LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?

TL;DR

LaDiC achieves state-of-the-art performance for diffusion-based methods on the MS COCO dataset with 38.2 BLEU@4 and 126.2 CIDEr, demonstrating exceptional performance without pre-training or ancillary modules, revealing the previously untapped potential of diffusion models in image-to-text generation.

Abstract

Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on their applicability for such tasks. In this work, we revisit diffusion models, highlighting their capacity for holistic context modeling and parallel decoding. With these benefits, diffusion models can alleviate the inherent limitations of AR methods, including their slow inference speed, error propagation, and unidirectional constraints. Furthermore, we identify the prior underperformance of diffusion models stemming from the absence of an effective latent space for image-text alignment, and the discrepancy between continuous diffusion processes and discrete textual data. In response, we introduce a novel architecture, LaDiC, which utilizes a split BERT to create a dedicated latent space for captions and integrates a regularization module to manage varying text lengths. Our framework also includes a diffuser for semantic image-to-text conversion and a Back&Refine technique to enhance token interactivity during inference. LaDiC achieves state-of-the-art performance for diffusion-based methods on the MS COCO dataset with 38.2 BLEU@4 and 126.2 CIDEr, demonstrating exceptional performance without pre-training or ancillary modules. This indicates strong competitiveness with AR models, revealing the previously untapped potential of diffusion models in image-to-text generation.

Figures (11)

• Figure 1: Inference process for image captioning. (a) Token-by-token generation manner of AR-based model. (b) Gradually denoising generation manner of the diffusion-based model (Ours).
• Figure 2: Three advantages of our diffusion-based model (LaDiC) compared to auto-regressive models (BLIP).
• Figure 3: Comparison of the pipeline between our LaDiC and that of previous diffusion-based models. We introduce text latent space to alleviate the burden on the diffuser.
• Figure 4: An overview of our LaDiC model. It mainly consists of the Image Encoder, Text Encoder, Diffuser, and Text Decoder. The diffusion process is depicted on the left, while the denoising process is depicted on the right. Initially, the caption $c$ is encoded into a text latent $x_0$ by the text encoder. Subsequently, diffusion process occurs within the textual latent space $\mathcal{X}$, where a diffuser is trained to restore the noisy text latent $x_t$ to its clean counterparts $\hat{x}_0$, guided by the associated image. Finally, the denoised text latent $\hat{x}_0$ is passed through a NAR text decoder to generate the final caption $\hat{c}$.
• Figure 5: Illustration of Back$\&$Refine technique.