Related papers: Contrastive Representation Distillation via Multi-…
State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…
The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher…
In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required…
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of…
Knowledge distillation (KD) is a machine learning framework that transfers knowledge from a teacher model to a student model. The vanilla KD proposed by Hinton et al. has been the dominant approach in logit-based distillation and…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
Object detection has advanced significantly with Detection Transformers (DETRs). However, these models are computationally demanding, posing challenges for deployment in resource-constrained environments (e.g., self-driving cars). Knowledge…
Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network).…
State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To provide a novel viewpoint to study logit distillation, we…
Knowledge distillation aims at transferring the knowledge from a large teacher model to a small student model with great improvements of the performance of the student model. Therefore, the student network can replace the teacher network to…
Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neural network (i.e., teacher model), which has been widely…
Knowledge distillation (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact…
Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. 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,…
In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's soft logits as extra supervision to train the student…
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…
Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limited-resource devices. Recently, several compression methods…
Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging probability distributions, but neglects the useful representational knowledge. We therefore propose Multi-view Contrastive Learning (MCL) for OKD to…
This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…