Related papers: ADPS: Asymmetric Distillation Post-Segmentation fo…

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student…

Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD).The representation discrepancy of anomalies in the teacher-student (T-S) model provides essential evidence for AD.…

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous…

Due to the data imbalance and the diversity of defects, student-teacher networks (S-T) are favored in unsupervised anomaly detection, which explores the discrepancy in feature representation derived from the knowledge distillation process…

Online Knowledge Distillation (OKD) methods streamline the distillation training process into a single stage, eliminating the need for knowledge transfer from a pretrained teacher network to a more compact student network. This paper…

With the wide application of knowledge distillation between an ImageNet pre-trained teacher model and a learnable student model, unsupervised anomaly detection has witnessed a significant achievement in the past few years. The success of…

Anomaly detection (AD) plays an important role in various real-world applications. Recent advancements in AD, however, are often biased towards industrial inspection, struggle to generalize to broader tasks like semantic anomaly detection…

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…

Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…

This paper aims to address the problem of anomaly discovery in semantic segmentation. Our key observation is that semantic classification plays a critical role in existing approaches, while the incorrectly classified pixels are easily…

For a very long time, unsupervised learning for anomaly detection has been at the heart of image processing research and a stepping stone for high performance industrial automation process. With the emergence of CNN, several methods have…

Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is available. This work discovers previously unknown problems of student-teacher…

Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak…

Reconstruction-based methods have been commonly used for unsupervised anomaly detection, in which a normal image is reconstructed and compared with the given test image to detect and locate anomalies. Recently, diffusion models have shown…

In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors. We observe that off-the-shelf KD methods manifest their efficacy only when the teacher model and student counterpart share similar intermediate…

Learning semantically meaningful representations from unstructured 3D point clouds remains a central challenge in computer vision, especially in the absence of large-scale labeled datasets. While masked point modeling (MPM) is widely used…

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.…