Related papers: LucidPPN: Unambiguous Prototypical Parts Network f…

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However,…

Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems. However, past work has usually relied on black box deep neural networks, whose reasoning…

Neural network architectures are most often conceptually designed and described in visual terms, but are implemented by writing error-prone code. PrototypeML is a machine learning development environment that bridges the dichotomy between…

Image anomaly detection and localization perform not only image-level anomaly classification but also locate pixel-level anomaly regions. Recently, it has received much research attention due to its wide application in various fields. This…

Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological…

In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning. Over recent years, a plethora of methods have emerged,…

Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff, and part predictions individually without performing any…

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world…

Deep learning-based multi-view coarse-grained 3D shape classification has achieved remarkable success over the past decade, leveraging the powerful feature learning capabilities of CNN-based and ViT-based backbones. However, as a…

Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures largely remain a black box. With a critical question -- how can the diffusion…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…

Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning-yet, large multimodal models (LMMs) struggle to perform this seemingly straightforward…

Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern…

In this paper, we present PARTICUL, a novel algorithm for unsupervised learning of part detectors from datasets used in fine-grained recognition. It exploits the macro-similarities of all images in the training set in order to mine for…

Interpretable deep learning models have received widespread attention in the field of image recognition. Due to the unique multi-instance learning of medical images and the difficulty in identifying decision-making regions, many…

Nucleus segmentation is a challenging task due to the crowded distribution and blurry boundaries of nuclei. Recent approaches represent nuclei by means of polygons to differentiate between touching and overlapping nuclei and have…

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large…

Prototype learning, a popular machine learning method designed for inherently interpretable decisions, leverages similarities to learned prototypes for classifying new data. While it is mainly applied in computer vision, in this work, we…

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to…