3 papers
cs.CV2024
Accelerating Augmentation Invariance Pretraining
Jinhong Lin, Cheng-En Wu, Yibing Wei +1
Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrast…
cs.LG2022
WeShort: Out-of-distribution Detection With Weak Shortcut structure
Jinhong Lin
Neural networks have achieved impressive performance for data in the distribution which is the same as the training set but can produce an overconfident incorrect result for the da…
cs.LG2021
Extracting knowledge from features with multilevel abstraction
Jinhong Lin, Zhaoyang Li
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. There…