023

Semantic-Aware Mixup for Domain Generalization

Deep neural networks (DNNs) have shown exciting performance in various t...

Please sign up or login with your details

Forgot password? Click here to reset