most citedBag of Tricks for Domain Adaptive Multi-Object Tracking

1 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2022

1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

Daehan Kim, Minseok Seo, YoungJin Jeon +1

The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsupervised domain adaptive model in semantic segmentation tasks for industrial waste sorting. In this paper, we in…

cs.CV20221 cited

Bag of Tricks for Domain Adaptive Multi-Object Tracking

Minseok Seo, Jeongwon Ryu, Kwangjin Yoon

In this paper, SIA_Track is presented which is developed by a research team from SI Analytics. The proposed method was built from pre-existing detector and tracker under the tracki…

cs.CV2022

Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation

Daehan Kim, Minseok Seo, Jinsun Park +1

In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting…

cs.CV20221 cited

Unsupervised Change Detection Based on Image Reconstruction Loss

Hyeoncheol Noh, Jingi Ju, Minseok Seo +2

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming.…

cs.CV2020

Sequential Feature Filtering Classifier

Minseok Seo, Jaemin Lee, Jongchan Park +1

We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes…