7 papers
Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention
Dongheon Lee, Seokju Yun, Jaegyun Im +1
Recent Super-Resolution~(SR) methods mainly adopt Transformers for their strong long-range modeling capability and exceptional representational capacity. However, most SR Transform…
RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation
Chanseul Cho, Seokju Yun, Jeaseong Jeon +2
Domain Generalized Semantic Segmentation (DGSS) aims to maintain robust performance across unseen target domains. Vision Foundation Models (VFMs) offer rich multi-domain knowledge…
StAR: Segment Anything Reasoner
Seokju Yun, Dongheon Lee, Noori Bae +3
As AI systems are being integrated more rapidly into diverse and complex real-world environments, the ability to perform holistic reasoning over an implicit query and an image to l…
Emulating Self-attention with Convolution for Efficient Image Super-Resolution
Dongheon Lee, Seokju Yun, Youngmin Ro
In this paper, we tackle the high computational overhead of Transformers for efficient image super-resolution~(SR). Motivated by the observations of self-attention's inter-layer re…
SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning
Seokju Yun, Seunghye Chae, Dongheon Lee +1
Domain generalization (DG) aims to adapt a model using one or multiple source domains to ensure robust performance in unseen target domains. Recently, Parameter-Efficient Fine-Tuni…
FFNet: MetaMixer-based Efficient Convolutional Mixer Design
Seokju Yun, Dongheon Lee, Youngmin Ro
Transformer, composed of self-attention and Feed-Forward Network, has revolutionized the landscape of network design across various vision tasks. While self-attention is extensivel…