Related papers: Composing Neural Learning and Symbolic Reasoning w…

Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as…

Existing end-to-end autonomous driving models rely heavily on purely data-driven inductive reasoning. This "black-box" nature leads to a lack of interpretability and absolute safety guarantees in complex, long-tail scenarios. To overcome…

Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations.…

Each year, thousands of people learn new visual categorization tasks -- radiologists learn to recognize tumors, birdwatchers learn to distinguish similar species, and crowd workers learn how to annotate valuable data for applications like…

Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong…

Parsing human poses in images is fundamental in extracting critical visual information for artificial intelligent agents. Our goal is to learn self-contained body part representations from images, which we call visual symbols, and their…

We investigate how neural networks can learn and process languages with hierarchical, compositional semantics. To this end, we define the artificial task of processing nested arithmetic expressions, and study whether different types of…

In this paper, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers activations, is extended by incorporating…

Texture classification is a problem that has various applications such as remote sensing and forest species recognition. Solutions tend to be custom fit to the dataset used but fails to generalize. The Convolutional Neural Network (CNN) in…

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional…

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability…

Neurosymbolic (NeSy) frameworks combine neural representations and learning with symbolic representations and reasoning. Combining the reasoning capacities, explainability, and interpretability of symbolic processing with the flexibility…

Stroke-based rendering aims to recreate an image with a set of strokes. Most existing methods render complex images using an uniform-block-dividing strategy, which leads to boundary inconsistency artifacts. To solve the problem, we propose…

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural…

In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot…

LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

There is an increased interest in solving complex constrained problems where part of the input is not given as facts but received as raw sensor data such as images or speech. We will use "visual sudoku" as a prototype problem, where the…

Visual reasoning with compositional natural language instructions, e.g., based on the newly-released Cornell Natural Language Visual Reasoning (NLVR) dataset, is a challenging task, where the model needs to have the ability to create an…