Related papers: BCE vs. CE in Deep Feature Learning
Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…
Contrastive learning has emerged as a cornerstone of unsupervised representation learning across vision, language, and graph domains, with InfoNCE as its dominant objective. Despite its empirical success, the theoretical underpinnings of…
Embedding tables are used by machine learning systems to work with categorical features. In modern Recommendation Systems, these tables can be very large, necessitating the development of new methods for fitting them in memory, even during…
The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the…
This paper investigates novel classifier ensemble techniques for uncertainty calibration applied to various deep neural networks for image classification. We evaluate both accuracy and calibration metrics, focusing on Expected Calibration…
This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of…
Cross-entropy (CE) loss is the de-facto standard for training deep neural networks to perform classification. However, CE-trained deep neural networks struggle with robustness and generalisation issues. To alleviate these issues, we propose…
The simplicity Bias (SB) of neural networks, i.e.\ their tendency to represent simple functions, is a key factor in their generalization capabilities. Recent studies show that an excessive SB may harm performance on complex tasks, and the…
Embracing the deep learning techniques for representation learning in clustering research has attracted broad attention in recent years, yielding a newly developed clustering paradigm, viz. the deep clustering (DC). Typically, the DC models…
Deep supervised hashing for image retrieval has attracted researchers' attention due to its high efficiency and superior retrieval performance. Most existing deep supervised hashing works, which are based on pairwise/triplet labels, suffer…
How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To…
The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…
Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find whether PC offers any advantages. Small scale experiments show that PC enables learning…
Ensembling is a successful technique to improve the performance of machine learning (ML) models. Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confidence instead of model errors to better classify difficult…
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…
Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges. As the negative samples are drawn from unlabeled datasets, a…
Deep learning-based methods achieved impressive results for the segmentation of medical images. With the development of 3D fully convolutional networks (FCNs), it has become feasible to produce improved results for multi-organ segmentation…
This paper proposes a generic formulation that significantly expedites the training and deployment of image classification models, particularly under the scenarios of many image categories and high feature dimensions. As a defining…
Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…
Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…