Daily papers related to Image/Video/Multimodal Generation from cs.CV
May 06, 2025
Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene diversity and layout complexity. While large language models (LLMs) can leverage diverse text-domain knowledge, they struggle with spatial realism, often producing unnatural object placements that fail to respect common sense. Our key insight is that vision perception can bridge this gap by providing realistic spatial guidance that LLMs lack. To this end, we introduce Scenethesis, a training-free agentic framework that integrates LLM-based scene planning with vision-guided layout refinement. Given a text prompt, Scenethesis first employs an LLM to draft a coarse layout. A vision module then refines it by generating an image guidance and extracting scene structure to capture inter-object relations. Next, an optimization module iteratively enforces accurate pose alignment and physical plausibility, preventing artifacts like object penetration and instability. Finally, a judge module verifies spatial coherence. Comprehensive experiments show that Scenethesis generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.
TLDR: scenethesis is a training-free agentic framework that leverages llms and vision perception to generate realistic and physically plausible 3d scenes from text prompts, addressing limitations of existing methods.
TLDR: scenethesis是一个无需训练的agentic框架，它利用llm和视觉感知来从文本提示生成逼真且物理上合理的3d场景，解决了现有方法的局限性。
Read Paper (PDF)Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance generation quality of the diffusion transformers. However, existing approaches necessitate to either introduce an additional and complex representation training framework or rely on a large-scale, pre-trained representation foundation model to provide representation guidance during the original generative training process. In this study, we posit that the unique discriminative process inherent to diffusion transformers enables them to offer such guidance without requiring external representation components. We therefore propose Self-Representation A}lignment (SRA), a simple yet straightforward method that obtain representation guidance through a self-distillation manner. Specifically, SRA aligns the output latent representation of the diffusion transformer in earlier layer with higher noise to that in later layer with lower noise to progressively enhance the overall representation learning during only generative training process. Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements. Moreover, SRA not only significantly outperforms approaches relying on auxiliary, complex representation training frameworks but also achieves performance comparable to methods that heavily dependent on powerful external representation priors.
TLDR: this paper proposes self-representation alignment (sra), a method to improve diffusion transformer performance by using the model's inherent discriminative properties for representation guidance, avoiding the need for external representation components or pre-trained models.
TLDR: 该论文提出自表示对齐（sra）方法，通过利用扩散转换器固有的判别特性来进行表示引导，从而提高扩散转换器的性能，避免了对外部表示组件或预训练模型的需求。
Read Paper (PDF)Text-to-image (T2I) diffusion models have rapidly advanced, enabling high-quality image generation conditioned on textual prompts. However, the growing trend of fine-tuning pre-trained models for personalization raises serious concerns about unauthorized dataset usage. To combat this, dataset ownership verification (DOV) has emerged as a solution, embedding watermarks into the fine-tuning datasets using backdoor techniques. These watermarks remain inactive under benign samples but produce owner-specified outputs when triggered. Despite the promise of DOV for T2I diffusion models, its robustness against copyright evasion attacks (CEA) remains unexplored. In this paper, we explore how attackers can bypass these mechanisms through CEA, allowing models to circumvent watermarks even when trained on watermarked datasets. We propose the first copyright evasion attack (i.e., CEAT2I) specifically designed to undermine DOV in T2I diffusion models. Concretely, our CEAT2I comprises three stages: watermarked sample detection, trigger identification, and efficient watermark mitigation. A key insight driving our approach is that T2I models exhibit faster convergence on watermarked samples during the fine-tuning, evident through intermediate feature deviation. Leveraging this, CEAT2I can reliably detect the watermarked samples. Then, we iteratively ablate tokens from the prompts of detected watermarked samples and monitor shifts in intermediate features to pinpoint the exact trigger tokens. Finally, we adopt a closed-form concept erasure method to remove the injected watermark. Extensive experiments show that our CEAT2I effectively evades DOV mechanisms while preserving model performance.
TLDR: this paper introduces a novel copyright evasion attack (ceat2i) against dataset ownership verification (dov) mechanisms in personalized text-to-image diffusion models, demonstrating its effectiveness in bypassing watermarks.
TLDR: 本文提出了一种针对个性化文本到图像扩散模型中数据集所有权验证（dov）机制的新型版权规避攻击（ceat2i），并证明其在绕过水印方面的有效性。
Read Paper (PDF)Current multi-subject customization approaches encounter two critical challenges: the difficulty in acquiring diverse multi-subject training data, and attribute entanglement across different subjects. To bridge these gaps, we propose MUSAR - a simple yet effective framework to achieve robust multi-subject customization while requiring only single-subject training data. Firstly, to break the data limitation, we introduce debiased diptych learning. It constructs diptych training pairs from single-subject images to facilitate multi-subject learning, while actively correcting the distribution bias introduced by diptych construction via static attention routing and dual-branch LoRA. Secondly, to eliminate cross-subject entanglement, we introduce dynamic attention routing mechanism, which adaptively establishes bijective mappings between generated images and conditional subjects. This design not only achieves decoupling of multi-subject representations but also maintains scalable generalization performance with increasing reference subjects. Comprehensive experiments demonstrate that our MUSAR outperforms existing methods - even those trained on multi-subject dataset - in image quality, subject consistency, and interaction naturalness, despite requiring only single-subject dataset.
TLDR: the paper introduces musar, a framework for multi-subject image customization using only single-subject training data, addressing data scarcity and subject entanglement challenges through debiased diptych learning and dynamic attention routing; it claims superior performance over methods trained on multi-subject data.
TLDR: 该论文介绍了musar，一个仅使用单主体训练数据进行多主体图像定制的框架。它通过去偏二联画学习和动态注意力路由来解决数据稀缺和主体纠缠的挑战，并声称优于在多主体数据上训练的方法。
Read Paper (PDF)Diffusion models have shown excellent performance in text-to-image generation. Nevertheless, existing methods often suffer from performance bottlenecks when handling complex prompts that involve multiple objects, characteristics, and relations. Therefore, we propose a Multi-agent Collaboration-based Compositional Diffusion (MCCD) for text-to-image generation for complex scenes. Specifically, we design a multi-agent collaboration-based scene parsing module that generates an agent system comprising multiple agents with distinct tasks, utilizing MLLMs to extract various scene elements effectively. In addition, Hierarchical Compositional diffusion utilizes a Gaussian mask and filtering to refine bounding box regions and enhance objects through region enhancement, resulting in the accurate and high-fidelity generation of complex scenes. Comprehensive experiments demonstrate that our MCCD significantly improves the performance of the baseline models in a training-free manner, providing a substantial advantage in complex scene generation.
TLDR: mccd introduces a multi-agent collaboration and hierarchical compositional diffusion approach to improve text-to-image generation for complex prompts by effectively parsing scenes and enhancing object regions.
TLDR: mccd 提出了一种基于多智能体协作和分层组合扩散的方法，通过有效解析场景和强化对象区域，来改进复杂提示的文本到图像生成。
Read Paper (PDF)Recent years have seen remarkable progress in both multimodal understanding models and image generation models. Despite their respective successes, these two domains have evolved independently, leading to distinct architectural paradigms: While autoregressive-based architectures have dominated multimodal understanding, diffusion-based models have become the cornerstone of image generation. Recently, there has been growing interest in developing unified frameworks that integrate these tasks. The emergence of GPT-4o's new capabilities exemplifies this trend, highlighting the potential for unification. However, the architectural differences between the two domains pose significant challenges. To provide a clear overview of current efforts toward unification, we present a comprehensive survey aimed at guiding future research. First, we introduce the foundational concepts and recent advancements in multimodal understanding and text-to-image generation models. Next, we review existing unified models, categorizing them into three main architectural paradigms: diffusion-based, autoregressive-based, and hybrid approaches that fuse autoregressive and diffusion mechanisms. For each category, we analyze the structural designs and innovations introduced by related works. Additionally, we compile datasets and benchmarks tailored for unified models, offering resources for future exploration. Finally, we discuss the key challenges facing this nascent field, including tokenization strategy, cross-modal attention, and data. As this area is still in its early stages, we anticipate rapid advancements and will regularly update this survey. Our goal is to inspire further research and provide a valuable reference for the community. The references associated with this survey will be available on GitHub soon.
TLDR: this paper surveys the emerging field of unified multimodal understanding and generation models, categorizing existing approaches (diffusion, autoregressive, hybrid), highlighting key challenges, and providing resources for future research. it aims to guide research in this rapidly evolving area.
TLDR: 本文综述了统一多模态理解和生成模型的新兴领域，对现有方法（扩散模型、自回归模型、混合模型）进行分类，强调了关键挑战，并为未来研究提供了资源。旨在指导这一快速发展领域的研究。
Read Paper (PDF)Text-to-image generation (T2I) refers to the text-guided generation of high-quality images. In the past few years, T2I has attracted widespread attention and numerous works have emerged. In this survey, we comprehensively review 141 works conducted from 2021 to 2024. First, we introduce four foundation model architectures of T2I (autoregression, non-autoregression, GAN and diffusion) and the commonly used key technologies (autoencoder, attention and classifier-free guidance). Secondly, we systematically compare the methods of these studies in two directions, T2I generation and T2I editing, including the encoders and the key technologies they use. In addition, we also compare the performance of these researches side by side in terms of datasets, evaluation metrics, training resources, and inference speed. In addition to the four foundation models, we survey other works on T2I, such as energy-based models and recent Mamba and multimodality. We also investigate the potential social impact of T2I and provide some solutions. Finally, we propose unique insights of improving the performance of T2I models and possible future development directions. In summary, this survey is the first systematic and comprehensive overview of T2I, aiming to provide a valuable guide for future researchers and stimulate continued progress in this field.
TLDR: this survey paper comprehensively reviews text-to-image generation (t2i) methods from 2021-2024, covering architectures, key technologies, performance comparisons, and potential social impact, also providing insights and future directions.
TLDR: 这篇综述全面回顾了2021-2024年的文本到图像生成(t2i)方法，涵盖架构、关键技术、性能比较和社会影响，并提供了见解和未来方向。
Read Paper (PDF)We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source implementation of the integrated MetaQueries and M2-omni framework, while introducing the novel multi-scale learnable tokens and multi-scale representation alignment strategy. By leveraging a fixed MLLM and a learnable diffusion model, Ming-Lite-Uni enables native multimodal AR models to perform both text-to-image generation and instruction based image editing tasks, expanding their capabilities beyond pure visual understanding. Our experimental results demonstrate the strong performance of Ming-Lite-Uni and illustrate the impressive fluid nature of its interactive process. All code and model weights are open-sourced to foster further exploration within the community. Notably, this work aligns with concurrent multimodal AI milestones - such as ChatGPT-4o with native image generation updated in March 25, 2025 - underscoring the broader significance of unified models like Ming-Lite-Uni on the path toward AGI. Ming-Lite-Uni is in alpha stage and will soon be further refined.
TLDR: ming-lite-uni is a new open-source multimodal framework featuring a unified visual generator and a native multimodal autoregressive model for vision and language tasks, enabling text-to-image generation and instruction-based image editing.
TLDR: ming-lite-uni 是一个新的开源多模态框架，具有统一的视觉生成器和原生多模态自回归模型，用于视觉和语言任务，支持文本到图像的生成和基于指令的图像编辑。
Read Paper (PDF)Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and original-edited image pairs. Recent efforts attempt to improve editing models through generating higher-quality edited images, pre-training on recognition tasks, or introducing vision-language models (VLMs) but fail to resolve this fundamental issue. In this paper, we offer a novel solution by constructing more effective editing instructions for given image pairs. This includes rectifying the editing instructions to better align with the original-edited image pairs and using contrastive editing instructions to further enhance their effectiveness. Specifically, we find that editing models exhibit specific generation attributes at different inference steps, independent of the text. Based on these prior attributes, we define a unified guide for VLMs to rectify editing instructions. However, there are some challenging editing scenarios that cannot be resolved solely with rectified instructions. To this end, we further construct contrastive supervision signals with positive and negative instructions and introduce them into the model training using triplet loss, thereby further facilitating supervision effectiveness. Our method does not require the VLM modules or pre-training tasks used in previous work, offering a more direct and efficient way to provide better supervision signals, and providing a novel, simple, and effective solution for instruction-based image editing. Results on multiple benchmarks demonstrate that our method significantly outperforms existing approaches. Compared with previous SOTA SmartEdit, we achieve 9.19% improvements on the Real-Edit benchmark with 30x less training data and 13x smaller model size.
TLDR: the paper introduces superedit, a method for improving instruction-based image editing by rectifying editing instructions using vlm guidance based on observed generation attributes and incorporating contrastive supervision with triplet loss, achieving superior performance with less data and smaller model size compared to sota methods.
TLDR: 该论文介绍了superedit，一种通过修正编辑指令来改进基于指令的图像编辑的方法。该方法利用视觉语言模型（vlm）的指导，根据观察到的生成属性来修正编辑指令，并结合三元组损失进行对比监督。相比于现有最佳方法，superedit在更少的数据和更小的模型尺寸下实现了更卓越的性能。
Read Paper (PDF)This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are consistent and, therefore, learnable within a specialized domain, like portrait generation. We generate a synthetic paired dataset and train a fast image-to-image translation head. Using two sets of low- and high-quality synthetic images, our model is trained to refine the output of a distilled generator (e.g., FLUX.1-schnell) to a level comparable to a baseline model like FLUX.1-dev, which is more computationally intensive. Our results show that the pipeline, which combines a distilled version of a large generative model with our enhancement layer, delivers similar photorealistic portraits to the baseline version with up to an 82% decrease in computational cost compared to FLUX.1-dev. This study demonstrates the potential for improving the efficiency of AI solutions involving large-scale image generation.
TLDR: this paper introduces a cost-effective method to improve the quality of images generated by distilled diffusion models by training an image-to-image translation head on a synthetic dataset, achieving comparable quality to baseline models with significantly reduced computational cost.
TLDR: 本文提出了一种经济高效的方法，通过在合成数据集上训练图像到图像的翻译头，来提高蒸馏扩散模型生成的图像质量，从而以显著降低的计算成本实现与基线模型相当的质量。
Read Paper (PDF)Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and resource-limited environments. Previous research has endeavored to address these limitations in a decoupled manner, utilizing either advanced samplers or efficient model quantization techniques. In this study, we uncover that quantization-induced noise disrupts directional estimation at each sampling step, further distorting the precise directional estimations of higher-order samplers when solving the sampling equations through discretized numerical methods, thereby altering the optimal sampling trajectory. To attain dual acceleration with high fidelity, we propose a sampling-aware quantization strategy, wherein a Mixed-Order Trajectory Alignment technique is devised to impose a more stringent constraint on the error bounds at each sampling step, facilitating a more linear probability flow. Extensive experiments on sparse-step fast sampling across multiple datasets demonstrate that our approach preserves the rapid convergence characteristics of high-speed samplers while maintaining superior generation quality. Code will be made publicly available soon.
TLDR: this paper proposes a sampling-aware quantization strategy, specifically mixed-order trajectory alignment, for diffusion models to improve both speed and generation quality in resource-constrained environments by mitigating quantization-induced noise during sampling.
TLDR: 本文提出了一种采样感知量化策略，即混合阶轨迹对齐，用于扩散模型，通过减轻采样过程中量化引起的噪声，从而在资源受限的环境中提高速度和生成质量。
Read Paper (PDF)Current text-to-image generative models struggle to accurately represent object states (e.g., "a table without a bottle," "an empty tumbler"). In this work, we first design a fully-automatic pipeline to generate high-quality synthetic data that accurately captures objects in varied states. Next, we fine-tune several open-source text-to-image models on this synthetic data. We evaluate the performance of the fine-tuned models by quantifying the alignment of the generated images to their prompts using GPT4o-mini, and achieve an average absolute improvement of 8+% across four models on the public GenAI-Bench dataset. We also curate a collection of 200 prompts with a specific focus on common objects in various physical states. We demonstrate a significant improvement of an average of 24+% over the baseline on this dataset. We release all evaluation prompts and code.
TLDR: the paper addresses the problem of text-to-image models struggling to represent object states by generating synthetic data and fine-tuning existing models, resulting in significant improvements in image-prompt alignment.
TLDR: 该论文通过生成合成数据并微调现有模型，解决了文本到图像模型难以表示对象状态的问题，从而显著提高了图像与提示的对齐程度。
Read Paper (PDF)Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there has been limited exploration into the effectiveness of long-term reasoning capabilities for reward modeling and how to activate these capabilities in MRMs. In this paper, we explore how Reinforcement Learning (RL) can be used to improve reward modeling. Specifically, we reformulate the reward modeling problem as a rule-based RL task. However, we observe that directly applying existing RL algorithms, such as Reinforce++, to reward modeling often leads to training instability or even collapse due to the inherent limitations of these algorithms. To address this issue, we propose the StableReinforce algorithm, which refines the training loss, advantage estimation strategy, and reward design of existing RL methods. These refinements result in more stable training dynamics and superior performance. To facilitate MRM training, we collect 200K preference data from diverse datasets. Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks. Compared to previous SOTA models, R1-Reward achieves a $8.4\%$ improvement on the VL Reward-Bench and a $14.3\%$ improvement on the Multimodal Reward Bench. Moreover, with more inference compute, R1-Reward's performance is further enhanced, highlighting the potential of RL algorithms in optimizing MRMs.
TLDR: the paper introduces r1-reward, a multimodal reward model trained using a novel stablereinforce algorithm, demonstrating significant performance improvements on multimodal reward modeling benchmarks.
TLDR: 该论文介绍了r1-reward，一个使用新型stablereinforce算法训练的多模态奖励模型，并在多模态奖励建模基准上展示了显著的性能提升。
Read Paper (PDF)Automatic segmentation of anatomical landmarks in endoscopic images can provide assistance to doctors and surgeons for diagnosis, treatments or medical training. However, obtaining the annotations required to train commonly used supervised learning methods is a tedious and difficult task, in particular for real images. While ground truth annotations are easier to obtain for synthetic data, models trained on such data often do not generalize well to real data. Generative approaches can add realistic texture to it, but face difficulties to maintain the structure of the original scene. The main contribution in this work is a novel image translation model that adds realistic texture to simulated endoscopic images while keeping the key scene layout information. Our approach produces realistic images in different endoscopy scenarios. We demonstrate these images can effectively be used to successfully train a model for a challenging end task without any real labeled data. In particular, we demonstrate our approach for the task of fold segmentation in colonoscopy images. Folds are key anatomical landmarks that can occlude parts of the colon mucosa and possible polyps. Our approach generates realistic images maintaining the shape and location of the original folds, after the image-style-translation, better than existing methods. We run experiments both on a novel simulated dataset for fold segmentation, and real data from the EndoMapper (EM) dataset. All our new generated data and new EM metadata is being released to facilitate further research, as no public benchmark is currently available for the task of fold segmentation.
TLDR: this paper presents a novel image translation model for sim2real endoscopy segmentation, adding realistic texture to simulated images while preserving structural information, which allows training a segmentation model without real labeled data. the authors also release a new simulated dataset as well as new metadata for the endomapper dataset.
TLDR: 本文提出了一种新的图像转换模型，用于内窥镜分割中的sim2real，在为模拟图像添加真实纹理的同时保留结构信息，从而无需真实标记数据即可训练分割模型。作者还发布了一个新的模拟数据集以及endomapper数据集的新元数据。
Read Paper (PDF)Recent advances in visual industrial anomaly detection have demonstrated exceptional performance in identifying and segmenting anomalous regions while maintaining fast inference speeds. However, anomaly classification-distinguishing different types of anomalies-remains largely unexplored despite its critical importance in real-world inspection tasks. To address this gap, we propose VELM, a novel LLM-based pipeline for anomaly classification. Given the critical importance of inference speed, we first apply an unsupervised anomaly detection method as a vision expert to assess the normality of an observation. If an anomaly is detected, the LLM then classifies its type. A key challenge in developing and evaluating anomaly classification models is the lack of precise annotations of anomaly classes in existing datasets. To address this limitation, we introduce MVTec-AC and VisA-AC, refined versions of the widely used MVTec-AD and VisA datasets, which include accurate anomaly class labels for rigorous evaluation. Our approach achieves a state-of-the-art anomaly classification accuracy of 80.4% on MVTec-AD, exceeding the prior baselines by 5%, and 84% on MVTec-AC, demonstrating the effectiveness of VELM in understanding and categorizing anomalies. We hope our methodology and benchmark inspire further research in anomaly classification, helping bridge the gap between detection and comprehensive anomaly characterization.
TLDR: the paper introduces velm, a multi-modal llm-based pipeline for anomaly classification in industrial settings, and provides two new datasets, mvtec-ac and visa-ac, with accurate anomaly class labels for evaluation.
TLDR: 本文介绍了一种基于多模态llm的异常分类管道velm，用于工业环境中的异常分类，并提供了两个新的数据集mvtec-ac和visa-ac，其中包含准确的异常类别标签，用于评估。
Read Paper (PDF)Chest X-rays (CXRs) are the most frequently performed imaging examinations in clinical settings. Recent advancements in Large Multimodal Models (LMMs) have enabled automated CXR interpretation, enhancing diagnostic accuracy and efficiency. However, despite their strong visual understanding, current Medical LMMs (MLMMs) still face two major challenges: (1) Insufficient region-level understanding and interaction, and (2) Limited accuracy and interpretability due to single-step reasoning. In this paper, we empower MLMMs with anatomy-centric reasoning capabilities to enhance their interactivity and explainability. Specifically, we first propose an Anatomical Ontology-Guided Reasoning (AOR) framework, which centers on cross-modal region-level information to facilitate multi-step reasoning. Next, under the guidance of expert physicians, we develop AOR-Instruction, a large instruction dataset for MLMMs training. Our experiments demonstrate AOR's superior performance in both VQA and report generation tasks.
TLDR: the paper introduces an anatomical ontology-guided reasoning (aor) framework to improve medical large multimodal models' (mlmms) performance in chest x-ray interpretation by enhancing region-level understanding and multi-step reasoning.
TLDR: 该论文介绍了一种解剖本体引导推理 (aor) 框架，通过增强区域级理解和多步推理，来提高医学大型多模态模型 (mlmm) 在胸部 x 光片解释方面的性能。
Read Paper (PDF)Heterogeneous morphological features and data imbalance pose significant challenges in rare thyroid carcinoma classification using ultrasound imaging. To address this issue, we propose a novel multitask learning framework, Channel-Spatial Attention Synergy Network (CSASN), which integrates a dual-branch feature extractor - combining EfficientNet for local spatial encoding and ViT for global semantic modeling, with a cascaded channel-spatial attention refinement module. A residual multiscale classifier and dynamically weighted loss function further enhance classification stability and accuracy. Trained on a multicenter dataset comprising more than 2000 patients from four clinical institutions, our framework leverages a residual multiscale classifier and dynamically weighted loss function to enhance classification stability and accuracy. Extensive ablation studies demonstrate that each module contributes significantly to model performance, particularly in recognizing rare subtypes such as FTC and MTC carcinomas. Experimental results show that CSASN outperforms existing single-stream CNN or Transformer-based models, achieving a superior balance between precision and recall under class-imbalanced conditions. This framework provides a promising strategy for AI-assisted thyroid cancer diagnosis.
TLDR: the paper introduces csasn, a multitask attention-based framework for classifying heterogeneous thyroid carcinoma in ultrasound images, using a dual-branch feature extractor and a cascaded channel-spatial attention refinement module to address data imbalance and improve classification accuracy.
TLDR: 该论文介绍了一种名为csasn的多任务注意力框架，用于对超声图像中异构性甲状腺癌进行分类。该框架采用双分支特征提取器和级联通道空间注意力细化模块，旨在解决数据不平衡问题并提高分类准确性。
Read Paper (PDF)