CVPR 2022, Representation Learning paper 리스트

 

CVPR에서 2022년 공개된 Representation Learning paper 리스트 공유합니다.

CVPR 2022에서 공개된 모든 논문은 아래 페이지에 링크되어 있습니다. 

 

 

https://openaccess.thecvf.com/CVPR2022?day=all 

CVPR 2022 Open Access Repository

 

https://docs.google.com/spreadsheets/d/1ilb2Wqea0uVKxlJsdJHR-3IVaWeqsWyk2M2aGmYVAPE/edit#gid=1112752087

CVPR 2022 Session Schedule

 

2022년 CVPR Paper List
Representation Learning 

Oral session

Masked Autoencoders Are Scalable Vision Learners

Learning ABCs: Approximate Bijective Correspondence for Isolating Factors of Variation With Weak Supervision

Bayesian Invariant Risk Minimization

Crafting Better Contrastive Views for Siamese Representation Learning

Rethinking Minimal Sufficient Representation in Contrastive Learning

Multi-Level Feature Learning for Contrastive Multi-View Clustering

Point-Level Region Contrast for Object Detection Pre-Training

Class-Incremental Learning by Knowledge Distillation With Adaptive Feature Consolidation

A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration

SLIC: Self-Supervised Learning With Iterative Clustering for Human Action Videos

Omnivore: A Single Model for Many Visual Modalities

DPICT: Deep Progressive Image Compression Using Trit-Planes

Efficient Geometry-Aware 3D Generative Adversarial Networks

Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation

Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning

Versatile Multi-Modal Pre-Training for Human-Centric Perception

Bridging Video-Text Retrieval With Multiple Choice Questions

Integrating Language Guidance Into Vision-Based Deep Metric Learning

 

 

 

Poster session

Unified Contrastive Learning in Image-Text-Label Space

AlignMixup: Improving Representations by Interpolating Aligned Features

On the Road to Online Adaptation for Semantic Image Segmentation

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

Kernelized Few-Shot Object Detection With Efficient Integral Aggregation

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

A Structured Dictionary Perspective on Implicit Neural Representations

LARGE: Latent-Based Regression Through GAN Semantics

Rethinking Controllable Variational Autoencoders

Learning Canonical F-Correlation Projection for Compact Multiview Representation

Cross-Architecture Self-Supervised Video Representation Learning

Improving Video Model Transfer With Dynamic Representation Learning

Self-Supervised Image Representation Learning With Geometric Set Consistency

HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging

Point-BERT: Pre-Training 3D Point Cloud Transformers With Masked Point Modeling

DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds

Neural Convolutional Surfaces

Representing 3D Shapes With Probabilistic Directed Distance Fields

H4D: Human 4D Modeling by Learning Neural Compositional Representation

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

Contrastive Regression for Domain Adaptation on Gaze Estimation

Forward Compatible Training for Large-Scale Embedding Retrieval Systems

Improving Subgraph Recognition With Variational Graph Information Bottleneck

Learning Soft Estimator of Keypoint Scale and Orientation With Probabilistic Covariant Loss

Few-Shot Keypoint Detection With Uncertainty Learning for Unseen Species

 

그외 다른 세션이지만,
Representation 키워드가 포함된 것이
 생각보다 많았습니다..

약 2000개의 논문 중 120개가 representation 키워드가 포함되어 있었습니다. 

 

Do Learned Representations Respect Causal Relationships?

SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization

NeuralHDHair: Automatic High-Fidelity Hair Modeling From a Single Image Using Implicit Neural Representations

Local Texture Estimator for Implicit Representation Function

Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution

Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection

TransRank: Self-Supervised Video Representation Learning via Ranking-Based Transformation Recognition

Slot-VPS: Object-Centric Representation Learning for Video Panoptic Segmentation

Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

Advancing High-Resolution Video-Language Representation With Large-Scale Video Transcriptions

SphereSR: 360° Image Super-Resolution With Arbitrary Projection via Continuous Spherical Image Representation

Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations

HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

ShapeFormer: Transformer-Based Shape Completion via Sparse Representation

Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction

BNV-Fusion: Dense 3D Reconstruction Using Bi-Level Neural Volume Fusion

Representation Compensation Networks for Continual Semantic Segmentation

BatchFormer: Learning To Explore Sample Relationships for Robust Representation Learning

Causality Inspired Representation Learning for Domain Generalization

Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks

Patch-Level Representation Learning for Self-Supervised Vision Transformers

Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

Towards Discriminative Representation: Multi-View Trajectory Contrastive Learning for Online Multi-Object Tracking

Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery

Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning

Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning

Motion-Aware Contrastive Video Representation Learning via Foreground-Background Merging

Hierarchical Self-Supervised Representation Learning for Movie Understanding

Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning

FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks

Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations

Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Motion-Adjustable Neural Implicit Video Representation

Neural Architecture Search With Representation Mutual Information

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation

Interspace Pruning: Using Adaptive Filter Representations To Improve Training of Sparse CNNs

GIFS: Neural Implicit Function for General Shape Representation

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

FoggyStereo: Stereo Matching With Fog Volume Representation

...

...