相关论文: Dual Relation Knowledge Distillation for Object De…

In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and…

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper, we point out two potential reasons for this problem: 1)…

The joint utilization of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating…

Dual pixels contain disparity cues arising from the defocus blur. This disparity information is useful for many vision tasks ranging from autonomous driving to 3D creative realism. However, directly estimating disparity from dual pixels is…

Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recently identified many scenarios where the training data may…

With the exponential increase in image data, training an image restoration model is laborious. Dataset distillation is a potential solution to this problem, yet current distillation techniques are a blank canvas in the field of image…

The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…

Very low-resolution face recognition is challenging due to the serious loss of informative facial details in resolution degradation. In this paper, we propose a generative-discriminative representation distillation approach that combines…

Traditional object detection are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. Knowledge distillation is a straightforward…

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…

Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large…

Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate…

While Knowledge Distillation (KD) has been recognized as a useful tool in many visual tasks, such as supervised classification and self-supervised representation learning, the main drawback of a vanilla KD framework is its mechanism, which…

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge…

The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

High-resolution processing of seismic signals is crucial for subsurface geological characterization and thin-layer reservoir identification. Traditional high-resolution algorithms can partially recover high-frequency information but often…

Most of recent attention-guided feature masking distillation methods perform knowledge transfer via global teacher attention maps without delving into fine-grained clues. Instead, performing distillation at finer granularity is conducive to…

Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enhance the student model by utilizing the similarity…