
-
Rethinking Spatial Dimensions of Vision Transformers
Vision Transformer (ViT) extends the application range of transformers f...
read it
-
Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
Knowledge distillation extracts general knowledge from a pre-trained tea...
read it
-
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
ImageNet has been arguably the most popular image classification benchma...
read it
-
VideoMix: Rethinking Data Augmentation for Video Classification
State-of-the-art video action classifiers often suffer from overfitting....
read it
-
ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network
This paper addresses representational bottleneck in a network and propos...
read it
-
Slowing Down the Weight Norm Increase in Momentum-based Optimizers
Normalization techniques, such as batch normalization (BN), have led to ...
read it
-
A Comprehensive Overhaul of Feature Distillation
We investigate the design aspects of feature distillation methods achiev...
read it
-
Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
In person re-identification (ReID) task, because of its shortage of trai...
read it
-
Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
An activation boundary for a neuron refers to a separating hyperplane th...
read it
-
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
Many recent works on knowledge distillation have provided ways to transf...
read it
-
Improving Knowledge Distillation with Supporting Adversarial Samples
Many recent works on knowledge distillation have provided ways to transf...
read it