Related papers: Diffusion Visual Counterfactual Explanations
Diffusion Transformer has demonstrated powerful capability and scalability in generating high-quality images and videos. Further pursuing the unification of generation and editing tasks has yielded significant progress in the domain of…
Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities…
Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the challenge of…
State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image…
Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging. Traditionally, creating a deep learning model for sketch-to-image synthesis needs to overcome the distorted input…
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first…
The concept of counterfactual explanations (CE) has emerged as one of the important concepts to understand the inner workings of complex AI systems. In this paper, we translate the idea of CEs to linear optimization and propose, motivate,…
Medical video diagnosis involves inferring clinical decisions from dynamic tissue responses throughout examination processes. Existing methods rely on an end-to-end learning paradigm that i) focuses on appearance rather than pathology, ii)…
Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For…
We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual…
Nowadays, there are many diffusion and autoregressive models that show impressive results for generating images from text and other input domains. However, these methods are not intended for ultra-high-resolution image synthesis. Vector…
In vision classification, generating inputs that elicit confident predictions is key to understanding model behavior and reliability, especially under adversarial or out-of-distribution (OOD) conditions. While traditional adversarial…
Recovering the spatial layout of the cameras and the geometry of the scene from extreme-view images is a longstanding challenge in computer vision. Prevailing 3D reconstruction algorithms often adopt the image matching paradigm and presume…
The latest developments in Artificial Intelligence include diffusion generative models, quite popular tools which can produce original images both unconditionally and, in some cases, conditioned by some inputs provided by the user. Apart…
Diffusion models have revolutionized generative modeling, enabling unprecedented realism in image and video synthesis. This success has sparked interest in leveraging their representations for visual understanding tasks. While recent works…
Replicating In-Context Learning (ICL) in computer vision remains challenging due to task heterogeneity. We propose \textbf{VIRAL}, a framework that elicits visual reasoning from a pre-trained image editing model by formulating ICL as…
Enabling generative models to decompose visual concepts from a single image is a complex and challenging problem. In this paper, we study a new and challenging task, customized concept decomposition, wherein the objective is to leverage…
Despite the growing interest in diffusion models, gaining a deep understanding of the model class remains an elusive endeavour, particularly for the uninitiated in non-equilibrium statistical physics. Thanks to the rapid rate of progress in…
Learning dense correspondences, critical for application such as video label propagation, is hindered by tedious and unscalable manual annotation. Self-supervised methods address this by using a cross-view pretext task, often modeled with a…
Diffusion models are a class of generative models that generate high-quality samples, but at present it is difficult to characterize how they depend upon their training data. This difficulty raises scientific and regulatory questions, and…