7 citations · 48 across the 69 of their papers we have counts for
14 papers · 1 filter
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
Jayeon Yoo, Dongkwan Lee, Inseop Chung +2
It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have…
Open Domain Generalization with a Single Network by Regularization Exploiting Pre-trained Features
Inseop Chung, KiYoon Yoo, Nojun Kwak
Open Domain Generalization (ODG) is a challenging task as it not only deals with distribution shifts but also category shifts between the source and target datasets. To handle this…
SAVE: Protagonist Diversification with Structure Agnostic Video Editing
Yeji Song, Wonsik Shin, Junsoo Lee +2
Driven by the upsurge progress in text-to-image (T2I) generation models, text-to-video (T2V) generation has experienced a significant advance as well. Accordingly, tasks such as mo…
Fast Sun-aligned Outdoor Scene Relighting based on TensoRF
Yeonjin Chang, Yearim Kim, Seunghyeon Seo +2
In this work, we introduce our method of outdoor scene relighting for Neural Radiance Fields (NeRF) named Sun-aligned Relighting TensoRF (SR-TensoRF). SR-TensoRF offers a lightweig…
SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning
JunHoo Lee, Jayeon Yoo, Nojun Kwak
In this paper, we hypothesize that gradient-based meta-learning (GBML) implicitly suppresses the Hessian along the optimization trajectory in the inner loop. Based on this hypothes…
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…
ConcatPlexer: Additional Dim1 Batching for Faster ViTs
Donghoon Han, Seunghyeon Seo, Donghyeon Jeon +3
Transformers have demonstrated tremendous success not only in the natural language processing (NLP) domain but also the field of computer vision, igniting various creative approach…
Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak
We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection…
Robust Multi-bit Natural Language Watermarking through Invariant Features
KiYoon Yoo, Wonhyuk Ahn, Jiho Jang +1
Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large lang…
FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis
Seunghyeon Seo, Yeonjin Chang, Nojun Kwak
Neural Radiance Field (NeRF) has been a mainstream in novel view synthesis with its remarkable quality of rendered images and simple architecture. Although NeRF has been developed…
AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion
Seungwoo Lee, Chaerin Kong, Donghyeon Jeon +1
Recent advances in diffusion models have showcased promising results in the text-to-video (T2V) synthesis task. However, as these T2V models solely employ text as the guidance, the…
Active Semi-Supervised Learning by Exploring Per-Sample Uncertainty and Consistency
Jaeseung Lim, Jongkeun Na, Nojun Kwak
Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a l…
Analyzing Multimodal Objectives Through the Lens of Generative Diffusion Guidance
Chaerin Kong, Nojun Kwak
Recent years have witnessed astonishing advances in the field of multimodal representation learning, with contrastive learning being the cornerstone for major breakthroughs. Latest…
MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model
Seunghyeon Seo, Jaeyoung Yoo, Jihye Hwang +1
One of the major challenges in multi-person pose estimation is instance-aware keypoint estimation. Previous methods address this problem by leveraging an off-the-shelf detector, he…