相关论文: Privileged Features Distillation at Taobao Recomme…

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new…

In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic…

In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and…

Our paper addresses the problem of models struggling to learn diverse features, due to either forgetting previously learned features or failing to learn new ones. To overcome this problem, we introduce Diverse Feature Learning (DFL), a…

In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent correlation among video frames, we learn discriminative features…

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…

Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be used, enabling the use of any teacher model trained on a…

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher). Albeit useful especially in the penultimate layer and…

Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression…

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination based approach would be desired as it fits seamlessly with the…

This paper aims to explore the potential of combining Deep Reinforcement Learning (DRL) with Knowledge Distillation (KD) by distilling various DRL algorithms and studying their distillation effects. By doing so, the computational burden of…

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is…

Recent improvements in convolutional neural network (CNN)-based single image super-resolution (SISR) methods rely heavily on fabricating network architectures, rather than finding a suitable training algorithm other than simply minimizing…

Cross-platform recommendation aims to improve recommendation accuracy by gathering heterogeneous features from different platforms. However, such cross-silo collaborations between platforms are restricted by increasingly stringent privacy…