Related papers: AlignMixup: Improving Representations By Interpola…
Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only…
The core of the general recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by…
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…
Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invariant data augmentation…
This paper introduces a simple extension of mixup (Zhang et al., 2018) data augmentation to enhance generalization in visual recognition tasks. Unlike the vanilla mixup method, which blends entire images, our approach focuses on combining…
Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence,…
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs…
Automatic Facial Expression Recognition (FER) has attracted increasing attention in the last 20 years since facial expressions play a central role in human communication. Most FER methodologies utilize Deep Neural Networks (DNNs) that are…
Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data…
Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of…
Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…
Deep learning has made significant advances in computer vision, particularly in image classification tasks. Despite their high accuracy on training data, deep learning models often face challenges related to complexity and overfitting. One…
This paper presents a supervised mixing augmentation method termed SuperMix, which exploits the salient regions within input images to construct mixed training samples. SuperMix is designed to obtain mixed images rich in visual features and…
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…
We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images. The model is unique in forming a nonlinear combination of three traditional interpolation techniques…
Mixture models are well-established learning approaches that, in computer vision, have mostly been applied to inverse or ill-defined problems. However, they are general-purpose divide-and-conquer techniques, splitting the input space into…
CutMix is a data augmentation strategy that cuts and pastes image patches to mixup training data. Existing methods pick either random or salient areas which are often inconsistent to labels, thus misguiding the training model. By our…
The Mixup scheme suggests mixing a pair of samples to create an augmented training sample and has gained considerable attention recently for improving the generalizability of neural networks. A straightforward and widely used extension of…
Pre-trained multi-modal models, such as CLIP, provide transferable embeddings and show promising results in diverse applications. However, the analysis of learned multi-modal embeddings is relatively unexplored, and the embedding…