Kihyuk Sohn

32

Papers

3,206

Total Citations

Papers (32)

Improved Deep Metric Learning with Multi-class N-pair Loss Objective

Language Model Beats Diffusion - Tokenizer is key to visual generation

Photorealistic Video Generation with Diffusion Models

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild

Feature Transfer Learning for Face Recognition With Under-Represented Data

Towards Universal Representation Learning for Deep Face Recognition

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Prefix Conditioning Unifies Language and Label Supervision

Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval

Visual Prompt Tuning for Generative Transfer Learning

MaskSketch: Unpaired Structure-Guided Masked Image Generation

Video Probabilistic Diffusion Models in Projected Latent Space

Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Towards Large-Pose Face Frontalization in the Wild

Domain Adaptation for Structured Output via Discriminative Patch Representations

Improving Face Recognition by Clustering Unlabeled Faces in the Wild

Learning Structured Output Representation using Deep Conditional Generative Models

MAGVIT: Masked Generative Video Transformer

Instruct-Imagen: Image Generation with Multi-modal Instruction

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Improving Object Detection With Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

Learning to Adapt Structured Output Space for Semantic Segmentation

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Controlling Neural Networks with Rule Representations

Object-aware Contrastive Learning for Debiased Scene Representation

StyleDrop: Text-to-Image Synthesis of Any Style

Collaborative Score Distillation for Consistent Visual Editing

Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units