2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Author and article information

          Journal
          09 February 2022
          Article
          2202.04287
          bc2e16c5-6823-45b9-ae39-4f87f481570c

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          AAAI 2022. Project page: http://sites.google.com/view/ast-ocdaseg
          cs.CV cs.LG

          Computer vision & Pattern recognition,Artificial intelligence
          Computer vision & Pattern recognition, Artificial intelligence

          Comments

          Comment on this article