Related papers: MULTI: Disentangling Camera Lens, Sensor, View, an…
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks. Despite its popularity, the inherent disparities in how different sources depict scene…
Counterfactual medical image generation effectively addresses data scarcity and enhances the interpretability of medical images. However, due to the complex and diverse pathological features of medical images and the imbalanced class…
Recent work has demonstrated the ability to leverage or distill pre-trained 2D features obtained using large pre-trained 2D models into 3D features, enabling impressive 3D editing and understanding capabilities using only 2D supervision.…
Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a…
Current semantic segmentation models typically require a substantial amount of manually annotated data, a process that is both time-consuming and resource-intensive. Alternatively, leveraging advanced text-to-image models such as Midjourney…
Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the…
Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e.g., they may change between domains,…
We present Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed…
Domain Adaptation (DA) is a highly relevant research topic when it comes to image classification with deep neural networks. Combining multiple source domains in a sophisticated way to optimize a classification model can improve the…
Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these…
Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and…
Existing multi-modal image fusion methods fail to address the compound degradations presented in source images, resulting in fusion images plagued by noise, color bias, improper exposure, \textit{etc}. Additionally, these methods often…
In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting…
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…
To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models…
Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and…
Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors…
Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…
Text-to-image (TTI) diffusion models have demonstrated impressive results in generating high-resolution images of complex and imaginative scenes. Recent approaches have further extended these methods with personalization techniques that…
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of…