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

Visual food recognition in real-world dietary logging scenarios naturally exhibits severe data imbalance, where a small number of food categories appear frequently while many others occur rarely, resulting in long-tailed class…

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…

Graph classification is a crucial task in many real-world multimedia applications, where graphs can represent various multimedia data types such as images, videos, and social networks. Previous efforts have applied graph neural networks…

For the task of image classification, neural networks primarily rely on visual patterns. In robust networks, we would expect for visually similar classes to be represented similarly. We consider the problem of when semantically similar…

In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting…

Class-imbalance is one of the major challenges in real world datasets, where a few classes (called majority classes) constitute much more data samples than the rest (called minority classes). Learning deep neural networks using such…

Industry recommender systems usually suffer from highly-skewed long-tail item distributions where a small fraction of the items receives most of the user feedback. This skew hurts recommender quality especially for the item slices without…

Mixup, a simple data augmentation method that randomly mixes two data points via linear interpolation, has been extensively applied in various deep learning applications to gain better generalization. However, the theoretical underpinnings…

This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to…

To solve the problem of poor performance of deep neural network models due to insufficient data, a simple yet effective interpolation-based data augmentation method is proposed: MSMix (Manifold Swap Mixup). This method feeds two different…

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Deep Belief Network (DBN) has a deep architecture that represents multiple features of input patterns hierarchically with the pre-trained Restricted Boltzmann Machines (RBM). A traditional RBM or DBN model cannot change its network…

Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…

Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images…

The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to…

Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain…

We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches…

We introduce a new method for training deep Boltzmann machines jointly. Prior methods of training DBMs require an initial learning pass that trains the model greedily, one layer at a time, or do not perform well on classification tasks. In…

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models…

Deep neural networks are vulnerable to adversarial attacks, often leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to counter such attacks. However, existing adversarial training…