activity
20172022
most citedFEED: Feature-level Ensemble for Knowledge Distillation

23 citations · 28 across the 4 of their papers we have counts for

collaborators

9 papers

cs.CV2022

Semantics-Guided Object Removal for Facial Images: with Broad Applicability and Robust Style Preservation

Jookyung Song, Yeonjin Chang, Seonguk Park +1

Object removal and image inpainting in facial images is a task in which objects that occlude a facial image are specifically targeted, removed, and replaced by a properly reconstru…

cs.LG20202 cited

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…

cs.CV2020

Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding

Seong Hyeon Park, Gyubok Lee, Manoj Bhat +6

Multi-agent trajectory forecasting in autonomous driving requires an agent to accurately anticipate the behaviors of the surrounding vehicles and pedestrians, for safe and reliable…

cs.LG2020

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…

cs.CV201923 cited

FEED: Feature-level Ensemble for Knowledge Distillation

SeongUk Park, Nojun Kwak

Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training st…

cs.CV2019

ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection

Jin Hyeok Yoo, Dongsuk Kum, Jun Won Choi

Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hier…