CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation

• URL: http://arxiv.org/abs/2508.10710v1
• Date: Thu, 14 Aug 2025 14:53:53 GMT
• Title: CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation
• Authors: Joohyeon Lee, Jin-Seop Lee, Jee-Hyong Lee,
• Abstract summary: Diffusion-based text-to-image generation models have demonstrated strong performance in terms of image quality and diversity.<n>They still struggle to generate images that accurately reflect the number of objects specified in the input prompt.<n>We propose textitCountCluster, a method that guides the object cross-attention map to be clustered according to the specified object count in the input.
• Score: 8.295319152986316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based text-to-image generation models have demonstrated strong performance in terms of image quality and diversity. However, they still struggle to generate images that accurately reflect the number of objects specified in the input prompt. Several approaches have been proposed that rely on either external counting modules for iterative refinement or quantity representations derived from learned tokens or latent features. However, they still have limitations in accurately reflecting the specified number of objects and overlook an important structural characteristic--The number of object instances in the generated image is largely determined in the early timesteps of the denoising process. To correctly reflect the object quantity for image generation, the highly activated regions in the object cross-attention map at the early timesteps should match the input object quantity, while each region should be clearly separated. To address this issue, we propose \textit{CountCluster}, a method that guides the object cross-attention map to be clustered according to the specified object count in the input, without relying on any external tools or additional training. The proposed method partitions the object cross-attention map into $k$ clusters at inference time based on attention scores, defines an ideal distribution in which each cluster is spatially well-separated, and optimizes the latent to align with this target distribution. Our method achieves an average improvement of 18.5\%p in object count accuracy compared to existing methods, and demonstrates superior quantity control performance across a variety of prompts. Code will be released at: https://github.com/JoohyeonL22/CountCluster .

Related papers

• Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models [54.641726517633025]
  We propose a new framework that uses pre-trained object counting techniques and object detectors to guide generation.<n>First, we optimize a counting token using an outer-loop loss computed on fully generated images.<n>Second, we introduce a detection-driven scaling term that corrects errors caused by viewpoint and proportion shifts.
  arXiv  Detail & Related papers  (2024-08-21T15:51:46Z)
• Make It Count: Text-to-Image Generation with an Accurate Number of Objects [31.909039527164403]
  Control of the number of objects depicted using text is surprisingly hard. Generating object-correct counts is challenging because the generative model needs to keep a sense of separate identity for every instance of the object. We show how CountGen can be used to guide denoising with correct object count.
  arXiv  Detail & Related papers  (2024-06-14T17:46:08Z)
• Counting Guidance for High Fidelity Text-to-Image Synthesis [16.76098645308941]
  Text-to-image diffusion models sometimes struggle to create high-fidelity content for the given input prompt.<n>We present a method to improve diffusion models so that they accurately produce the correct object count based on the input prompt.
  arXiv  Detail & Related papers  (2023-06-30T11:40:35Z)
• CLIP-Count: Towards Text-Guided Zero-Shot Object Counting [32.07271723717184]
  We propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Our method effectively generates high-quality density maps for objects-of-interest.
  arXiv  Detail & Related papers  (2023-05-12T08:19:39Z)
• Single Image Object Counting and Localizing using Active-Learning [4.56877715768796]
  We present a new method for counting and localizing repeating objects in single-image scenarios. Our method trains a CNN over a small set of labels carefully collected from the input image in few active-learning iterations. Compared with existing user-assisted counting methods, our active-learning iterations achieve state-of-the-art performance in terms of counting and localizing accuracy, number of user mouse clicks, and running-time.
  arXiv  Detail & Related papers  (2021-11-16T11:29:21Z)
• A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection [56.82077636126353]
  We take advantage of object-centric images to improve object detection in scene-centric images. We present a simple yet surprisingly effective framework to do so. Our approach can improve the object detection (and instance segmentation) accuracy of rare objects by 50% (and 33%) relatively.
  arXiv  Detail & Related papers  (2021-02-17T17:27:21Z)
• Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting [18.733301622920102]
  Multi-class object counting expands the scope of application of object counting task. The multi-target detection task can achieve multi-class object counting in some scenarios. We propose a simple yet efficient counting network based on point-level annotations.
  arXiv  Detail & Related papers  (2020-12-15T08:38:28Z)
• Weakly-Supervised Semantic Segmentation via Sub-category Exploration [73.03956876752868]
  We propose a simple yet effective approach to enforce the network to pay attention to other parts of an object. Specifically, we perform clustering on image features to generate pseudo sub-categories labels within each annotated parent class. We conduct extensive analysis to validate the proposed method and show that our approach performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-08-03T20:48:31Z)
• Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks [55.11806035788036]
  It is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
  arXiv  Detail & Related papers  (2020-07-31T06:11:06Z)
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision [89.57847958016981]
  Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires textitexplicitly modeling the object textitbody and textitedge, which correspond to the high and low frequency of the image. We show that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries.
  arXiv  Detail & Related papers  (2020-07-20T12:11:22Z)
• A Few-Shot Sequential Approach for Object Counting [63.82757025821265]
  We introduce a class attention mechanism that sequentially attends to objects in the image and extracts their relevant features. The proposed technique is trained on point-level annotations and uses a novel loss function that disentangles class-dependent and class-agnostic aspects of the model. We present our results on a variety of object-counting/detection datasets, including FSOD and MS COCO.
  arXiv  Detail & Related papers  (2020-07-03T18:23:39Z)
• Rethinking Object Detection in Retail Stores [55.359582952686175]
  We propose a new task, simultaneously object localization and counting, abbreviated as Locount. Locount requires algorithms to localize groups of objects of interest with the number of instances. We collect a large-scale object localization and counting dataset with rich annotations in retail stores.
  arXiv  Detail & Related papers  (2020-03-18T14:01:54Z)

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.