paper-with-me

홈 › Papers

Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis

2023-07-22 · Hao Tang, Guolei Sun, Nicu Sebe, Luc van Gool

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three largely unresolved challenges. 1) The semantic labels do not provide detailed structural information, making it challenging to synthesize local details and structures; 2) The widely adopted CNN operations such as convolution, down-sampling, and normalization usually cause spatial resolution loss and thus cannot fully preserve the original semantic information, leading to semantically inconsistent results (e.g., missing small objects); 3) Existing semantic image synthesis methods focus on modeling 'local' semantic information from a single input semantic layout. However, they ignore 'global' semantic information of multiple input semantic layouts, i.e., semantic cross-relations between pixels across different input layouts. To tackle 1), we propose to use the edge as an intermediate representation which is further adopted to guide image generation via a proposed attention guided edge transfer module. To tackle 2), we design an effective module to selectively highlight class-dependent feature maps according to the original semantic layout to preserve the semantic information. To tackle 3), inspired by current methods in contrastive learning, we propose a novel contrastive learning method, which aims to enforce pixel embeddings belonging to the same semantic class to generate more similar image content than those from different classes. We further propose a novel multi-scale contrastive learning method that aims to push same-class features from different scales closer together being able to capture more semantic relations by explicitly exploring the structures of labeled pixels from multiple input semantic layouts from different scales.

📄 PDF Abstract BibTeX arXiv:2307.12084

Code (1)

ha0tang/ecgan 공식 구현 pytorch

Tasks

Contrastive LearningImage Generation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

A Framework For Image Synthesis Using Supervised Contrastive Learning

2024-12-05 · Yibin Liu, Jianyu Zhang, Li Zhang, Shijian Li 외

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods th…

Contrastive LearningGenerative Adversarial NetworkImage GenerationSemantic correspondence

Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis

2020-03-31 · Hao Tang, Xiaojuan Qi, Guolei Sun, Dan Xu 외

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satisfactory due to three largely unresolved …

Contrastive LearningImage Generation

Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection

2025-03-18 · Chunlei Li, Yilei Shi, Jingliang Hu, Xiao Xiang Zhu 외

Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approa…

Anomaly DetectionKnowledge DistillationSelf-Supervised LearningUnsupervised Anomaly Detection

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

2022-07-18 · Ziqiang Li, Chaoyue Wang, Heliang Zheng, Jing Zhang 외

Data-Efficient GANs (DE-GANs), which aim to learn generative models with a limited amount of training data, encounter several challenges for generating high-quality samples. Since data augmentation strategies have largel…

Contrastive LearningData AugmentationDiversity

KG-GAN: Knowledge-Guided Generative Adversarial Networks

2019-05-29 · Che-Han Chang, Chun-Hsien Yu, Szu-Ying Chen, Edward Y. Chang

Can generative adversarial networks (GANs) generate roses of various colors given only roses of red petals as input? The answer is negative, since GANs' discriminator would reject all roses of unseen petal colors. In thi…

Image Generation