Attentive Normalization for Conditional Image Generation

• URL: http://arxiv.org/abs/2004.03828v1
• Date: Wed, 8 Apr 2020 06:12:25 GMT
• Title: Attentive Normalization for Conditional Image Generation
• Abstract summary: We characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization. Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations. Experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.
• Score: 126.08247355367043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain. It is still not sufficient for categories with complicated structures. In this paper, we characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization. Specifically, the input feature map is softly divided into several regions based on its internal semantic similarity, which are respectively normalized. It enhances consistency between distant regions with semantic correspondence. Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations, and thus can be directly applied to large-size feature maps without much computational burden. Extensive experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.

Related papers

• SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies [27.260310284240248]
  SeesawNet is a unified architecture that balances common and instance-specific dependency modeling in both temporal and channel dimensions.<n>At its core is Adaptive Stationary-Nonstationary Attention (ASNA), which captures common dependencies from normalized sequences and specific dependencies from raw sequences.<n>Built upon ASNA, SeesawNet alternates dedicated temporal and channel relationship modeling to jointly capture long-range and cross-variable dependencies.
  arXiv  Detail & Related papers  (2026-05-14T08:29:52Z)
• Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation [48.806000388608005]
  Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts.<n>We propose a more direct approach that eschews the logits-optimization process by directly deriving an analytic solution for the segmentation map.
  arXiv  Detail & Related papers  (2026-04-09T02:14:35Z)
• Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification [17.399427621622703]
  We establish representation-based generalization bounds in a distribution-free transductive setting.<n>Our bounds are efficiently computable and strongly correlate with empirical generalization in graph node classification.<n>This yields depth-dependent characterizations that capture the non-monotonic relationship between depth and generalization error.
  arXiv  Detail & Related papers  (2026-03-10T06:43:18Z)
• EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models [52.3015009878545]
  We develop an image segmentor capable of generating fine-grained segmentation maps without any additional training. Our framework identifies semantic correspondences between image pixels and spatial locations of low-dimensional feature maps. In extensive experiments, the produced segmentation maps are demonstrated to be well delineated and capture detailed parts of the images.
  arXiv  Detail & Related papers  (2024-01-22T07:34:06Z)
• Smooth image-to-image translations with latent space interpolations [64.8170758294427]
  Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain. We show that our regularization techniques can improve the state-of-the-art I2I translations by a large margin.
  arXiv  Detail & Related papers  (2022-10-03T11:57:30Z)
• An attention-driven hierarchical multi-scale representation for visual recognition [3.3302293148249125]
  Convolutional Neural Networks (CNNs) have revolutionized the understanding of visual content. We propose a method to capture high-level long-range dependencies by exploring Graph Convolutional Networks (GCNs) Our approach is simple yet extremely effective in solving both the fine-grained and generic visual classification problems.
  arXiv  Detail & Related papers  (2021-10-23T09:22:22Z)
• Image Synthesis via Semantic Composition [74.68191130898805]
  We present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations.
  arXiv  Detail & Related papers  (2021-09-15T02:26:07Z)
• Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition [50.932864767867365]
  We propose a framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Based on the precise attribute locations, we propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. Results show that the proposed method performs favorably against state-of-the-art methods without increasing parameters.
  arXiv  Detail & Related papers  (2021-09-13T03:36:44Z)
• ICON: Learning Regular Maps Through Inverse Consistency [19.27928605302463]
  We explore what induces regularity for spatial transformations, e.g., when computing image registrations. We find that deep networks combined with an inverse consistency loss and randomized off-grid yield well behaved, approximately diffeomorphic, spatial transformations. Despite the simplicity of this approach, our experiments present compelling evidence, on both synthetic and real data, that regular maps can be obtained without carefully tuned explicit regularizers and competitive registration performance.
  arXiv  Detail & Related papers  (2021-05-10T15:52:12Z)
• Stride and Translation Invariance in CNNs [2.4213989921339847]
  We show that stride can greatly benefit translation invariance given that it is combined with sufficient similarity between neighbouring pixels. We also explore the efficacy of other solutions proposed, namely global average pooling, anti-aliasing, and data augmentation.
  arXiv  Detail & Related papers  (2021-03-18T09:17:06Z)
• HCNet: Hierarchical Context Network for Semantic Segmentation [6.4047628200011815]
  We propose a hierarchical context network to model homogeneous pixels with strong correlations and heterogeneous pixels with weak correlations. Our approach realizes a mean IoU of 82.8% and overall accuracy of 91.4% on Cityscapes and ISPRS Vaihingen dataset.
  arXiv  Detail & Related papers  (2020-10-10T09:51:17Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.