相关论文: FreeBlend: Advancing Concept Blending with Staged …

Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However, existing CBMs and their variants have two crucial…

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…

This paper provides an efficient training-free painterly image harmonization (PIH) method, dubbed FreePIH, that leverages only a pre-trained diffusion model to achieve state-of-the-art harmonization results. Unlike existing methods that…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…

This paper provides an in-depth examination of the concept of semantic diffusion as a complementary instrument to large language models (LLMs) for design applications. Conventional LLMs and diffusion models fail to induce a convergent,…

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

There is growing interest in concept-based models (CBMs) that combine high-performance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A key requirement is that the concepts be interpretable.…

Modern text-to-image (T2I) models amplify harmful societal biases, challenging their ethical deployment. We introduce an inference-time method that reliably mitigates social bias while keeping prompt semantics and visual context…

We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable typography and place an occluding object over the intended text region. This setting…

Style transfer is an inventive process designed to create an image that maintains the essence of the original while embracing the visual style of another. Although diffusion models have demonstrated impressive generative power in…

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

In visual generation tasks, the responses and combinations of complex concepts often lack stability and are error-prone, which remains an under-explored area. In this paper, we attempt to explore the causal factors for poor concept…

Deep learning-based medical image classification techniques are rapidly advancing in medical image analysis, making it crucial to develop accurate and trustworthy models that can be efficiently deployed across diverse clinical scenarios.…

There is an increasing interest in using image-generating diffusion models for deep data augmentation and image morphing. In this context, it is useful to interpolate between latents produced by inverting a set of input images, in order to…

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the…

In the field of computer vision, visible light images often exhibit low contrast in low-light conditions, presenting a significant challenge. While infrared imagery provides a potential solution, its utilization entails high costs and…

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…