Related papers: Improving Resnet-9 Generalization Trained on Small…

Deep residual learning (ResNet) is a new method for training very deep neural networks using identity map-ping for shortcut connections. ResNet has won the ImageNet ILSVRC 2015 classification task, and achieved state-of-the-art performances…

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing models are questionable because the same test sets have been…

Major winning Convolutional Neural Networks (CNNs), such as AlexNet, VGGNet, ResNet, GoogleNet, include tens to hundreds of millions of parameters, which impose considerable computation and memory overhead. This limits their practical use…

Convolutional neural networks have been achieving the best possible accuracies in many visual pattern classification problems. However, due to the model capacity required to capture such representations, they are often oversensitive to…

Normalization is an important and vastly investigated technique in deep learning. However, its role for Ordinary Differential Equation based networks (neural ODEs) is still poorly understood. This paper investigates how different…

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the…

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…

Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous,…

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations.…

Deep learning models have proven to be effective on medical datasets for accurate diagnostic predictions from images. However, medical datasets often contain noisy, mislabeled, or poorly generalizable images, particularly for edge cases and…

Data augmentation is essential to achieve state-of-the-art performance in many deep learning applications. However, the most effective augmentation techniques become computationally prohibitive for even medium-sized datasets. To address…

We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…

Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of…

Empirical adversarial risk minimization (EARM) is a widely used mathematical framework to robustly train deep neural nets (DNNs) that are resistant to adversarial attacks. However, both natural and robust accuracies, in classifying clean…

This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated…

Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with…

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that trivially evaluating…

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…