AAAI 2025 accepted papers on Label-efficient and robust learning
394 of the 3,486 papers accepted at AAAI 2025 (11.3%) are on Label-efficient and robust learning, compared with 13.9% at AAAI 2024. They fall into 9 topics.
See AAAI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Recognition and long-tail · 197 papers
- SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery (56 citations)
- Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition (38 citations)
- DAMMFND: Domain-Aware Multimodal Multi-view Fake News Detection (26 citations)
- Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixing (23 citations)
- Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification (21 citations)
- Augmenting Sequential Recommendation with Balanced Relevance and Diversity (20 citations)
- AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (13 citations)
- Enhancing Multi-View Classification Reliability with Adaptive Rejection (13 citations)
- Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning (12 citations)
- Motif-Oriented Representation Learning with Topology Refinement for Drug-Drug Interaction Prediction (12 citations)
- Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech Deepfakes (12 citations)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (12 citations)
and 185 more in the interactive map.
Domain adaptation and generalization · 51 papers
- HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation (33 citations)
- FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation (29 citations)
- AIF-SFDA: Autonomous Information Filter Driven Source-Free Domain Adaptation for Medical Image Segmentation (18 citations)
- DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation (18 citations)
- MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning (17 citations)
- Drawing Informative Gradients from Sources: A One-stage Transfer Learning Framework for Cross-city Spatiotemporal Forecasting (10 citations)
- Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation (10 citations)
- Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning (8 citations)
- Improving Generalization for AI-Synthesized Voice Detection (7 citations)
- SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learning (7 citations)
- Dynamic Target Distribution Estimation for Source-Free Open-Set Domain Adaptation (6 citations)
- Knowledge-Guided Domain Adaptation Model for Transferring Drug Response Prediction from Cell Lines to Patients (6 citations)
and 39 more in the interactive map.
Self-supervised and contrastive · 27 papers
- Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking (14 citations)
- Multi-aspect Self-guided Deep Information Bottleneck for Multi-modal Clustering (9 citations)
- Self-supervised Trusted Contrastive Multi-view Clustering with Uncertainty Refined (9 citations)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (8 citations)
- mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design (6 citations)
- DualNet: Robust Self-Supervised Stereo Matching with Pseudo-Label Supervision (5 citations)
- Enhancing Contrastive Learning Inspired by the Philosophy of “The Blind Men and the Elephant” (4 citations)
- Accounting for Spatial Variability with the Histogram of Oriented Gradients Based Masking Improves Performance of Masked Autoencoder over Hyperspectral Satellite Imagery (Student Abstract) (3 citations)
- AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images (3 citations)
- EMPLACE: Self-Supervised Urban Scene Change Detection (3 citations)
- ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting (3 citations)
- Can Generative Models Improve Self-Supervised Representation Learning? (2 citations)
and 15 more in the interactive map.
Semi-supervised learning · 25 papers
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (11 citations)
- Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis (9 citations)
- Semi-Supervised Multi-View Multi-Label Learning with View-Specific Transformer and Enhanced Pseudo-Label (9 citations)
- Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation (8 citations)
- RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning (7 citations)
- Relaxed Class-consensus Consistency for Semi-supervised Semantic Segmentation (7 citations)
- SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization (7 citations)
- Semi-Supervised Online Cross-Modal Hashing (6 citations)
- Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation (4 citations)
- Anatomical Knowledge Mining and Matching for Semi-supervised Medical Multi-structure Detection (3 citations)
- Open-world Radio Frequency Fingerprint Identification via Augmented Semi-supervised Learning (3 citations)
- Probability-Density-aware Semi-supervised Learning (3 citations)
and 13 more in the interactive map.
Knowledge distillation · 24 papers
- Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition (23 citations)
- Unlocking the Potential of Reverse Distillation for Anomaly Detection (17 citations)
- Uncertainty-aware Knowledge Tracing (12 citations)
- DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection (10 citations)
- Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization (10 citations)
- Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias (6 citations)
- Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation (6 citations)
- Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration (6 citations)
- A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models (5 citations)
- Adaptive Dual Guidance Knowledge Distillation (5 citations)
- Debiased Distillation for Consistency Regularization (5 citations)
- MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities (5 citations)
and 12 more in the interactive map.
OOD and anomaly detection · 21 papers
- CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection (18 citations)
- Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning (15 citations)
- Early Concept Drift Detection via Prediction Uncertainty (15 citations)
- Qsco: A Quantum Scoring Module for Open-Set Supervised Anomaly Detection (8 citations)
- Disentangling Tabular Data Towards Better One-Class Anomaly Detection (5 citations)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (5 citations)
- Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection (5 citations)
- ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection (4 citations)
- Unsupervised Anomaly Detection for Tabular Data Using Deep Noise Evaluation (4 citations)
- Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion (4 citations)
- Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail (3 citations)
- ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection (3 citations)
and 9 more in the interactive map.
Noisy labels · 21 papers
- Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels (17 citations)
- Calibrated Disambiguation for Partial Multi-label Learning (8 citations)
- Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction (8 citations)
- Optimized Gradient Clipping for Noisy Label Learning (6 citations)
- Distribution-Consistency-Guided Multi-modal Hashing (5 citations)
- Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled Yet Hard-to-Learn Samples in Noisy Data (5 citations)
- Noisy Label Calibration for Multi-View Classification (5 citations)
- Revisiting Interpolation for Noisy Label Correction (5 citations)
- Robust Logit Adjustment for Learning with Long-Tailed Noisy Data (5 citations)
- RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise (5 citations)
- TSVC: Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval (4 citations)
- Combating Semantic Contamination in Learning with Label Noise (3 citations)
and 9 more in the interactive map.
Test-time adaptation · 14 papers
- Bridging the Gap for Test-Time Multimodal Sentiment Analysis (12 citations)
- Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation (7 citations)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (5 citations)
- A Layer Selection Approach to Test Time Adaptation (4 citations)
- Attention Bootstrapping for Multi-Modal Test-Time Adaptation (4 citations)
- Fully Test-time Adaptation for Tabular Data (4 citations)
- Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers (4 citations)
- Online Fraud Detection via Test-Time Retrieval-Based Representation Enrichment (3 citations)
- PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation (3 citations)
- Test-Time Adaptation on Noisy Data via Model-Pruning-Based Filtering and Flatness-Aware Entropy Minimization (3 citations)
- COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism (2 citations)
- Efficient Deformable Convolutional Prompt for Continual Test-Time Adaptation in Medical Image Segmentation (2 citations)
and 2 more in the interactive map.
Zero-/few-shot and meta-learning · 14 papers
- MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context (9 citations)
- Few-Shot Fine-Grained Image Classification with Progressively Feature Refinement and Continuous Relationship Modeling (5 citations)
- ZeroHAR: Sensor Context Augments Zero-Shot Wearable Action Recognition (4 citations)
- Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer (3 citations)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning (3 citations)
- Fair Training with Zero Inputs (2 citations)
- Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning (2 citations)
- TNCSE: Tensor Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings (2 citations)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (1 citation)
- EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation (1 citation)
- Manhattan Self-Attention Diffusion Residual Networks with Dynamic Bias Rectification for BCI-based Few-Shot Learning (1 citation)
- Consistency of Compositional Generalization Across Multiple Levels
and 2 more in the interactive map.