Related papers: DBN-Mix: Training Dual Branch Network Using Bilate…

Image-text matching remains a challenging task due to heterogeneous semantic diversity across modalities and insufficient distance separability within triplets. Different from previous approaches focusing on enhancing multi-modal…

Camera traps are a method for monitoring wildlife and they collect a large number of pictures. The number of images collected of each species usually follows a long-tail distribution, i.e., a few classes have a large number of instances,…

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We…

Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder…

Long-tailed distributions in image recognition pose a considerable challenge due to the severe imbalance between a few dominant classes with numerous examples and many minority classes with few samples. Recently, the use of large generative…

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…

In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent…

Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution. However, video data in the real world typically exhibit an imbalanced long-tailed class distribution, resulting in a…

In the context of the long-tail scenario, models exhibit a strong demand for high-quality data. Data-centric approaches aim to enhance both the quantity and quality of data to improve model performance. Among these approaches, information…

Object detection has been widely explored for class-balanced datasets such as COCO. However, real-world scenarios introduce the challenge of long-tailed distributions, where numerous categories contain only a few instances. This inherent…

Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data.…

Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. To address unbalanced data, most studies try balancing the data, the loss, or the classifier to…

Inspired by the great success of Deep Neural Networks (DNNs) in natural language processing (NLP), DNNs have been increasingly applied in source code analysis and attracted significant attention from the software engineering community. Due…

Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer…

Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases,…