paper-with-me

Papers

Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation

2023-08-02 · Guojin Zhong, Jin Yuan, Pan Wang, Kailun Yang, Weili Guan, Zhiyong Li

The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image. This paper proposes a novel model named "Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment" (FSA-CDM), which introduces contrastive positive/negative samples into the diffusion model to boost performance for markup-to-image generation. Technically, we design a fine-grained cross-modal alignment module to well explore the sequence similarity between the two modalities for learning robust feature representations. To improve the generalization ability, we propose a contrast-augmented diffusion model to explicitly explore positive and negative samples by maximizing a novel contrastive variational objective, which is mathematically inferred to provide a tighter bound for the model's optimization. Moreover, the context-aware cross attention module is developed to capture the contextual information within markup language during the denoising process, yielding better noise prediction results. Extensive experiments are conducted on four benchmark datasets from different domains, and the experimental results demonstrate the effectiveness of the proposed components in FSA-CDM, significantly exceeding state-of-the-art performance by about 2%-12% DTW improvements. The code will be released at https://github.com/zgj77/FSACDM.

📄 PDF Abstract BibTeX arXiv:2308.01147

Code (1)

zgj77/fsacdm 공식 구현

Tasks

cross-modal alignmentDenoisingImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
DTW Dynamic Time Warping (DTW) [1] is one of well-known distance measures between a pairwise of time series. The main idea of DTW is to compute the distance from the matching of…

Similar Papers 제목 키워드 기반

Learnable Sequence Augmenter for Triplet Contrastive Learning in Sequential Recommendation

2025-03-26 · Wei Wang, Yujie Lin, Jianli Zhao, Moyan Zhang 외

Most existing contrastive learning-based sequential recommendation (SR) methods rely on random operations (e.g., crop, reorder, and substitute) to generate augmented sequences. These methods often struggle to create posi…

Contrastive LearningSelf-Supervised LearningSequential RecommendationTriplet

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

2025-02-02 · Yuanhuiyi Lyu, Xu Zheng, Lutao Jiang, Yibo Yan 외

Recent text-to-image generative models, e.g., Stable Diffusion V3 and Flux, have achieved notable progress. However, these models are strongly restricted to their limited knowledge, a.k.a., their own fixed parameters, th…

Contrastive LearningImage GenerationObjectRAG+2

Intent-aware Diffusion with Contrastive Learning for Sequential Recommendation

2025-04-22 · Yuanpeng Qu, Hajime Nobuhara

Contrastive learning has proven effective in training sequential recommendation models by incorporating self-supervised signals from augmented views. Most existing methods generate multiple views from the same interactio…

Contrastive LearningData AugmentationSequential Recommendation

Diffusion-based Contrastive Learning for Sequential Recommendation

2024-05-15 · Ziqiang Cui, Haolun Wu, Bowei He, Ji Cheng 외

Contrastive learning has been effectively utilized to enhance the training of sequential recommendation models by leveraging informative self-supervised signals. Most existing approaches generate augmented views of the s…

Contrastive LearningSequential Recommendation

Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models

2026-07-05 · Riccardo O. Feingold, Davide Liconti, Chenyu Yang, Robert K. Katzschmann arxiv

Action-conditioned world models allow robots to predict the future consequences of candidate actions without additional physical interaction, supporting policy evaluation, planning, and data augmentation. We present Mask…

Data Augmentation