Related papers: Using Feature Alignment Can Improve Clean Average …

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…

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies. Although these methods have different underlying logic, both rely…

We propose an object detection method that improves the accuracy of the conventional SSD (Single Shot Multibox Detector), which is one of the top object detection algorithms in both aspects of accuracy and speed. The performance of a deep…

Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i.e. task-individual). In this paper, a collaborative framework called MatchDet (i.e.…

Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images. However, in some application domains such as remote sensing, purchasing…

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

By adding human-imperceptible perturbations to images, DNNs can be easily fooled. As one of the mainstream methods, feature space targeted attacks perturb images by modulating their intermediate feature maps, for the discrepancy between the…

In frame-based vision, object detection faces substantial performance degradation under challenging conditions due to the limited sensing capability of conventional cameras. Event cameras output sparse and asynchronous events, providing a…

Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection…

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Object detection is a fundamental problem in computer vision, aiming at locating and classifying objects in image. Although current devices can easily take very high-resolution images, current approaches of object detection seldom consider…

A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a…

We propose a novel implicit feature refinement module for high-quality instance segmentation. Existing image/video instance segmentation methods rely on explicitly stacked convolutions to refine instance features before the final…

Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful. Despite the great success of the generic object detection methods trained on ground-to-ground images, a huge performance drop is…

DNNs are vulnerable to adversarial examples, which poses great security concerns for security-critical systems. In this paper, a novel adaptive-patch-based physical attack (AP-PA) framework is proposed, which aims to generate adversarial…

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from inevitably decreased clean accuracy. Instead…