research
∙
06/21/2023
Inter-Instance Similarity Modeling for Contrastive Learning
The existing contrastive learning methods widely adopt one-hot instance ...
share
research
∙
06/05/2023
Asymmetric Patch Sampling for Contrastive Learning
Asymmetric appearance between positive pair effectively reduces the risk...
research
∙
12/17/2022
Modeling Global Distribution for Federated Learning with Label Distribution Skew
Federated learning achieves joint training of deep models by connecting ...
research
∙
11/23/2021
Learning Dynamic Preference Structure Embedding From Temporal Networks
The dynamics of temporal networks lie in the continuous interactions bet...
research
∙
10/27/2021
Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Knowledge distillation (KD) aims to craft a compact student model that i...
research
∙
05/18/2021
Contrastive Model Inversion for Data-Free Knowledge Distillation
Model inversion, whose goal is to recover training data from a pre-train...
research
∙
02/28/2021
Training Generative Adversarial Networks in One Stage
Generative Adversarial Networks (GANs) have demonstrated unprecedented s...
research
∙
12/09/2020
Progressive Network Grafting for Few-Shot Knowledge Distillation
Knowledge distillation has demonstrated encouraging performances in deep...
research
∙
03/17/2020
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
Exploring the intrinsic interconnections between the knowledge encoded i...
research
∙
12/23/2019
Data-Free Adversarial Distillation
Knowledge Distillation (KD) has made remarkable progress in the last few...
research
∙
09/26/2019
Deep Model Transferability from Attribution Maps
Exploring the transferability between heterogeneous tasks sheds light on...
research
∙
08/20/2019
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
A massive number of well-trained deep networks have been released by dev...
research
∙
11/07/2018
Amalgamating Knowledge towards Comprehensive Classification
With the rapid development of deep learning, there have been an unpreced...
research
∙
07/19/2018
Selective Zero-Shot Classification with Augmented Attributes
In this paper, we introduce a selective zero-shot classification problem...
research
∙
03/30/2018