Related papers: Convolutional Dynamic Alignment Networks for Inter…
Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly…
Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform an inverse computer graphics task, and the network parameters…
Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…
In recent years, convolutional neural networks (CNNs) with channel-wise feature refining mechanisms have brought noticeable benefits to modelling channel dependencies. However, current attention paradigms fail to infer an optimal channel…
Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical…
The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised DA by…
Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions,…
Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs…
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of…
Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…
Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…
Recently, Convolutional Neural Networks (CNNs) have shown unprecedented success in the field of computer vision, especially on challenging image classification tasks by relying on a universal approach, i.e., training a deep model on a…
The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, this paper introduces a…
Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizability with modality-specific structure. Continuous (implicit) methods preserve fine-grained…
Deep convolutional networks are ubiquitous in computer vision, due to their excellent performance across different tasks for various domains. Models are, however, often trained in isolation for each task, failing to exploit relatedness…
Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps…
We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…
We tackle image question answering (ImageQA) problem by learning a convolutional neural network (CNN) with a dynamic parameter layer whose weights are determined adaptively based on questions. For the adaptive parameter prediction, we…