Related papers: Hybrid Losses for Hierarchical Embedding Learning

Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it is critical to determine classifier-agnostic bounds on the…

Deep learning work on musical instrument recognition has generally focused on instrument classes for which we have abundant data. In this work, we exploit hierarchical relationships between instruments in a few-shot learning setup to enable…

In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points…

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces…

Compositional zero-shot learning (CZSL) aims to recognize unseen state-object compositions by generalizing from a training set of their primitives (state and object). Current methods often overlook the rich hierarchical structures, such as…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Text classification has become increasingly challenging due to the continuous refinement of classification label granularity and the expansion of classification label scale. To address that, some research has been applied onto strategies…

Large scale image classification models trained on top of popular datasets such as Imagenet have shown to have a distributional skew which leads to disparities in prediction accuracies across different subsections of population…

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to…

Triplet loss, one of the deep metric learning (DML) methods, is to learn the embeddings where examples from the same class are closer than examples from different classes. Motivated by DML, we propose an effective BP-Triplet Loss for…

The multi-label classification problem has generated significant interest in recent years. However, existing approaches do not adequately address two key challenges: (a) the ability to tackle problems with a large number (say millions) of…

Recent pre-trained transformer models achieve superior performance in various code processing objectives. However, although effective at optimizing decision boundaries, common approaches for fine-tuning them for downstream classification…

In this paper, we propose mean squared error (MSE) loss with outlying label for class imbalanced classification. Cross entropy (CE) loss, which is widely used for image recognition, is learned so that the probability value of true class is…

Average-K classification is an alternative to top-K classification in which the number of labels returned varies with the ambiguity of the input image but must average to K over all the samples. A simple method to solve this task is to…

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and…

Music-text multimodal systems have enabled new approaches to Music Information Research (MIR) applications such as audio-to-text and text-to-audio retrieval, text-based song generation, and music captioning. Despite the reported success,…

Contrastive learning has demonstrated promising performance in image and text domains either in a self-supervised or a supervised manner. In this work, we extend the supervised contrastive learning framework to clinical risk prediction…

Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets.…

Recent algorithms in convolutional neural networks (CNN) considerably advance the fine-grained image classification, which aims to differentiate subtle differences among subordinate classes. However, previous studies have rarely focused on…