主动学习(Active Learning)领域部分经典论文汇总

只简单找了一小部分

---

CVPR

• [link] [code] [Ensemble] [18]
  The Power of Ensembles for Active Learning in Image Classification

• [link] [code] [LLAL] [19]
  Learning Loss for Active Learning

• [link] [code] [SRAAL] [20]
  State-Relabeling Adversarial Active Learning

• [link] [code] [AL-FK] [20]
  Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision

• [link] [code] [TA-VAAL] [21]
  Task-Aware Variational Adversarial Active Learning

• [link] [code] [MI-AOD] [21]
  Multiple Instance Active Learning for Object Detection

• [link] [code] [AL-GCN] [21]
  Sequential Graph Convolutional Network for Active Learning

• [link] [code] [VaB-AL] [21]
  VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning

• [link] [code] [TQS] [21]
  Transferable Query Selection for Active Domain Adaptation

• [link] [code] [EAL] [22]
  Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint

• [link] [code] [Alpha-MIX] [22]
  Active Learning by Feature Mixing

• [link] [code] [BoostMIS] [22]
  BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

• [link] [code] [RIPU] [22]
  Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation

• [link] [code] [A-Teacher] [22]
  Active Teacher for Semi-Supervised Object Detection

• [link] [code] [SV] [22]
  Sequential Voting With Relational Box Fields for Active Object Detection

• [link] [code] [*] [22]
  Towards Robust and Reproducible Active Learning Using Neural Networks

• [link] [code] [blog] [SDM] [22]
  Learning Distinctive Margin Toward Active Domain Adaptation

---

ICCV

• [link] [code] [VAAL] [19]
  Variational Adversarial Active Learning

• [link] [code] [AL-OD] [19]
  Active Learning for Deep Detection Neural Networks

• [link] [code] [ISAL] [21]
  Influence Selection for Active Learning

• [link] [code] [S3VAADA] [21]
  S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

• [link] [code] [AUDA] [21]
  Active Universal Domain Adaptation

• [link] [code] [CLUE] [21]
  Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

• [link] [code] [SSL-AL] [21]
  Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels

• [link] [code] [TOD] [21]
  Semi-Supervised Active Learning With Temporal Output Discrepancy

• [link] [code] [MADA] [21]
  Multi-Anchor Active Domain Adaptation for Semantic Segmentation

• [link] [code] [AL-MDN] [21]
  Active Learning for Deep Object Detection via Probabilistic Modeling

• [link] [code] [HD-AMOT] [23]
  Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking

• [link] [code] [HAL3D] [23]
  HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling

• [link] [code] [HPAL] [23]
  Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation

• [link] [code] [TiDAL] [23]
  TiDAL: Learning Training Dynamics for Active Learning

• [link] [code] [ALWOD] [23]
  ALWOD: Active Learning for Weakly-Supervised Object Detection

• [link] [code] [KAFAL] [23]
  Knowledge-Aware Federated Active Learning with Non-IID Data

• [link] [code] [Superpixel] [23]
  Adaptive Superpixel for Active Learning in Semantic Segmentation

• [link] [code] [SeedAL] [23]
  You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation

---

ECCV

• [link] [code] [CDAL] [20]
  Contextual Diversity for Active Learning

• [link] [code] [C-AL-SSL] [20]
  Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

• [link] [code] [ASAL] [20]
  Attend and Segment: Attention Guided Active Semantic Segmentation

• [link] [code] [DAAL] [20]
  Dual Adversarial Network for Deep Active Learning

• [link] [code] [WD-KD-AL] [20]
  Weight Decay Scheduling and Knowledge Distillation for Active Learning

---

AAAI

• [link] [code] [Watchdog] [18]
  Active Lifelong Learning with Watchdog

• [link] [code] [SPAL] [19]
  Self-Paced Active Learning: Query the Right Thing at the Right Time

• [link] [code] [AS-OS] [19]
  Active Sampling for Open-Set Classification without Initial Annotation

• [link] [code] [AGB] [20]
  Cost-Accuracy Aware Adaptive Labeling for Active Learning

• [link] [code] [NCE-Net] [21]
  Nearest Neighbor Classifier Embedded Network for Active Learning

• [link] [code] [U-AL] [21]
  Unsupervised Active Learning via Subspace Learning

• [link] [code] [ADS] [21]
  Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment

• [link] [code] [TrustAL] [22]
  TrustAL: Trustworthy Active Learning using Knowledge Distillation

• [link] [code] [AL-GradNorm] [22]
  Boosting Active Learning via Improving Test Performance

• [link] [code] [EADA] [22]
  Active Learning for Domain Adaptation: An Energy-Based Approach

---

MICCAI

• [link] [code] [SA] [17]
  Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation

• [link] [code] [ASA] [20]
  Attention, Suggestion and Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation

• [link] [code] [DRLA] [20]
  Deep Reinforcement Active Learning for Medical Image Classification

• [link] [code] [ACC] [21]
  Annotation-Efficient Cell Counting

• [link] [code] [PSL-AL] [21]
  Partial-supervised Learning for Vessel Segmentation in Ocular Images

---

ICLR

• [link] [code] [CoreSet] [18]
  Active Learning for Convolutional Neural Networks: A Core-Set Approach

• [link] [code] [BADGE] [20]
  Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

---

WACV

• [link] [code] [AADA] [20]
  Active Adversarial Domain Adaptation

• [link] [code] [IL-AD] [20]
  Active Learning for Imbalanced Datasets

• [link] [code] [ASAL] [20]
  Adversarial Sampling for Active Learning

• [link] [code] [CBAL] [22]
  Class-Balanced Active Learning for Image Classification

• [link] [code] [IWPS] [22]
  Identifying Wrongly Predicted Samples: A Method for Active Learning

• [link] [code] [ALS4GAN] [22]
  Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images

---

ACCV

• [link] [code] [DEAL] [20]
  DEAL: Difficulty-aware Active Learning for Semantic Segmentation

---

arXiv

• [link] [code] [A-SSL] [22]
  Semantic Segmentation with Active Semi-Supervised Learning