113 citations · 203 across the 21 of their papers we have counts for
23 papers
Continual Learning via Self-Probe Gradients
Dongkyu Cho, Rumi Chunara, Sungmin Cha
Adapting pretrained models to new data can cause catastrophic forgetting of previously learned behavior. When only a few past samples remain, they give continual learning methods s…
Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
Sungmin Cha, Kyunghyun Cho
Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits…
Forget Forgetting: Continual Learning in a World of Abundant Memory
Dongkyu Cho, Taesup Moon, Rumi Chunara +2
Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottl…
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
Sungmin Cha, Sungjun Cho, Dasol Hwang +1
Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and co…
Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation
Jihwan Kwak, Sungmin Cha, Taesup Moon
This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped al…
Hyperparameters in Continual Learning: A Reality Check
Sungmin Cha, Kyunghyun Cho
Continual learning (CL) aims to train a model on a sequence of tasks (i.e., a CL scenario) while balancing the trade-off between plasticity (learning new tasks) and stability (reta…
Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
Sungmin Cha, Kyunghyun Cho, Taesup Moon
We introduce a novel Pseudo-Negative Regularization (PNR) framework for effective continual self-supervised learning (CSSL). Our PNR leverages pseudo-negatives obtained through mod…
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sen…
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
Joel Jang, Dongkeun Yoon, Sohee Yang +4
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities…
Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective
Sungmin Cha, Jihwan Kwak, Dongsub Shim +4
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evalu…
Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Batch Normalization (BN) and its variants has been extensively studied for neural nets in various computer vision tasks, but relatively little work has been dedicated to studying t…
Supervised Neural Discrete Universal Denoiser for Adaptive Denoising
Sungmin Cha, Seonwoo Min, Sungroh Yoon +1
We improve the recently developed Neural DUDE, a neural network-based adaptive discrete denoiser, by combining it with the supervised learning framework. Namely, we make the superv…
Observations on K-image Expansion of Image-Mixing Augmentation for Classification
Joonhyun Jeong, Sungmin Cha, Youngjoon Yoo +3
Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their…
NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations
Sungmin Cha, Naeun Ko, Youngjoon Yoo +1
We propose a novel and effective purification based adversarial defense method against pre-processor blind white- and black-box attacks. Our method is computationally efficient and…
SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
Sungmin Cha, Beomyoung Kim, Youngjoon Yoo +1
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowl…
FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise
Jaeseok Byun, Sungmin Cha, Taesup Moon
We consider the challenging blind denoising problem for Poisson-Gaussian noise, in which no additional information about clean images or noise level parameters is available. Partic…
CPR: Classifier-Projection Regularization for Continual Learning
Sungmin Cha, Hsiang Hsu, Taebaek Hwang +2
We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired b…
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
Sangwon Jung, Hongjoon Ahn, Sungmin Cha +1
We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Ou…
Uncertainty-based Continual Learning with Adaptive Regularization
Hongjoon Ahn, Sungmin Cha, Donggyu Lee +1
We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learni…
GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
Sungmin Cha, Taeeon Park, Byeongjoon Kim +2
We tackle a challenging blind image denoising problem, in which only single distinct noisy images are available for training a denoiser, and no information about noise is known, ex…
DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling
Sunghwan Joo, Sungmin Cha, Taesup Moon
We propose DoPAMINE, a new neural network based multiplicative noise despeckling algorithm. Our algorithm is inspired by Neural AIDE (N-AIDE), which is a recently proposed neural a…
Fully Convolutional Pixel Adaptive Image Denoiser
Sungmin Cha, Taesup Moon
We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully con…
Neural Affine Grayscale Image Denoising
Sungmin Cha, Taesup Moon
We propose a new grayscale image denoiser, dubbed as Neural Affine Image Denoiser (Neural AIDE), which utilizes neural network in a novel way. Unlike other neural network based ima…