614 citations · 2.5k across the 63 of their papers we have counts for
64 papers
Conditional Score Guidance for Text-Driven Image-to-Image Translation
Hyunsoo Lee, Minsoo Kang, Bohyung Han
We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our method aims to generate a target image by selective…
On the Stability-Plasticity Dilemma of Class-Incremental Learning
Dongwan Kim, Bohyung Han
A primary goal of class-incremental learning is to strike a balance between stability and plasticity, where models should be both stable enough to retain knowledge learned from pre…
Multi-Modal Representation Learning with Text-Driven Soft Masks
Jaeyoo Park, Bohyung Han
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. Fi…
ContraNeRF: 3D-Aware Generative Model via Contrastive Learning with Unsupervised Implicit Pose Embedding
Mijeong Kim, Hyunjoon Lee, Bohyung Han
Although 3D-aware GANs based on neural radiance fields have achieved competitive performance, their applicability is still limited to objects or scenes with the ground-truths or pr…
Randomized Adversarial Style Perturbations for Domain Generalization
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…
Cross-Class Feature Augmentation for Class Incremental Learning
Taehoon Kim, Jaeyoo Park, Bohyung Han
We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the pas…
Variational Distribution Learning for Unsupervised Text-to-Image Generation
Minsoo Kang, Doyup Lee, Jiseob Kim +2
We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generat…
Information-Theoretic GAN Compression with Variational Energy-based Model
Minsoo Kang, Hyewon Yoo, Eunhee Kang +3
We propose an information-theoretic knowledge distillation approach for the compression of generative adversarial networks, which aims to maximize the mutual information between te…
Metric Compatible Training for Online Backfilling in Large-Scale Retrieval
Seonguk Seo, Mustafa Gokhan Uzunbas, Bohyung Han +2
Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computati…
Towards Sequence-Level Training for Visual Tracking
Minji Kim, Seungkwan Lee, Jungseul Ok +2
Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is…
Multi-Level Branched Regularization for Federated Learning
Jinkyu Kim, Geeho Kim, Bohyung Han
A critical challenge of federated learning is data heterogeneity and imbalance across clients, which leads to inconsistency between local networks and unstable convergence of globa…
Pooling Revisited: Your Receptive Field is Suboptimal
Dong-Hwan Jang, Sanghyeok Chu, Joonhyuk Kim +1
The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably. Many components in a ne…
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
Ilchae Jung, Minji Kim, Eunhyeok Park +1
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural netwo…
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
Minsoo Kang, Jaeyoo Park, Bohyung Han
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous ta…
Class-Incremental Learning for Action Recognition in Videos
Jaeyoo Park, Minsoo Kang, Bohyung Han
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continu…
Learning to Adapt to Unseen Abnormal Activities under Weak Supervision
Jaeyoo Park, Junha Kim, Bohyung Han
We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when o…
Learning Semantic Segmentation from Multiple Datasets with Label Shifts
Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh +4
With increasing applications of semantic segmentation, numerous datasets have been proposed in the past few years. Yet labeling remains expensive, thus, it is desirable to jointly…
Information-Theoretic Bias Reduction via Causal View of Spurious Correlation
Seonguk Seo, Joon-Young Lee, Bohyung Han
We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic…
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
Mijeong Kim, Seonguk Seo, Bohyung Han
We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential re…
Learning Debiased and Disentangled Representations for Semantic Segmentation
Sanghyeok Chu, Dongwan Kim, Bohyung Han
Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is parti…
Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform
Myungseo Song, Jinyoung Choi, Bohyung Han
We propose a versatile deep image compression network based on Spatial Feature Transform (SFT arXiv:1804.02815), which takes a source image and a corresponding quality map as input…
Unsupervised Learning of Debiased Representations with Pseudo-Attributes
Seonguk Seo, Joon-Young Lee, Bohyung Han
Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations…
MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
Jinyoung Choi, Bohyung Han
We propose a framework of generative adversarial networks with multiple discriminators, which collaborate to represent a real dataset more effectively. Our approach facilitates lea…
Open-Set Representation Learning through Combinatorial Embedding
Geeho Kim, Junoh Kang, Bohyung Han
Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in ident…