Related papers: Two-Stage Triplet Loss Training with Curriculum Au…

We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an…

Real-world systems are often formulated as constrained optimization problems. Techniques to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential Equations (Neural ODEs), have been used. However, these…

Developing 3D vision-language models with robust clinical reasoning remains a challenge due to the inherent complexity of volumetric medical imaging, the tendency of models to overfit superficial report patterns, and the lack of…

Methods to learn under algorithmic triage have predominantly focused on supervised learning settings where each decision, or prediction, is independent of each other. Under algorithmic triage, a supervised learning model predicts a fraction…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Audio-text retrieval aims at retrieving a target audio clip or caption from a pool of candidates given a query in another modality. Solving such cross-modal retrieval task is challenging because it not only requires learning robust feature…

Accurate stereo depth estimation plays a critical role in various 3D tasks in both indoor and outdoor environments. Recently, learning-based multi-view stereo methods have demonstrated competitive performance with a limited number of views.…

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the…

The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral…

Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently.…

Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages, as well as monolingual bias in pre-training. Existing methods, such as bilingual…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

Retrieval-augmented generation (RAG) grounds large language models (LLMs) in up-to-date external evidence, yet existing multi-hop RAG pipelines still issue redundant subqueries, explore too shallowly, or wander through overly long search…

Self-supervised pre-training recently demonstrates success on large-scale multimodal data, and state-of-the-art contrastive learning methods often enforce the feature consistency from cross-modality inputs, such as video/audio or video/text…

In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to…

Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…

We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.…

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…

In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of unsupervised backlit image enhancement. Our work builds on the state-of-the-art CLIP-LIT approach, which learns a…

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…