paper-with-me

Papers

Unconditional Image-Text Pair Generation with Multimodal Cross Quantizer

2022-04-15 · Hyungyung Lee, Sungjin Park, Joonseok Lee, Edward Choi

Although deep generative models have gained a lot of attention, most of the existing works are designed for unimodal generation. In this paper, we explore a new method for unconditional image-text pair generation. We design Multimodal Cross-Quantization VAE (MXQ-VAE), a novel vector quantizer for joint image-text representations, with which we discover that a joint image-text representation space is effective for semantically consistent image-text pair generation. To learn a multimodal semantic correlation in a quantized space, we combine VQ-VAE with a Transformer encoder and apply an input masking strategy. Specifically, MXQ-VAE accepts a masked image-text pair as input and learns a quantized joint representation space, so that the input can be converted to a unified code sequence, then we perform unconditional image-text pair generation with the code sequence. Extensive experiments show the correlation between the quantized joint space and the multimodal generation capability on synthetic and real-world datasets. In addition, we demonstrate the superiority of our approach in these two aspects over several baselines. The source code is publicly available at: https://github.com/ttumyche/MXQ-VAE.

📄 PDF Abstract BibTeX arXiv:2204.07537

Code (1)

ttumyche/mxq-vae 공식 구현 pytorch

Tasks

multimodal generationQuantization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation

2026-06-15 · Kyeongmin Yeo, Yunhong Min, Minhyuk Sung arxiv

We introduce MUNI, an end-to-end multimodal latent diffusion framework for any-to-any generation that unifies subset-conditioned cross-modal generation and unconditional joint sampling through a shared stochastic latent.…

Text-to-Image Generation Via Energy-Based CLIP

2024-08-30 · Roy Ganz, Michael Elad

Joint Energy Models (JEMs), while drawing significant research attention, have not been successfully scaled to real-world, high-resolution datasets. We present EB-CLIP, a novel approach extending JEMs to the multimodal v…

Image GenerationText to Image GenerationText-to-Image Generation

Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG

2026-07-12 · Saadeldine Eletter, Owais Aijaz, Preslav Nakov arxiv

Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, e…

Style Transfer

LT-GAN: Self-Supervised GAN with Latent Transformation Detection

2020-10-19 · Parth Patel, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy

Generative Adversarial Networks (GANs) coupled with self-supervised tasks have shown promising results in unconditional and semi-supervised image generation. We propose a self-supervised approach (LT-GAN) to improve the …

Image Generation

FashionEngine: Interactive 3D Human Generation and Editing via Multimodal Controls

2024-04-02 · Tao Hu, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu

We present FashionEngine, an interactive 3D human generation and editing system that creates 3D digital humans via user-friendly multimodal controls such as natural languages, visual perceptions, and hand-drawing sketche…

Virtual Try-on