Related papers: Sparse and Dense Retrievers Learn Better Together:…

We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into retrieval-ready sparse features. When trained on frozen…

Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations…

Sparse dictionary learning (SDL) is a fundamental technique that is useful for many image processing tasks. As an example we consider here image recovery, where SDL can be cast as a nonsmooth optimization problem. For this kind of problems,…

Current pre-trained language model approaches to information retrieval can be broadly divided into two categories: sparse retrievers (to which belong also non-neural approaches such as bag-of-words methods, e.g., BM25) and dense retrievers.…

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have…

Learned sparse retrieval, which can efficiently perform retrieval through mature inverted-index engines, has garnered growing attention in recent years. Particularly, the inference-free sparse retrievers are attractive as they eliminate…

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks…

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain…

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…

A lot of recent work has focused on sparse learned indexes that use deep neural architectures to significantly improve retrieval quality while keeping the efficiency benefits of the inverted index. While such sparse learned structures…

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Sparse representation using over-complete dictionaries have shown to produce good quality results in various image processing tasks. Dictionary learning algorithms have made it possible to engineer data adaptive dictionaries which have…

Lexical and semantic matching capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust than either alone. Prior work performs hybrid retrieval by conducting lexical…

Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and…

Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a…

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging.…

Recent advances in deep neural networks have achieved unprecedented success in visual speech recognition. However, there remains substantial disparity between current methods and their deployment in resource-constrained devices. In this…