CVPR 2022 accepted papers on Learning theory and algorithms
27 of the 2,077 papers accepted at CVPR 2022 (1.3%) are on Learning theory and algorithms, compared with 1.1% at CVPR 2021. They fall into 7 topics.
See CVPR 2022 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
Clustering · 9 papers
- Multi-Level Feature Learning for Contrastive Multi-View Clustering (388 citations)
- Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase (85 citations)
- DeepDPM: Deep Clustering With an Unknown Number of Clusters (75 citations)
- Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes (60 citations)
- GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation (19 citations)
- MPC: Multi-View Probabilistic Clustering (12 citations)
- RAMA: A Rapid Multicut Algorithm on GPU (7 citations)
- A Sampling-Based Approach for Efficient Clustering in Large Datasets (5 citations)
- The Flag Median and FlagIRLS (4 citations)
Prediction and decision losses · 7 papers
- Deep Unlearning via Randomized Conditionally Independent Hessians (60 citations)
- One Loss for Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching (50 citations)
- Towards Robust and Reproducible Active Learning Using Neural Networks (43 citations)
- Towards Better Understanding Attribution Methods (36 citations)
- How Much More Data Do I Need? Estimating Requirements for Downstream Tasks (24 citations)
- Pushing the Envelope of Gradient Boosting Forests via Globally-Optimized Oblique Trees (15 citations)
- A Unified Framework for Implicit Sinkhorn Differentiation (9 citations)
Combinatorial and search optimization · 4 papers
- Learning To Solve Hard Minimal Problems (30 citations)
- A Hybrid Quantum-Classical Algorithm for Robust Fitting (28 citations)
- Optimizing Elimination Templates by Greedy Parameter Search (10 citations)
- FastDOG: Fast Discrete Optimization on GPU (7 citations)
Matrix and tensor methods · 3 papers
- Moving Window Regression: A Novel Approach to Ordinal Regression (92 citations)
- Non-Iterative Recovery From Nonlinear Observations Using Generative Models (9 citations)
- Fast, Accurate and Memory-Efficient Partial Permutation Synchronization (5 citations)
Optimal transport · 2 papers
- Bending Graphs: Hierarchical Shape Matching Using Gated Optimal Transport (19 citations)
- Computing Wasserstein-p Distance Between Images With Linear Cost (7 citations)
Fairness · 1 paper
- Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers (36 citations)
Sample complexity · 1 paper
- Maximum Consensus by Weighted Influences of Monotone Boolean Functions (6 citations)
