Dataset distillation: A comprehensive review
Recent success of deep learning is largely attributed to the sheer amount of data used for
training deep neural networks. Despite the unprecedented success, the massive data …
training deep neural networks. Despite the unprecedented success, the massive data …
Distilling knowledge via knowledge review
Abstract Knowledge distillation transfers knowledge from the teacher network to the student
one, with the goal of greatly improving the performance of the student network. Previous …
one, with the goal of greatly improving the performance of the student network. Previous …
Decoupled knowledge distillation
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 …
intermediate layers, while the significance of logit distillation is greatly overlooked. To …
Knowledge distillation from a stronger teacher
Unlike existing knowledge distillation methods focus on the baseline settings, where the
teacher models and training strategies are not that strong and competing as state-of-the-art …
teacher models and training strategies are not that strong and competing as state-of-the-art …
Knowledge distillation with the reused teacher classifier
Abstract Knowledge distillation aims to compress a powerful yet cumbersome teacher model
into a lightweight student model without much sacrifice of performance. For this purpose …
into a lightweight student model without much sacrifice of performance. For this purpose …
Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining
Mainstream 3D representation learning approaches are built upon contrastive or generative
modeling pretext tasks, where great improvements in performance on various downstream …
modeling pretext tasks, where great improvements in performance on various downstream …
Masked generative distillation
Abstract Knowledge distillation has been applied to various tasks successfully. The current
distillation algorithm usually improves students' performance by imitating the output of the …
distillation algorithm usually improves students' performance by imitating the output of the …
Neural feature fusion fields: 3d distillation of self-supervised 2d image representations
We present Neural Feature Fusion Fields (N3F),\a method that improves dense 2D image
feature extractors when the latter are applied to the analysis of multiple images …
feature extractors when the latter are applied to the analysis of multiple images …
3d infomax improves gnns for molecular property prediction
Molecular property prediction is one of the fastest-growing applications of deep learning with
critical real-world impacts. Although the 3D molecular graph structure is necessary for …
critical real-world impacts. Although the 3D molecular graph structure is necessary for …
Contrastive representation learning: A framework and review
Contrastive Learning has recently received interest due to its success in self-supervised
representation learning in the computer vision domain. However, the origins of Contrastive …
representation learning in the computer vision domain. However, the origins of Contrastive …