5 papers
Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun +3
A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-…
SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models
Jiwoo Chung, Sangeek Hyun, MinKyu Lee +5
Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by cac…
Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization
MinKyu Lee, Sangeek Hyun, Woojin Jun +3
This work analyzes the training dynamics of Image Restoration (IR) Transformers and uncovers a critical yet overlooked issue: conventional LayerNorm (LN) drives feature magnitudes…
Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation
Jiwoo Chung, Sangeek Hyun, Hyunjun Kim +3
Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture…
Auto-Encoded Supervision for Perceptual Image Super-Resolution
MinKyu Lee, Sangeek Hyun, Woojin Jun +1
This work tackles the fidelity objective in the perceptual super-resolution~(SR). Specifically, we address the shortcomings of pixel-level loss ($\mathcal{L}_\text{pix…