86 citations · 296 across the 10 of their papers we have counts for
11 papers
ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space
Minkyu Kim, Baekseung Kim, Junhoo Lee +2
Diffusion models achieve high-quality image generation but remain computationally expensive due to iterative denoising across many timesteps. Existing acceleration methods mainly r…
Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
Byeonggeun Kim, Seunghan Yang, Jangho Kim +3
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance norm…
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Byeonggeun Kim, Seunghan Yang, Jangho Kim +1
This technical report describes the details of our TASK1A submission of the DCASE2021 challenge. The goal of the task is to design an audio scene classification system for device-i…
Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
KiYoon Yoo, Jangho Kim, Jiho Jang +1
Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversaria…
Position-based Scaled Gradient for Model Quantization and Pruning
Jangho Kim, KiYoon Yoo, Nojun Kwak
We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly. First, we theoretica…
Feature-map-level Online Adversarial Knowledge Distillation
Inseop Chung, SeongUk Park, Jangho Kim +1
Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. T…
QKD: Quantization-aware Knowledge Distillation
Jangho Kim, Yash Bhalgat, Jinwon Lee +2
Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge…
Feature Fusion for Online Mutual Knowledge Distillation
Jangho Kim, Minsung Hyun, Inseop Chung +1
We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated…
StackNet: Stacking Parameters for Continual learning
Jangho Kim, Jeesoo Kim, Nojun Kwak
Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gr…
Vehicle Image Generation Going Well with The Surroundings
Jeesoo Kim, Jangho Kim, Jaeyoung Yoo +2
Since the generative neural networks have made a breakthrough in the image generation problem, lots of researches on their applications have been studied such as image restoration,…
Paraphrasing Complex Network: Network Compression via Factor Transfer
Jangho Kim, SeongUk Park, Nojun Kwak
Many researchers have sought ways of model compression to reduce the size of a deep neural network (DNN) with minimal performance degradation in order to use DNNs in embedded syste…