14 citations · 52 across the 14 of their papers we have counts for
15 papers
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Kangsan Kim, Geon Park, Youngwan Lee +2
Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on ou…
Training-Free Exponential Context Extension via Cascading KV Cache
Jeffrey Willette, Heejun Lee, Youngwan Lee +2
The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context…
A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention
Heejun Lee, Geon Park, Youngwan Lee +7
In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented lan…
Visualizing the loss landscape of Self-supervised Vision Transformer
Youngwan Lee, Jeffrey Ryan Willette, Jonghee Kim +1
The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows bet…
KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
Youngwan Lee, Kwanyong Park, Yoorhim Cho +2
As text-to-image (T2I) synthesis models increase in size, they demand higher inference costs due to the need for more expensive GPUs with larger memory, which makes it challenging…
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
Sunil Hwang, Jaehong Yoon, Youngwan Lee +1
Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an ex…
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders
Youngwan Lee, Jeffrey Willette, Jonghee Kim +2
Masked image modeling (MIM) has become a popular strategy for self-supervised learning~(SSL) of visual representations with Vision Transformers. A representative MIM model, the mas…
MPViT: Multi-Path Vision Transformer for Dense Prediction
Youngwan Lee, Jonghee Kim, Jeff Willette +1
Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with vary…
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
Youngwan Lee, Hyung-Il Kim, Kimin Yun +1
Video classification researches that have recently attracted attention are the fields of temporal modeling and 3D efficient architecture. However, the temporal modeling methods are…
Adversarial Training with Stochastic Weight Average
Joong-Won Hwang, Youngwan Lee, Sungchan Oh +1
Adversarial training deep neural networks often experience serious overfitting problem. Recently, it is explained that the overfitting happens because the sample complexity of trai…
Localization Uncertainty Estimation for Anchor-Free Object Detection
Youngwan Lee, Joong-won Hwang, Hyung-Il Kim +4
Since many safety-critical systems, such as surgical robots and autonomous driving cars operate in unstable environments with sensor noise and incomplete data, it is desirable for…
CenterMask : Real-Time Anchor-Free Instance Segmentation
Youngwan Lee, Jongyoul Park
We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage o…
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
Youngwan Lee, Joong-won Hwang, Sangrok Lee +2
As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Althoug…
Rank of Experts: Detection Network Ensemble
Seung-Hwan Bae, Youngwan Lee, Youngjoo Jo +2
The recent advances of convolutional detectors show impressive performance improvement for large scale object detection. However, in general, the detection performance usually decr…
Wide-Residual-Inception Networks for Real-time Object Detection
Youngwan Lee, Byeonghak Yim, Huien Kim +4
Since convolutional neural network(CNN)models emerged,several tasks in computer vision have actively deployed CNN models for feature extraction. However,the conventional CNN models…