Related papers: Fine-Grained ImageNet Classification in the Wild
A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as problems of hierarchical classification, in which the…
With the tremendous success of deep learning in visual tasks, the representations extracted from intermediate layers of learned models, that is, deep features, attract much attention of researchers. Previous empirical analysis shows that…
A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…
Machine learning methods must be trusted to make appropriate decisions in real-world environments, even when faced with out-of-distribution (OOD) samples. Many current approaches simply aim to detect OOD examples and alert the user when an…
Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that…
Humans are able to categorize images very efficiently, in particular to detect the presence of an animal very quickly. Recently, deep learning algorithms based on convolutional neural networks (CNNs) have achieved higher than human accuracy…
Fine-grained classification models are designed to focus on the relevant details necessary to distinguish highly similar classes, particularly when intra-class variance is high and inter-class variance is low. Most existing models rely on…
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to…
With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a…
Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our…
Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning…
The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…
Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance…
Image classifiers are an important component of today's software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However,…
Convolutional Neural Networks have become state of the art methods for image classification over the last couple of years. By now they perform better than human subjects on many of the image classification datasets. Most of these datasets…
Text recognition in the wild is an important technique for digital maps and urban scene understanding, in which the natural resembling properties between glyphs is one of the major reasons that lead to wrong recognition results. To address…
Pose variation and subtle differences in appearance are key challenges to fine-grained classification. While deep networks have markedly improved general recognition, many approaches to fine-grained recognition rely on anchoring networks to…
While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…
Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image…