相关论文: FROD: Robust Object Detection for Free

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

State-of-the-art object detectors are vulnerable to localized patch hiding attacks, where an adversary introduces a small adversarial patch to make detectors miss the detection of salient objects. The patch attacker can carry out a…

In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended…

The robustness of object detection models is a major concern when applied to real-world scenarios. The performance of most models tends to degrade when confronted with images affected by corruptions, since they are usually trained and…

Recent years have witnessed significant advancements in deep learning-based 3D object detection, leading to its widespread adoption in numerous applications. As 3D object detectors become increasingly crucial for security-critical tasks, it…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

Recently, large pre-trained foundation models have become widely adopted by machine learning practitioners for a multitude of tasks. Given that such models are publicly available, relying on their use as backbone models for downstream tasks…

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…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial…

In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been…

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…

Efficient and accurate object detection is an important topic in the development of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased significantly. The project aims to…

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

Given the large-scale multi-modal training of recent vision-based models and their generalization capabilities, understanding the extent of their robustness is critical for their real-world deployment. In this work, we evaluate the…

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly…

We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification…

Object tracking is an essential task in computer vision that has been studied since the early days of the field. Being able to follow objects that undergo different transformations in the video sequence, including changes in scale,…

Despite their excellent performance, state-of-the-art computer vision models often fail when they encounter adversarial examples. Video perception models tend to be more fragile under attacks, because the adversary has more places to…