相关论文: Explaining image classifiers by removing input fea…

Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled new approaches to data…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has…

We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are…

Generative diffusion models have advanced image editing with high-quality results and intuitive interfaces such as prompts and semantic drawing. However, these interfaces lack precise control, and the associated methods typically specialize…

This paper improves upon existing data pruning methods for image classification by introducing a novel pruning metric and pruning procedure based on importance sampling. The proposed pruning metric explicitly accounts for data separability,…

Evaluation of generative models has been an underrepresented field despite the surge of generative architectures. Most recent models are evaluated upon rather obsolete metrics which suffer from robustness issues, while being unable to…

We address in this work the question of identifying the failure conditions of a given image classifier. To do so, we exploit the capacity of producing controllable distributions of high quality image data made available by recent Generative…

Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images. However, they still have difficulties to generate the…

Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologists to visualize deformities in medical imaging. Most of the…

Image inpainting methods have shown significant improvements by using deep neural networks recently. However, many of these techniques often create distorted structures or blurry textures inconsistent with surrounding areas. The problem is…

Image editing has advanced significantly with the introduction of text-conditioned diffusion models. Despite this progress, seamlessly adding objects to images based on textual instructions without requiring user-provided input masks…

We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and…

Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models. These methods perturb parts of the input to measure how those parts affect the output. Since the methods only require the input and…

In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are…

We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels…

Image recognition/classification is a widely studied problem, but its reverse problem, image generation, has drawn much less attention until recently. But the vast majority of current methods for image generation require training/retraining…

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in…

Many real-world datasets can be divided into groups according to certain salient features (e.g. grouping images by subject, grouping text by font, etc.). Often, machine learning tasks require that these features be represented separately…

Detecting manipulated images has become a significant emerging challenge. The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being…