11 citations · 21 across the 8 of their papers we have counts for
9 papers
Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
Hyeonwoo Cho, Donghyeon Baek, Yewon Kim +1
Recent advancements in Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks, yet the quadratic computational complexity arising from t…
GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
Hyunju Lee, Youngmin Oh, Jeimin Jeon +2
Transformer architecture search (TAS) aims to automatically discover efficient vision transformers (ViTs), reducing the need for manual design. Existing TAS methods typically train…
Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
Jeimin Jeon, Youngmin Oh, Junghyup Lee +4
N-shot neural architecture search (NAS) exploits a supernet containing all candidate subnets for a given search space. The subnets are typically trained with a static training stra…
FYI: Flip Your Images for Dataset Distillation
Byunggwan Son, Youngmin Oh, Donghyeon Baek +1
Dataset distillation synthesizes a small set of images from a large-scale real dataset such that synthetic and real images share similar behavioral properties (e.g, distributions o…
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration
Hyekang Park, Jongyoun Noh, Youngmin Oh +2
We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based metho…
ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
Youngmin Oh, Donghyeon Baek, Bumsub Ham
We address the problem of incremental semantic segmentation (ISS) recognizing novel object/stuff categories continually without forgetting previous ones that have been learned. The…
Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
Donghyeon Baek, Youngmin Oh, Sanghoon Lee +2
Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes…
OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Sanghoon Lee, Youngmin Oh, Donghyeon Baek +2
We address the task of person search, that is, localizing and re-identifying query persons from a set of raw scene images. Recent approaches are typically built upon OIMNet, a pion…
Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation
Donghyeon Baek, Youngmin Oh, Bumsub Ham
We address the problem of generalized zero-shot semantic segmentation (GZS3) predicting pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative…