Related papers: Learning from Adversarial Features for Few-Shot Cl…
Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples. Recent approaches pre-train a feature extractor, and then fine-tune for episodic meta-learning. Other…
Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…
Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.The network tends to overfit and does not generalize well to unseen classes due to insufficient training data. Many methods have…
Despite the recent developments in vision-related problems using deep neural networks, there still remains a wide scope in the improvement of generalizing these models to unseen examples. In this paper, we explore the domain of few-shot…
We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs. Besides the traditional content and style representation based on deep features and…
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework,…
Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…
We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…
Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…
The robustness of neural networks to intended perturbations has recently attracted significant attention. In this paper, we propose a new method, \emph{learning with a strong adversary}, that learns robust classifiers from supervised data.…
Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the…
With a goal of accelerating fabrication of additively manufactured components with precise microstructures, we developed a method for structural characterization of key features in additively manufactured materials and parts. The method…
Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core obstacle behind this failure: channel bias, where networks…
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either…
Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust…
Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…
Deep learning has revolutionized various fields, yet its efficacy is hindered by overfitting and the requirement of extensive annotated data, particularly in few-shot learning scenarios where limited samples are available. This paper…
Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the…
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and…
Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional…