Efficient Semantic Image Synthesis via Class-Adaptive Normalization

• URL: http://arxiv.org/abs/2012.04644v2
• Date: Tue, 4 May 2021 23:20:35 GMT
• Title: Efficient Semantic Image Synthesis via Class-Adaptive Normalization
• Authors: Zhentao Tan and Dongdong Chen and Qi Chu and Menglei Chai and Jing Liao and Mingming He and Lu Yuan and Gang Hua and Nenghai Yu
• Abstract summary: Class-adaptive normalization (CLADE) is a lightweight but equally-effective variant that is only adaptive to semantic class. We introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE. The proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE.
• Score: 116.63715955932174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the advantages inside the box is still highly demanded to help reduce the significant computation and parameter overhead introduced by this novel structure. In this paper, from a return-on-investment point of view, we conduct an in-depth analysis of the effectiveness of this spatially-adaptive normalization and observe that its modulation parameters benefit more from semantic-awareness rather than spatial-adaptiveness, especially for high-resolution input masks. Inspired by this observation, we propose class-adaptive normalization (CLADE), a lightweight but equally-effective variant that is only adaptive to semantic class. In order to further improve spatial-adaptiveness, we introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE and propose a truly spatially-adaptive variant of CLADE, namely CLADE-ICPE.Through extensive experiments on multiple challenging datasets, we demonstrate that the proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE, but it is much more efficient with fewer extra parameters and lower computational cost. The code and pretrained models are available at \url{https://github.com/tzt101/CLADE.git}.

Related papers

• Transducer Consistency Regularization for Speech to Text Applications [4.510630624936377]
  We present Transducer Consistency Regularization (TCR), a consistency regularization method for transducer models. We utilize occupational probabilities to give different weights on transducer output distributions, thus only alignments close to oracle alignments would contribute to the model learning. Our experiments show the proposed method is superior to other consistency regularization implementations and could effectively reduce word error rate (WER) by 4.3% relatively comparing with a strong baseline on the textscLibrispeech dataset.
  arXiv  Detail & Related papers  (2024-10-09T23:53:13Z)
• Conditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization [2.3419031955865517]
  We propose a learning-based registration approach based on a novel conditional spatially adaptive instance normalization (CSAIN) Experiments show that our proposed method outperforms the baseline approaches while achieving spatially-variant and adaptive regularization.
  arXiv  Detail & Related papers  (2023-03-19T16:12:06Z)
• Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis [68.1281982092765]
  We propose a novel normalization module, termed as REtrieval-based Spatially AdaptIve normaLization (RESAIL) RESAIL provides pixel level fine-grained guidance to the normalization architecture. Experiments on several challenging datasets show that our RESAIL performs favorably against state-of-the-arts in terms of quantitative metrics, visual quality, and subjective evaluation.
  arXiv  Detail & Related papers  (2022-04-06T14:21:39Z)
• Adaptive and Cascaded Compressive Sensing [10.162966219929887]
  Scene-dependent adaptive compressive sensing (CS) has been a long pursuing goal which has huge potential in significantly improving the performance of CS. We propose a restricted isometry property (RIP) condition based error clamping, which could directly predict the reconstruction error. We also propose a cascaded feature fusion reconstruction network that could efficiently utilize the information derived from different adaptive sampling stages.
  arXiv  Detail & Related papers  (2022-03-21T07:50:24Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Deep Contrastive Graph Representation via Adaptive Homotopy Learning [76.22904270821778]
  Homotopy model is an excellent tool exploited by diverse research works in the field of machine learning. We propose a novel adaptive homotopy framework (AH) in which the Maclaurin duality is employed. AH can be widely utilized to enhance the homotopy-based algorithm.
  arXiv  Detail & Related papers  (2021-06-17T04:46:04Z)
• SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients [99.13839450032408]
  It is desired to design a universal framework for adaptive algorithms to solve general problems. In particular, our novel framework provides adaptive methods under non convergence support for setting.
  arXiv  Detail & Related papers  (2021-06-15T15:16:28Z)
• Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications [5.660384137948734]
  The proposed algorithm converges to the correct distribution with a controllable bias under mild conditions. We show that the proposed algorithm canally converge to the correct distribution with a controllable bias under mild conditions.
  arXiv  Detail & Related papers  (2020-06-29T20:57:20Z)
• Rethinking Spatially-Adaptive Normalization [111.13203525538496]
  Class-adaptive normalization (CLADE) is a lightweight variant that is not adaptive to spatial positions or layouts. CLADE greatly reduces the computation cost while still being able to preserve the semantic information during the generation.
  arXiv  Detail & Related papers  (2020-04-06T17:58:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.