相关论文: The Domain Mixed Unit: A New Neural Arithmetic Lay…

Neural networks in general, from MLPs and CNNs to attention-based Transformers, are constructed from layers of linear combinations followed by nonlinear operations such as ReLU, Sigmoid, or Softmax. Despite their strength, these…

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter framework and design…

We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD). Our goal is to…

Deep metric learning (DML) is a popular approach for images retrieval, solving verification (same or not) problems and addressing open set classification. Arguably, the most common DML approach is with triplet loss, despite significant…

Neural Algorithmic Reasoning is an emerging area of machine learning which seeks to infuse algorithmic computation in neural networks, typically by training neural models to approximate steps of classical algorithms. In this context, much…

Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in…

A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard,…

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these…

The emergence of new, off-path smart network cards (SmartNICs), known generally as Data Processing Units (DPU), has opened a wide range of research opportunities. Of particular interest is the use of these and related devices in tandem with…

We propose Dynamic Meta-Metrics (DMM), a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. Rather than relying on a single static ensemble or language-specific weighting,…

Measurement update rules for Bayes filters often contain hand-crafted heuristics to compute observation probabilities for high-dimensional sensor data, like images. In this work, we propose the novel approach Deep Measurement Update (DMU)…

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations…

Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain…

Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performance on image-related tasks. However, it also has high…

In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching. Our proposed method is a dual auto-encoder neural network that maps 2D and 3D input into a shared latent space…

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the…

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem…

We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

Domain decomposition methods (DDMs) are popular solvers for discretized systems of partial differential equations (PDEs), with one-level and multilevel variants. These solvers rely on several algorithmic and mathematical parameters,…