Junmo Kim

39

Papers

33

Total Citations

Papers (39)

FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection

Implicit Steganography Beyond the Constraints of Modality

Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective

Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep

Preference Distillation via Value based Reinforcement Learning

ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object

EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning

Rotating Your Face Using Multi-Task Deep Neural Network

Unsupervised Simultaneous Orthogonal Basis Clustering Feature Selection

Deep Saliency With Encoded Low Level Distance Map and High Level Features

A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning

Active Convolution: Learning the Shape of Convolution for Image Classification

Deep Pyramidal Residual Networks

Generating a Fusion Image: One's Identity and Another's Shape

Learning Not to Learn: Training Deep Neural Networks With Biased Data

Continual Learning With Extended Kronecker-Factored Approximate Curvature

Regularization on Spatio-Temporally Smoothed Feature for Action Recognition

Joint Negative and Positive Learning for Noisy Labels

Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement

Fix the Noise: Disentangling Source Feature for Controllable Domain Translation

Reinforcement Learning-Based Black-Box Model Inversion Attacks

Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View

Entropy Minimization for Convex Relaxation Approaches

Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition

NLNL: Negative Learning for Noisy Labels

Improving Generalization of Batch Whitening by Convolutional Unit Optimization

Camera Distortion-Aware 3D Human Pose Estimation in Video With Optimization-Based Meta-Learning

Progressive Seed Generation Auto-Encoder for Unsupervised Point Cloud Learning

Disposable Transfer Learning for Selective Source Task Unlearning

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

Weight Decay Scheduling and Knowledge Distillation for Active Learning

On the Angular Update and Hyperparameter Tuning of a Scale-Invariant Network

DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning

Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization

SynAD: Enhancing Real-World End-to-End Autonomous Driving Models through Synthetic Data Integration

Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation

Constructing Fast Network through Deconstruction of Convolution

UniCLIP: Unified Framework for Contrastive Language-Image Pre-training

NeurIPS 2022arXiv