Related papers: Concept Activation Vectors for Generating User-Def…

Insights into the learned latent representations are imperative for verifying deep neural networks (DNNs) in critical computer vision (CV) tasks. Therefore, state-of-the-art supervised Concept-based eXplainable Artificial Intelligence…

In this paper, we address the challenging problem of 3D concept grounding (i.e. segmenting and learning visual concepts) by looking at RGBD images and reasoning about paired questions and answers. Existing visual reasoning approaches…

Unmanned aerial vehicles (UAVs) are frequently used for aerial mapping and general monitoring tasks. Recent progress in deep learning enabled automated semantic segmentation of imagery to facilitate the interpretation of large-scale complex…

The rapid adoption of transformer-based models in computational pathology has enabled prediction of molecular and clinical biomarkers from H&E whole-slide images, yet interpretability has not kept pace with model complexity. While…

Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This…

We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single instance to changes in shape across categories. In this work, we improve on a prior…

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…

Interpreting a large number of neurons in deep learning is difficult. Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof. It uses a decoder…

Sketch-based modeling strives to bring the ease and immediacy of drawing to the 3D world. However, while drawings are easy for humans to create, they are very challenging for computers to interpret due to their sparsity and ambiguity. We…

Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical properties of the complex domain (e.g., holomorphicity) make…

Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision…

Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent…

Computer-Aided Design (CAD) generative modeling is driving significant innovations across industrial applications. Recent works have shown remarkable progress in creating solid models from various inputs such as point clouds, meshes, and…

Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials…

Generative models rely on the key idea that data can be represented in terms of latent variables which are uncorrelated by definition. Lack of correlation is important because it suggests that the latent space manifold is simpler to…

The ability of deep learning methods to perform classification and regression tasks relies heavily on their capacity to uncover manifolds in high-dimensional data spaces and project them into low-dimensional representation spaces. In this…