Related papers: Rethinking Softmax Cross-Entropy Loss for Adversar…
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we…
We review the current schemes of text-image matching models and propose improvements for both training and inference. First, we empirically show limitations of two popular loss (sum and max-margin loss) widely used in training text-image…
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…
This paper proposes a new loss function for adversarial training. Since adversarial training has difficulties, e.g., necessity of high model capacity, focusing on important data points by weighting cross-entropy loss has attracted much…
Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and…
Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails to address the…
Ranking tasks constitute fundamental components of extreme similarity learning frameworks, where extremely large corpora of objects are modeled through relative similarity relationships adhering to predefined ordinal structures. Among…
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…
In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks,…
While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…
Metric learning aims at finding a suitable distance metric over the input space, to improve the performance of distance-based learning algorithms. In high-dimensional settings, it can also serve as dimensionality reduction by imposing a…
Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training…
The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that…
Metric learning seeks a transformation of the feature space that enhances prediction quality for the given task at hand. In this work we provide PAC-style sample complexity rates for supervised metric learning. We give matching lower- and…
In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical…
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…
Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial…
Deep learning models have shown incredible performance on numerous image recognition, classification, and reconstruction tasks. Although very appealing and valuable due to their predictive capabilities, one common threat remains challenging…
Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to…
Recently, multimodal contrastive learning (MMCL) approaches, such as CLIP, have achieved a remarkable success in learning representations that are robust against distribution shift and generalize to new domains. Despite the empirical…