Pith. sign in

REVIEW 6 cited by

A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.16656 v1 pith:HJSZSVMQ submitted 2023-10-25 cs.CV cs.AIcs.LG

classification cs.CVcs.AIcs.LG
keywords modelimagemodelsalignmentcaptionsimagesoftencorpus
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-image diffusion models achieved a remarkable leap in capabilities over the last few years, enabling high-quality and diverse synthesis of images from a textual prompt. However, even the most advanced models often struggle to precisely follow all of the directions in their prompts. The vast majority of these models are trained on datasets consisting of (image, caption) pairs where the images often come from the web, and the captions are their HTML alternate text. A notable example is the LAION dataset, used by Stable Diffusion and other models. In this work we observe that these captions are often of low quality, and argue that this significantly affects the model's capability to understand nuanced semantics in the textual prompts. We show that by relabeling the corpus with a specialized automatic captioning model and training a text-to-image model on the recaptioned dataset, the model benefits substantially across the board. First, in overall image quality: e.g. FID 14.84 vs. the baseline of 17.87, and 64.3% improvement in faithful image generation according to human evaluation. Second, in semantic alignment, e.g. semantic object accuracy 84.34 vs. 78.90, counting alignment errors 1.32 vs. 1.44 and positional alignment 62.42 vs. 57.60. We analyze various ways to relabel the corpus and provide evidence that this technique, which we call RECAP, both reduces the train-inference discrepancy and provides the model with more information per example, increasing sample efficiency and allowing the model to better understand the relations between captions and images.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Determinism of Randomness: Prompt-Residual Seed Shaping for Diffusion Generation

    cs.CV 2025-11 unverdicted novelty 7.0 of 10

    A geometric view of semantic anisotropy in diffusion latents motivates a prompt-residual seed-shaping method that improves prompt alignment and visual quality without training.

  2. GAVEL: Grounded Caption Error Verification and Localization

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    GAVEL introduces a joint task, dataset, and benchmark for verifying, explaining, and localizing caption-image misalignments, with a supervised baseline that improves grounding and explanation metrics over strong close...

  3. Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    HRFD aligns multi-dimensional preferences in text-to-image diffusion via hierarchical relevance feedback and statistical distribution divergence measurement between liked and disliked image sets, remaining training-fr...

  4. ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning

    cs.CV 2025-07 conditional novelty 6.0 of 10

    ShortFT fine-tunes Stable Diffusion by backpropagating reward gradients through a distilled few-step shortcut denoising chain, improving alignment scores over DRaFT-LV and DRTune.

  5. On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling

    cs.CR 2025-06 conditional novelty 6.0 of 10

    An adversarial mislabeling attack on VLM captioners can inject dirty-label poison samples into text-to-image training data and corrupt a model's output for specific prompts with a small number of images.

  6. Agent AI: Surveying the Horizons of Multimodal Interaction

    cs.AI 2024-01 unverdicted novelty 4.0 of 10

    The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.

Pith tools