Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

弱监督和无监督定位任务的基于框的细化

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

多样化的协同训练打造强大的半监督分割器

Late Stopping: Avoiding Confidently Learning from Mislabeled Examples

迟到：避免从贴错标签的例子中自信地学习

Ponder: Point Cloud Pre-Training via Neural Rendering

思考：通过神经渲染进行点云预训练

Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning

用于自监督视觉表示学习的语义一致特征搜索

Stable and Causal Inference for Discriminative Self-Supervised Deep Visual Representations

判别性自我监督深度视觉表示的稳定因果推理

Towards Semi-Supervised Learning with Non-Random Missing Labels

走向具有非随机缺失标签的半监督学习

Hallucination Improves the Performance of Unsupervised Visual Representation Learning

幻觉提高了无监督视觉表征学习的性能

Audiovisual Masked Autoencoders

视听屏蔽自动编码器

Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning

缩小课堂空间以增强半监督学习的确定性

Logic-Induced Diagnostic Reasoning for Semi-Supervised Semantic Segmentation

半监督语义分割的逻辑诱导诊断推理

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

GasMono：室内场景的几何辅助自监督单目深度估计

Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training

你需要的只是模仿吗？ 通过双阶段训练进行广义决策

All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reduction

All4One：通过自注意力和减少冗余进行共生邻居对比学习

Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning

无标签跟踪：通过对比相似性学习进行无监督多对象跟踪

Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need

主动自我监督学习：你只需要一些低成本的关系

Diffusion Models as Masked Autoencoders

作为屏蔽自动编码器的扩散模型

Enhanced Meta Label Correction for Coping with Label Corruption

增强元标签更正以应对标签损坏

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-Supervised Learning

随机量化：数据无关自监督学习的通用增强

Prototypes-Oriented Transductive Few-Shot Learning with Conditional Transport

具有条件传输的面向原型的转导式小样本学习

Pseudo-Label Alignment for Semi-Supervised Instance Segmentation

用于半监督实例分割的伪标签对齐

Pixel-Wise Contrastive Distillation

逐像素对比蒸馏

Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization

利用群体智慧实现熵最小化的开放集测试时间适应

Semi-Supervised Learning via Weight-Aware Distillation under Class Distribution Mismatch

类别分布不匹配下通过权重感知蒸馏的半监督学习

Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts

用于协变量和标签偏移下测试时间适应的标签偏移适配器

SimMatchV2: Semi-Supervised Learning with Graph Consistency

SimMatchV2：具有图一致性的半监督学习

Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples

在没有源样本的情况下使用域自适应对抗性扰动对深度视觉模型进行无监督精度估计

Learning by Sorting: Self-Supervised Learning with Group Ordering Constraints

通过排序学习：具有组排序约束的自监督学习

L-DAWA: Layer-Wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning

L-DAWA：联合自监督视觉表示学习中的分层发散感知权重聚合

Class-Relation Knowledge Distillation for Novel Class Discovery

用于新类发现的类关系知识蒸馏

Representation Uncertainty in Self-Supervised Learning as Variational Inference

作为变分推理的自监督学习中的表示不确定性

Point-TTA: Test-Time Adaptation for Point Cloud Registration using Multitask Meta-Auxiliary Learning

Point-TTA：使用多任务元辅助学习进行点云注册的测试时适应

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

基于自蒸馏的表示学习的自适应相似性引导

Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

使用语义聚类进行点对比预测，用于点云视频的自监督学习

Time does Tell: Self-Supervised Time-Tuning of Dense Image Representations

时间确实会告诉我们：密集图像表示的自监督时间调整

To Adapt or not to Adapt? Real-Time Adaptation for Semantic Segmentation

适应还是不适应？ 语义分割的实时适应

MixBag: Bag-Level Data Augmentation for Learning from Label Proportions

MixBag：用于从标签比例中学习的袋级数据增强

Masked Spatio-Temporal Structure Prediction for Self-Supervised Learning on Point Cloud Videos

用于点云视频自监督学习的屏蔽时空结构预测

Parametric Classification for Generalized Category Discovery: A Baseline Study

广义类别发现的参数分类：基线研究

Object-Centric Multiple Object Tracking

以对象为中心的多对象跟踪

Learning Semi-Supervised Gaussian Mixture Models for Generalized Category Discovery

学习用于广义类别发现的半监督高斯混合模型

Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-Point Supervision

具有单点监督的 3D 实例分割的多实例图协作传播

Semantics Meets Temporal Correspondence: Self-Supervised Object-Centric Learning in Videos

语义与时间对应：视频中的自我监督的以对象为中心的学习

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

基于代理锚的无监督学习用于持续广义类别发现

DreamTeacher: Pretraining Image Backbones with Deep Generative Models

DreamTeacher：使用深度生成模型预训练图像主干

MATE: Masked Autoencoders are Online 3D Test-Time Learners

MATE：屏蔽自动编码器是在线 3D 测试时间学习者

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

PADDLES：相位幅度谱解开早期停止，用于带噪声标签的学习

Calibrating Uncertainty for Semi-Supervised Crowd Counting

校准半监督人群计数的不确定性

Test Time Adaptation for Blind Image Quality Assessment

盲图像质量评估的测试时间调整