162 citations · 221 across the 11 of their papers we have counts for
12 papers
Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning
Athul Shibu, Abhishek Kumar, Heechul Jung +1
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networ…
Fair Comparison between Efficient Attentions
Jiuk Hong, Chaehyeon Lee, Soyoun Bang +1
Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a…
Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints
Jaesin Ahn, Jiuk Hong, Jeongwoo Ju +1
A vision transformer (ViT) is the dominant model in the computer vision field. Despite numerous studies that mainly focus on dealing with inductive bias and complexity, there remai…
Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner
Chaehyeon Lee, Junghoon Seo, Heechul Jung
In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because t…
Extending Contrastive Learning to Unsupervised Coreset Selection
Jeongwoo Ju, Heechul Jung, Yoonju Oh +1
Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providin…
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
Jaemin Na, Heechul Jung, Hyung Jin Chang +1
Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, most of the studies were based on direct adap…