Search Results for author: TaeHoon Kim

Found 15 papers, 7 papers with code

A 0.65-pJ/bit 3.6-TB/s/mm I/O Interface with XTalk Minimizing Affine Signaling for Next-Generation HBM with High Interconnect Density

no code implementations8 Apr 2024 Hyunjun Park, Jiwon Shin, Hanseok Kim, Jihee Kim, Haengbeom Shin, TaeHoon Kim, Jung-Hun Park, Woo-Seok Choi

This paper presents an I/O interface with Xtalk Minimizing Affine Signaling (XMAS), which is designed to support high-speed data transmission in die-to-die communication over silicon interposers or similar high-density interconnects susceptible to crosstalk.

OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation

no code implementations18 Mar 2024 Seungbeom Woo, Geonwoo Baek, TaeHoon Kim, Jaemin Na, Joong-won Hwang, Wonjun Hwang

This framework dynamically cycles through multiple target domains, aligning each domain individually to restrain the biased alignment problem, and utilizes Fisher information to minimize the forgetting of knowledge from previous target domains.

Domain Adaptation Multi-target Domain Adaptation +1

D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection

1 code implementation CVPR 2024 Dinh Phat Do, TaeHoon Kim, Jaemin Na, Jiwon Kim, Keonho Lee, Kyunghwan Cho, Wonjun Hwang

However, there are limited studies on adapting from the visible to the thermal domain, because the domain gap between the visible and thermal domains is much larger than expected, and traditional domain adaptation can not successfully facilitate learning in this situation.

Domain Adaptation object-detection +1

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection

no code implementations CVPR 2024 Jongwook Choi, TaeHoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi

This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos.

Contrastive Learning DeepFake Detection +1

Cross-Class Feature Augmentation for Class Incremental Learning

no code implementations4 Apr 2023 TaeHoon Kim, Jaeyoo Park, Bohyung Han

The proposed approach has a unique perspective to utilize the previous knowledge in class incremental learning since it augments features of arbitrary target classes using examples in other classes via adversarial attacks on a previously learned classifier.

Class Incremental Learning Incremental Learning +1

Randomized Adversarial Style Perturbations for Domain Generalization

no code implementations4 Apr 2023 TaeHoon Kim, Bohyung Han

We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP), which is motivated by the observation that the characteristics of each domain are captured by the feature statistics corresponding to style.

Domain Generalization

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

1 code implementation13 Nov 2022 TaeHoon Kim, Mark Marsden, Pyunghwan Ahn, Sangyun Kim, Sihaeng Lee, Alessandra Sala, Seung Hwan Kim

However, we find that large-scale bidirectional training between image and text enables zero-shot image captioning.

Image Captioning Keyword Extraction

Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution

1 code implementation15 Mar 2022 Jinsu Yoo, TaeHoon Kim, Sihaeng Lee, Seung Hwan Kim, Honglak Lee, Tae Hyun Kim

Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods.

Image Restoration Super-Resolution

FrostNet: Towards Quantization-Aware Network Architecture Search

1 code implementation17 Jun 2020 Taehoon Kim, Youngjoon Yoo, Jihoon Yang

In this paper, we present a new network architecture search (NAS) procedure to find a network that guarantees both full-precision (FLOAT32) and quantized (INT8) performances.

Object Detection Quantization +1

Abstractive Text Classification Using Sequence-to-convolution Neural Networks

1 code implementation20 May 2018 Taehoon Kim, Jihoon Yang

Seq2CNN is trained end-to-end to classify various-length texts without preprocessing inputs into fixed length.

Data Augmentation General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.