paper-with-me

Papers

Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation

2022-09-28 · Xintian Wu, Hanbin Zhao, Liangli Zheng, Shouhong Ding, Xi Li

As a challenging task, text-to-image generation aims to generate photo-realistic and semantically consistent images according to the given text descriptions. Existing methods mainly extract the text information from only one sentence to represent an image and the text representation effects the quality of the generated image well. However, directly utilizing the limited information in one sentence misses some key attribute descriptions, which are the crucial factors to describe an image accurately. To alleviate the above problem, we propose an effective text representation method with the complements of attribute information. Firstly, we construct an attribute memory to jointly control the text-to-image generation with sentence input. Secondly, we explore two update mechanisms, sample-aware and sample-joint mechanisms, to dynamically optimize a generalized attribute memory. Furthermore, we design an attribute-sentence-joint conditional generator learning scheme to align the feature embeddings among multiple representations, which promotes the cross-modal network training. Experimental results illustrate that the proposed method obtains substantial performance improvements on both the CUB (FID from 14.81 to 8.57) and COCO (FID from 21.42 to 12.39) datasets.

📄 PDF Abstract BibTeX arXiv:2209.14046

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImage GenerationSentenceText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search

2017-07-01 · CVPR 2017 7 · Bo Zhao, Jiashi Feng, Xiao Wu, Shuicheng Yan

We introduce a new fashion search protocol where attribute manipulation is allowed within the interaction between users and search engines, e.g. manipulating the color attribute of the clothing from red to blue. It is pa…

AttributeRepresentation LearningTriplet

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models

2023-03-19 · CVPR 2023 1 · Matthew L. Olson, Shusen Liu, Rushil Anirudh, Jayaraman J. Thiagarajan 외

Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for tools to audit trained networks in human intelligible for…

AttributeFairness

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures

2025-08-14 · Parsa Omidi, Xingshuai Huang, Axel Laborieux, Bahareh Nikpour 외 arxiv

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations i…

Continual Learning

GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting

2023-02-28 · CVPR 2023 1 · Kangyang Luo, Xiang Li, Yunshi Lan, Ming Gao

Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community. However, catastrophic forgetting caused by data heterogeneity and partial parti…

Continual LearningFederated Learningimage-classificationImage Classification

Towards Equitable AI: Detecting Bias in Using Large Language Models for Marketing

2025-02-18 · Berk Yilmaz, Huthaifa I. Ashqar

The recent advances in large language models (LLMs) have revolutionized industries such as finance, marketing, and customer service by enabling sophisticated natural language processing tasks. However, the broad adoption…

Bias DetectionMarketing