Computer Vision - ECCV 2022

Fast Two-View Motion Segmentation Using Christoffel Polynomials.- UCTNet: Uncertainty-Aware Cross-Modal Transformer Network for Indoor RGB-D Semantic Segmentation.- Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation.- Learning Regional Purity for Instance Segmentation on 3D Point Clouds.- Cross-Domain Few-Shot Semantic Segmentation.- Generative Subgraph Contrast for Self-Supervised Graph Representation Learning.- SdAE: Self-Distillated Masked Autoencoder.- Demystifying Unsupervised Semantic Correspondence Estimation.- Open-Set Semi-Supervised Object Detection.- Vibration-Based Uncertainty Estimation for Learning from Limited Supervision.- Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation.- Weakly Supervised Object Localization through Inter-class Feature Similarity and Intra-Class Appearance Consistency.- Active Learning Strategies for Weakly-Supervised Object Detection.- Mc-BEiT: Multi-Choice Discretization for Image BERT Pre-training.- Bootstrapped Masked Autoencoders for Vision BERT Pretraining.- Unsupervised Visual Representation Learning by Synchronous Momentum Grouping.- Improving Few-Shot Part Segmentation Using Coarse Supervision.- What to Hide from Your Students: Attention-Guided Masked Image Modeling.- Pointly-Supervised Panoptic Segmentation.- MVP: Multimodality-Guided Visual Pre-training.- Locally Varying Distance Transform for Unsupervised Visual Anomaly Detection.- HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation.- SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation.- Dual-Domain Self-Supervised Learning and Model Adaption for Deep Compressive Imaging.- Unsupervised Selective Labeling for More Effective Semi-Supervised Learning.- Max Pooling with Vision Transformers Reconciles Class and Shape in Weakly Supervised Semantic Segmentation.- Dense Siamese Network for Dense Unsupervised Learning.- Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation.- CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation.- Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization.- RDA: Reciprocal Distribution Alignment for Robust Semi-Supervised Learning.- MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation.- United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning.- Synergistic Self-Supervised and Quantization Learning.- Semi-Supervised Vision Transformers.- Domain Adaptive Video Segmentation via Temporal Pseudo Supervision.- Diverse Learner: Exploring Diverse Supervision for Semi-SupervisedObject Detection.- A Closer Look at Invariances in Self-Supervised Pre-training for 3D Vision.- ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization.- FedX: Unsupervised Federated Learning with Cross Knowledge Distillation.- W2N: Switching from Weak Supervision to Noisy Supervision for Object Detection.- Decoupled Adversarial Contrastive Learning for Self-Supervised Adversarial Robustness.