CVPR 2021 accepted papers on Learning theory and algorithms
18 of the 1,661 papers accepted at CVPR 2021 (1.1%) are on Learning theory and algorithms, compared with 1.7% at CVPR 2020. They fall into 6 topics.
See CVPR 2021 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Optimal transport · 5 papers
- A Generalized Loss Function for Crowd Counting and Localization (210 citations)
- A Sliced Wasserstein Loss for Neural Texture Synthesis (65 citations)
- Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps (56 citations)
- Hilbert Sinkhorn Divergence for Optimal Transport (9 citations)
- MongeNet: Efficient Sampler for Geometric Deep Learning (2 citations)
Combinatorial and search optimization · 4 papers
- Quantum Permutation Synchronization (37 citations)
- Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-Constrained Optimization (34 citations)
- Consensus Maximisation Using Influences of Monotone Boolean Functions (12 citations)
- Crossing Cuts Polygonal Puzzles: Models and Solvers (4 citations)
Prediction and decision losses · 3 papers
- An Alternative Probabilistic Interpretation of the Huber Loss (182 citations)
- Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach (11 citations)
- Simpler Certified Radius Maximization by Propagating Covariances (5 citations)
Clustering · 3 papers
- COMPLETER: Incomplete Multi-View Clustering via Contrastive Prediction (441 citations)
- Reconsidering Representation Alignment for Multi-View Clustering (227 citations)
- MultiLink: Multi-Class Structure Recovery via Agglomerative Clustering and Model Selection (20 citations)
Sample complexity · 2 papers
- Towards Evaluating and Training Verifiably Robust Neural Networks (14 citations)
- Optimal Quantization Using Scaled Codebook (2 citations)
Matrix and tensor methods · 1 paper
- Adaptive Rank Estimate in Robust Principal Component Analysis (7 citations)
