research
∙
06/08/2023
Sy-CON: Symmetric Contrastive Loss for Continual Self-Supervised Representation Learning
We introduce a novel and general loss function, called Symmetric Contras...
share
research
∙
01/27/2023
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Since the recent advent of regulations for data protection (e.g., the Ge...
research
∙
10/04/2022
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
Pretrained Language Models (LMs) memorize a vast amount of knowledge dur...
research
∙
06/16/2022
Is Continual Learning Truly Learning Representations Continually?
Continual learning (CL) aims to learn from sequentially arriving tasks w...
research
∙
01/29/2022
Task-Balanced Batch Normalization for Exemplar-based Class-Incremental Learning
Batch Normalization (BN) is an essential layer for training neural netwo...
research
∙
11/24/2021
Supervised Neural Discrete Universal Denoiser for Adaptive Denoising
We improve the recently developed Neural DUDE, a neural network-based ad...
research
∙
10/08/2021
Observations on K-image Expansion of Image-Mixing Augmentation for Classification
Image-mixing augmentations (e.g., Mixup or CutMix), which typically mix ...
research
∙
06/22/2021
Self-Supervised Iterative Contextual Smoothing for Efficient Adversarial Defense against Gray- and Black-Box Attack
We propose a novel and effective input transformation based adversarial ...
research
∙
05/23/2021
FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise
We consider the challenging blind denoising problem for Poisson-Gaussian...
research
∙
06/12/2020
CPR: Classifier-Projection Regularization for Continual Learning
We propose a general, yet simple patch that can be applied to existing r...
research
∙
03/30/2020
Adaptive Group Sparse Regularization for Continual Learning
We propose a novel regularization-based continual learning method, dubbe...
research
∙
05/28/2019
Uncertainty-based Continual Learning with Adaptive Regularization
We introduce a new regularization-based continual learning algorithm, du...
research
∙
05/25/2019
GAN2GAN: Generative Noise Learning for Blind Image Denoising with Single Noisy Images
We tackle a challenging blind image denoising problem, in which only sin...
research
∙
02/07/2019
DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling
We propose DoPAMINE, a new neural network based multiplicative noise des...
research
∙
07/19/2018
Fully Convolutional Pixel Adaptive Image Denoiser
We propose a new denoising algorithm, dubbed as Fully Convolutional Adap...
research
∙
09/17/2017