Related papers: Extremal Contours: Gradient-driven contours for co…
Image classifiers are known to be difficult to interpret and therefore require explanation methods to understand their decisions. We present ShearletX, a novel mask explanation method for image classifiers based on the shearlet transform --…
Humans can easily perceive illusory contours and complete missing forms in fragmented shapes. This work investigates whether such capability can arise in convolutional neural networks (CNNs) using deep structural priors computed directly…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…
Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…
Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…
Deep convolutional neural networks (CNN) proved to be highly accurate to perform anatomical segmentation of medical images. However, some of the most popular CNN architectures for image segmentation still rely on post-processing strategies…
ControlNet excels at creating content that closely matches precise contours in user-provided masks. However, when these masks contain noise, as a frequent occurrence with non-expert users, the output would include unwanted artifacts. This…
We develop a new optimisation technique that combines multiresolution subdivision surfaces for boundary description with immersed finite elements for the discretisation of the primal and adjoint problems of optimisation. Similar to wavelets…
Curve evolution schemes for image segmentation based on a region based contour model allowing for junctions, vector-valued images and topology changes are introduced. Together with an a posteriori denoising in the segmented homogeneous…
Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaining labeled datasets is expensive. While previous works in…
Scientists, engineers, biologists, and technology specialists universally leverage image segmentation to extract shape ensembles containing many thousands of curves representing patterns in observations and measurements. These large curve…
Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a $28\times 28$ binary grid. Generally, a low-resolution grid is not sufficient to capture the…
We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold…
Unsupervised instance segmentation aims to segment distinct object instances in an image without relying on human-labeled data. This field has recently seen significant advancements, partly due to the strong local correspondences afforded…
Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold. In this paper, we propose a novel method to detect image contours from the extracted…
Computing the gradients of a rendering process is paramount for diverse applications in computer vision and graphics. However, accurate computation of these gradients is challenging due to discontinuities and rendering approximations,…
Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts directly at a single granularity level. However, this approach…
Image inpainting aims to fill in the missing pixels with visually coherent and semantically plausible content. Despite the great progress brought from deep generative models, this task still suffers from i. the difficulties in large-scale…
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…
Interpreting Convolutional Neural Networks (CNNs) is critical for safety-sensitive applications such as healthcare and autonomous systems. Popular visual explanation methods like Grad-CAM use a single convolutional layer, potentially…