15 papers
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
Dongyeun Lee, Amir Zandieh, Vahab Mirrokni +2
Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundame…
Learning Neural Deformation Representation for 4D Dynamic Shape Generation
Gyojin Han, Jiwan Hur, Jaehyun Choi +1
Recent developments in 3D shape representation opened new possibilities for generating detailed 3D shapes. Despite these advances, there are few studies dealing with the generation…
Inlier-Centric Post-Training Quantization for Object Detection Models
Minsu Kim, Dongyeun Lee, Jaemyung Yu +3
Object detection is pivotal in computer vision, yet its immense computational demands make deployment slow and power-hungry, motivating quantization. However, task-irrelevant morph…
Frequency-Aware Token Reduction for Efficient Vision Transformer
Dong-Jae Lee, Jiwan Hur, Jaehyun Choi +2
Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a s…
SynAD: Enhancing Real-World End-to-End Autonomous Driving Models through Synthetic Data Integration
Jongsuk Kim, Jaeyoung Lee, Gyojin Han +3
Recent advancements in deep learning and the availability of high-quality real-world driving datasets have propelled end-to-end autonomous driving. Despite this progress, relying s…
B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
Changho Choi, Youngwoo Shin, Gyojin Han +2
Understanding dynamic outdoor environments requires capturing complex object interactions and their evolution over time. LiDAR-based 4D point clouds provide precise spatial geometr…
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
Dongyeun Lee, Jiwan Hur, Hyounguk Shon +2
Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained enviro…
DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
Jaehyun Choi, Gyojin Han, Dong-Jae Lee +2
Dataset Condensation (DC) has emerged as a promising solution to mitigate the computational and storage burdens associated with training deep learning models. However, existing DC…
PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion
Jaehyun Choi, Jiwan Hur, Gyojin Han +2
Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence be…
Self-supervised Transformation Learning for Equivariant Representations
Jaemyung Yu, Jaehyun Choi, Dong-Jae Lee +2
Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations l…
AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation
Jaehyun Choi, Junwon Ko, Dong-Jae Lee +1
Open compound domain adaptation (OCDA) is a practical domain adaptation problem that consists of a source domain, target compound domain, and unseen open domain. In this problem, t…
Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency
Woonghyun Ka, Jae Young Lee, Jaehyun Choi +1
In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth net…
Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep
Jae Young Lee, Woonghyun Ka, Jaehyun Choi +1
We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learn…
Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective
HyeongGwon Hong, Yooshin Cho, Hanbyel Cho +2
Gradient inversion attacks can leak data privacy when clients share weight updates with the server in federated learning (FL). Existing studies mainly use L2 or cosine distance as…
Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning
Jiwan Hur, Jaehyun Choi, Gyojin Han +2
Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream t…