相关论文: Supervised Contrastive Representation Learning: La…

Recent work has observed an intriguing ''Neural Collapse'' phenomenon in well-trained neural networks, where the last-layer representations of training samples with the same label collapse into each other. This appears to suggest that the…

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into…

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks…

Deep learning for change detection is one of the current hot topics in the field of remote sensing. However, most end-to-end networks are proposed for supervised change detection, and unsupervised change detection models depend on…

Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing…

With the rapid development of deep learning, a variety of change detection methods based on deep learning have emerged in recent years. However, these methods usually require a large number of training samples to train the network model, so…

Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown…

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Inverse problems in imaging such as denoising, deblurring, superresolution (SR) have been addressed for many decades. In recent years, convolutional neural networks (CNNs) have been widely used for many inverse problem areas. Although their…

Deep convolutional neural networks (CNN) have recently been shown in many computer vision and pattern recog- nition applications to outperform by a significant margin state- of-the-art solutions that use traditional hand-crafted features.…

Supervised contrastive representation learning has been shown to be effective in various transfer learning scenarios. However, while asymmetric non-contrastive learning (ANCL) often outperforms its contrastive learning counterpart in…

Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches zero. We inquire into the phenomena coined Neural Collapse in…

Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive learning is susceptible to feature suppression, i.e., it may…

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the…

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to…

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for…

Understanding feature representation for deep neural networks (DNNs) remains an open question within the general field of explainable AI. We use principal component analysis (PCA) to study the performance of a k-nearest neighbors classifier…

Our proposed framework attempts to break the trade-off between performance and explainability by introducing an explainable-by-design convolutional neural network (CNN) based on the lateral inhibition mechanism. The ExplaiNet model consists…