相关论文: Class-Aware Robust Adversarial Training for Object…

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative…

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can…

Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations. This inductive bias can be injected into neural…

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…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

We propose a framework for robust and efficient training of Dense Object Nets (DON) with a focus on multi-object robot manipulation scenarios. DON is a popular approach to obtain dense, view-invariant object descriptors, which can be used…

Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified…

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation costs in the field of object detection. In this study, we…

Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of…

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…

Adversarial approach has been widely used for data generation in the last few years. However, this approach has not been extensively utilized for classifier training. In this paper, we propose an adversarial framework for classifier…

Our work addresses the problem of learning to localize objects in an open-world setting, i.e., given the bounding box information of a limited number of object classes during training, the goal is to localize all objects, belonging to both…

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…