Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation

• URL: http://arxiv.org/abs/2607.14962v1
• Date: Thu, 16 Jul 2026 13:14:21 GMT
• Title: Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
• Abstract summary: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes.<n>We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage.<n>We then propose multi-axis max@K, a group-based reinforcement learning objective for improving such coverage in T2I models.
• Score: 29.478072341221722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage. We then propose multi-axis max@K, a group-based reinforcement learning objective for improving such coverage in diffusion-based T2I models. Given a group of samples and one score per target category, multi-axis max@K first takes the maximum score across samples for each category and then sums these category-wise maxima. The resulting credit assignment gives a sample positive weight on a category only when it increases that category's group-wise maximum, allowing different samples to contribute to different categories. We first validate the credit-assignment mechanism on a synthetic mixture and on SD3.5-M using deterministic pixel-based color rewards. We then evaluate the same objective on perceived-appearance fairness. Across three automatic evaluators on held-out prompts, multi-axis max@K improves the Fairness Score by 0.23-0.36 relative to the base model, while maintaining image quality and text alignment.

Related papers

• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• Center-guided Classifier for Semantic Segmentation of Remote Sensing Images [2.803715177543843]
  CenterSeg is a novel classifier for semantic segmentation of remote sensing images.<n>It solves problems with multiple prototypes, direct supervision under Grassmann manifold, and interpretability strategy.<n>Besides the superior performance, CenterSeg has the advantages of simplicity, lightweight, compatibility, and interpretability.
  arXiv  Detail & Related papers  (2025-03-21T09:21:37Z)
• Bridging the Gap: Aligning Text-to-Image Diffusion Models with Specific Feedback [5.415802995586328]
  Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models.<n>We propose an efficient fine-turning method with specific reward objectives, including three stages.<n> Experimental results on this benchmark show that our model outperforms other SOTA methods in both alignment and fidelity.
  arXiv  Detail & Related papers  (2024-11-28T09:56:28Z)
• A consensus-constrained parsimonious Gaussian mixture model for clustering hyperspectral images [0.0]
  Food engineers use hyperspectral images to classify the type and quality of a food sample.<n>In order to train these methods, every pixel in each training image needs to be labelled.<n>A consensus-constrained parsimonious Gaussian mixture model (ccPGMM) is proposed to label pixels in hyperspectral images.
  arXiv  Detail & Related papers  (2024-03-05T22:23:43Z)
• Adversarial AutoMixup [50.1874436169571]
  We propose AdAutomixup, an adversarial automatic mixup augmentation approach. It generates challenging samples to train a robust classifier for image classification. Our approach outperforms the state of the art in various classification scenarios.
  arXiv  Detail & Related papers  (2023-12-19T08:55:00Z)
• Diversified in-domain synthesis with efficient fine-tuning for few-shot classification [64.86872227580866]
  Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. We propose DISEF, a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification.
  arXiv  Detail & Related papers  (2023-12-05T17:18:09Z)
• Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching [63.88319217738223]
  We present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher demonstrates impressive generalization performance across various segmentation tasks, all without training. Our results further showcase the open-world generality and flexibility of Matcher when applied to images in the wild.
  arXiv  Detail & Related papers  (2023-05-22T17:59:43Z)
• High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation [17.804090651425955]
  Image-level weakly-supervised segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss. We reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method.
  arXiv  Detail & Related papers  (2023-04-05T17:43:57Z)
• Generating Representative Samples for Few-Shot Classification [8.62483598990205]
  Few-shot learning aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. We generate visual samples based on semantic embeddings using a conditional variational autoencoder model.
  arXiv  Detail & Related papers  (2022-05-05T20:58:33Z)
• Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search [90.30623718137244]
  We propose a novel deep hashing method for scalable multi-label image search. A new rank-consistency objective is applied to align the similarity orders from two spaces. A powerful loss function is designed to penalize the samples whose semantic similarity and hamming distance are mismatched.
  arXiv  Detail & Related papers  (2021-02-02T13:46:58Z)
• Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning [116.91819311885166]
  We propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to textbfCross-samples and Multi-level representation. Our method, termed as CsMl, has the ability to integrate multi-level visual representations across samples in a robust way.
  arXiv  Detail & Related papers  (2020-12-04T17:26:24Z)
• ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering [59.77141155608009]
  We propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model. ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our framework in different scenarios, thereby improving its generalization ability; 2) it automatically learns a proper weight for each view, thereby reducing the influence of noises; and 3) it aligns the same instances in different views, thereby decreasing the impact of missing instances.
  arXiv  Detail & Related papers  (2020-11-20T10:37:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.