79 citations · 113 across the 10 of their papers we have counts for
10 papers
Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling
Sanghyeok Chu, Pyunghwan Ahn, Gwangmo Song +3
Sparse Upcycling provides an efficient way to initialize a Mixture-of-Experts (MoE) model from pretrained dense weights instead of training from scratch. However, since all experts…
Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
Youngtaek Oh, Pyunghwan Ahn, Jinhyung Kim +4
Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in l…
ContextMix: A context-aware data augmentation method for industrial visual inspection systems
Hyungmin Kim, Donghun Kim, Pyunghwan Ahn +3
While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These…
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Taehoon Kim, Pyunghwan Ahn, Sangyun Kim +39
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed t…
Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Taehoon Kim, Mark Marsden, Pyunghwan Ahn +4
When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To…
Projection-based Point Convolution for Efficient Point Cloud Segmentation
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi +2
Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processi…
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
Doyeon Kim, Woonghyun Ka, Pyungwhan Ahn +3
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neur…
Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning
Juyoung Yang, Pyunghwan Ahn, Doyeon Kim +2
With the development of 3D scanning technologies, 3D vision tasks have become a popular research area. Owing to the large amount of data acquired by sensors, unsupervised learning…
PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentation
JuYoung Yang, Chanho Lee, Pyunghwan Ahn +3
Following considerable development in 3D scanning technologies, many studies have recently been proposed with various approaches for 3D vision tasks, including some methods that ut…
EDAS: Efficient and Differentiable Architecture Search
Hyeong Gwon Hong, Pyunghwan Ahn, Junmo Kim
Transferrable neural architecture search can be viewed as a binary optimization problem where a single optimal path should be selected among candidate paths in each edge within the…