Related papers: Hierarchical Self-supervised Augmented Knowledge D…

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization. This paper delves…

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories…

Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill…

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

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 is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…

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…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image…

Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual…

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network…