86 citations · 685 across the 67 of their papers we have counts for
12 papers · 1 filter
PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation
Jangho Kim, Simyung Chang, Nojun Kwak
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rar…
LFI-CAM: Learning Feature Importance for Better Visual Explanation
Kwang Hee Lee, Chaewon Park, Junghyun Oh +1
Class Activation Mapping (CAM) is a powerful technique used to understand the decision making of Convolutional Neural Network (CNN) in computer vision. Recently, there have been at…
Prototype-based Personalized Pruning
Jangho Kim, Simyung Chang, Sungrack Yun +1
Nowadays, as edge devices such as smartphones become prevalent, there are increasing demands for personalized services. However, traditional personalization methods are not suitabl…
Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation
Sangho Lee, Kiyoon Yoo, Nojun Kwak
Federated learning (FL), which utilizes communication between the server (core) and local devices (edges) to indirectly learn from more data, is an emerging field in deep learning…
On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective
SeongUk Park, KiYoon Yoo, Nojun Kwak
To put a state-of-the-art neural network to practical use, it is necessary to design a model that has a good trade-off between the resource consumption and performance on the test…
Class-Imbalanced Semi-Supervised Learning
Minsung Hyun, Jisoo Jeong, Nojun Kwak
Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption th…
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…
Disentangling Options with Hellinger Distance Regularizer
Minsung Hyun, Junyoung Choi, Nojun Kwak
In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and…
Task-oriented Design through Deep Reinforcement Learning
Junyoung Choi, Minsung Hyun, Nojun Kwak
We propose a new low-cost machine-learning-based methodology which assists designers in reducing the gap between the problem and the solution in the design process. Our work applie…
Unpriortized Autoencoder For Image Generation
Jaeyoung Yoo, Hojun Lee, Nojun Kwak
In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assumi…
Towards Governing Agent's Efficacy: Action-Conditional -VAE for Deep Transparent Reinforcement Learning
John Yang, Gyujeong Lee, Minsung Hyun +2
We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable w…
Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
YoungJoon Yoo, Seonguk Park, Junyoung Choi +2
This paper proposes a new algorithm for controlling classification results by generating a small additive perturbation without changing the classifier network. Our work is inspired…