Related papers: A Simple Data Mixing Prior for Improving Self-Supe…
The deep Convolutional Neural Network (CNN) became very popular as a fundamental technique for image classification and objects recognition. To improve the recognition accuracy for the more complex tasks, deeper networks have being…
User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some…
Training deep neural networks requires datasets with a large number of annotated examples. The collection and annotation of these datasets is not only extremely expensive but also faces legal and privacy problems. These factors are a…
Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…
While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation…
In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is…
Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in…
Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…
The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…
Magnetic Resonance Imaging (MRI) has become an important technique in the clinic for the visualization, detection, and diagnosis of various diseases. However, one bottleneck limitation of MRI is the relatively slow data acquisition process.…
Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…
As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning.…
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…
Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a…
Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…
Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning…
Contrastive representation learning of videos highly relies on the availability of millions of unlabelled videos. This is practical for videos available on web but acquiring such large scale of videos for real-world applications is very…
Since many real-world data can be described from multiple views, multi-view learning has attracted considerable attention. Various methods have been proposed and successfully applied to multi-view learning, typically based on matrix…
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…
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,…