Related papers: Robust and Accurate Object Detection via Self-Know…
The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…
Knowledge distillation is a widely used paradigm for inheriting information from a complicated teacher network to a compact student network and maintaining the strong performance. Different from image classification, object detectors are…
Adversarial training has been widely explored for mitigating attacks against deep models. However, most existing works are still trapped in the dilemma between higher accuracy and stronger robustness since they tend to fit a model towards…
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.…
Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…
Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…
Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…
We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for…
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…
Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame.…
Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate…
Convolutional neural networks have a significant improvement in the accuracy of Object detection. As convolutional neural networks become deeper, the accuracy of detection is also obviously improved, and more floating-point calculations are…
Object detection, as a fundamental computer vision task, has achieved a remarkable progress with the emergence of deep neural networks. Nevertheless, few works explore the adversarial robustness of object detectors to resist adversarial…
Deep learning models are shown to be vulnerable to adversarial examples. Though adversarial training can enhance model robustness, typical approaches are computationally expensive. Recent works proposed to transfer the robustness to…
Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss,…
Object detection has achieved remarkable accuracy through deep learning, yet these improvements often come with increased computational cost, limiting deployment on resource-constrained devices. Knowledge Distillation (KD) provides an…
Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adversarial…
Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…
Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation…
Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…