Related papers: Use Generalized Representations, But Do Not Forget…

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

In asymmetric retrieval systems, models with different capacities are deployed on platforms with different computational and storage resources. Despite the great progress, existing approaches still suffer from a dilemma between retrieval…

Surface-related multiples pose significant challenges in seismic data processing, often obscuring primary reflections and reducing imaging quality. Traditional methods rely on computationally expensive algorithms, the prior knowledge of…

Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks. However, they have recently been shown to suffer limitation in compositional generalization, failing to effectively learn the…

In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the ability of model to extract representative and…

We address multi-reference visual place recognition (VPR), where reference sets captured under varying conditions are used to improve localisation performance. While deep learning with large-scale training improves robustness, increasing…

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…

In this paper, we investigate the use of 3D surface geometry for face recognition and compare it to one based on color map information. The 3D surface and color map data are from the CAESAR anthropometric database. We find that the…

Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scenes that were not observed during training, possibly depending…

Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not…

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and…

Recently, we have seen an increase in the global facial recognition market size. Despite significant advances in face recognition technology with the adoption of convolutional neural networks, there are still open challenges, such as when…

Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it…

Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context. This is intuitively useful for generalization, especially in Named-Entity Recognition where it is crucial to…

Transformer models have recently achieved impressive performance on NLP tasks, owing to new algorithms for self-supervised pre-training on very large text corpora. In contrast, recent literature suggests that simple average word models…

Neural implicit functions have emerged as a powerful representation for surfaces in 3D. Such a function can encode a high quality surface with intricate details into the parameters of a deep neural network. However, optimizing for the…

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…

By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised methods for learning image representations have reached impressive results on standard benchmarks. The result has been a crowded field - many methods with…

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Existing 3D surface representation approaches are unable to accurately classify pixels and their orientation lying on the boundary of an object. Thus resulting in coarse representations which usually require post-processing steps to extract…