08

2021 August

Full List of papers - updated weekly

• GIRAFFE : Representing Scenes as Compositional Generative Neural Feature Fields (진오)
• Closed-From Factorization of Latent Semantics in GANs (진오)
• GANSpace: Discovering Interpretable GAN Controls (진오)
• Contrastive Learning for Unpaired Image to Image Translation (진오)
• Momentum Contrast for Unsupervised Visual Representation Learning (진오)
• Conditonal Gnerative Adversarial Nets (진오)
• Conditional Image Synthesis with Auxiliary Classifier GANs (진오)
• CORAL - Colored structural representation for bi-modal place recognition (강희)
• Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments (강희)
• Semantic Graph Based Place Recognition for 3D Point Clouds (강희)
• HRegNet : A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration (강희)
• NeuroMorph : Unsupervised Shape Interpolation and Correspondence in One Go (강희)
• KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control (강희)
• Unsupervised Learning of Probably Symmetric Deformable 3D objects from Images in the Wild (민국)
• Emerging Properties in Self-Supervised Vision Transformers (민국)
• Omni-GAN: On the Secrets of cGANs and Beyond (민국)
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (민국)
• Denosing Diffusion Probabilistic Models (민국)
• Diffusion Models beat GANs on Image Synthesis (민국)
• Denoising Diffusion Implicit Models (민국)
• cGANs with projection discriminator (민국)
• LOGAN: Latent Optimisation For Generative Adversarial Networks (민국)
• cGANs with Auxiliary Discriminative Classifier (민국)
• Dual Projection Generative Adversarial Networks for Conditional Image Generation (민국)
• CircleGAN: Generative Adversarial Learning across Spherical Circles (민국)
• On the difficulty of training Recurrent Neural Networks (승욱)
• Spatial-Temporal Transformer for Dynamic Scene graph Generation (승욱)
• A Closer Look at Memorization in Deep Networks (승욱)
• An Empirical Study of Training Self-Supervised Vision Transformers (승욱)
• End-to-End Object Detection with Transformers (승욱)
• IDM: An intermediate Domain Module for Domain Adaptive Re-ID (승욱)
• MDETR - Modulated Detection for End-to-End Multi-Modal Understanding (승욱)
• Recurrent Parameter Generators (승욱)
• RobustNet: Improving Domain Generalization in Urban-Scene segmentation via Instance Selective Whitening (승욱)
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification (승욱)
• How to avoid machine learning pitfalls: A guide for academic researchers (승욱)
• How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (승욱)
• Generating Long Sequences with Sparse Transformers (a.k.a Sparse Transformer) (승욱)
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (승욱)
• Relational Embedding for Few-shot Classification (승욱)
• Mobile-Former: Bridging MobileNet and Transformer (승욱)
• Do Vision Transformers See like Convolutional Neural Networks? (승욱)
• FastFormer: Additive Attention is All you need (승욱)
• PonderNet: Learning to ponder (승욱)
• PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers (승욱)
• Deformable DETR: Deformable Transformers for End-to-end Object detection (승욱)
• Co-Attention for Conditioned Image matching (승욱)
• Polygonal Building Extraction by Frame Field Learning (수현)
• Stand-Alone Self-Attention in Vision Models (수현)
• Scaling Local Self-Attention for Parameter Efficient Visual Backbones (수현)
• Where and What ? Examining Interpretable Disentangled Representations (수현)
• PackIt: A virtual Environment for Geometric Planning (수현)
• Non-local Neural Networks (수현)
• FaceNet: A Unified Embedding for Face Recognition and Clustering (수현)
• Sampling Matters in Deep Embedding Learning (수현)
• Wasserstein gan (수현)
• Relational recurrent neural networks (수현)
• A simple neural network module for relational reasoning (수현)
• Relation Networks for Object Detection (수현)
• MLP-Mixer: An all-MLP Architecture for Vision (수현)
• A Unified Objective for Novel Class Discovery (수현)
• Momentum Contrast for Unsupervised Visual Representation Learning (수현)
• Improved Baselines with Momentum Contrastive Learning (수현)
• NeRD: Neural 3D Reflection Symmetry Detector (우현)
• Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations (우현)
• StarGAN v2: Diverse Image Synthesis for Multiple Domains (우현)
• Twin Auxiliary Classifier GAN (우현)
• ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot (우현)
• BIGRoC: Boosting Image Generation via a Robust Classifier (우현)
• End-to-End Object Detection with Transformers (우현)
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization (우현)
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (우현)
• Neural Discrete Representation Learning (우현)
• Pixel Recurrent Neural Networks (우현)
• Few-Shot Unsupervised Image-to-Image Translation (우현)
• Diverse Image Generation via Self-Conditioned GANs (우현)
• Conditional Image Generation with PixelCNN Decoders (우현)
• Auto-Encoding Variational Bayes (우현)
• NICE: Non-linear Independent Components Estimation (우현)
• Density Estimation using RealNVP (우현)
• Group Equivariant Convolutional Networks (우현)
• Steerable CNNs (우현)
• Learning to Diversify for Single Domain Generalization (우현)
• Transforming Auto-Encoder (우현)
• Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis (윤우)
• Variational Inference with Normalizing flows (지예)
• E(n) equivariant normalizing flow (지예)
• Deep clustering for unsupervised learning of visual features (DeepCluster) (지예)
• Guiding Deep Molecular Optimization with Genetic Exploration (지예)
• Augmenting Genetic algorithms with deep neural networks for exploring the chemical space (지예)
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (SWaV) (지예)
• Strategies for pre-training graph neural networks (지예)