{"total":62,"rows":[{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2102.12129","title":"Self-Domain Adaptation for Face Anti-Spoofing","created":"2021-02-24","cited_by_count":49,"area":null},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2102.07432","title":"Fast and accurate optimization on the orthogonal manifold without retraction","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35,"area":null},{"id":"2202.07052","title":"Orthogonalising gradients to speed up neural network optimisation","created":"2022-02-14","cited_by_count":27,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2103.04243","title":"Estimating and Improving Fairness with Adversarial Learning","created":"2021-03-07","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2302.08210","title":"A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold","created":"2023-02-16","cited_by_count":21,"area":null},{"id":"2109.11338","title":"Orthogonal Graph Neural Networks","created":"2021-09-23","cited_by_count":19,"area":null},{"id":"2410.22135","title":"Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation","created":"2024-10-29","cited_by_count":17,"area":null},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2208.09932","title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","created":"2022-08-21","cited_by_count":14,"area":null},{"id":"2303.09261","title":"Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2110.08774","title":"Nonlinear Transform Induced Tensor Nuclear Norm for Tensor Completion","created":"2021-10-17","cited_by_count":13,"area":null},{"id":"2104.08490","title":"Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations","created":"2021-04-17","cited_by_count":12,"area":null},{"id":"2204.11418","title":"Riemannian Hamiltonian methods for min-max optimization on manifolds","created":"2022-04-25","cited_by_count":12,"area":null},{"id":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2209.14778","title":"Batch Normalization Explained","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2105.09109","title":"An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks","created":"2021-05-19","cited_by_count":7,"area":null},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7,"area":"moe"},{"id":"2108.00051","title":"Coordinate descent on the orthogonal group for recurrent neural network training","created":"2021-07-30","cited_by_count":5,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2102.12139","title":"Interpreting the Latent Space of Generative Adversarial Networks using Supervised Learning","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2106.07916","title":"Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2106.10704","title":"Better Training using Weight-Constrained Stochastic Dynamics","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2207.02119","title":"Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2303.05066","title":"Distortion-Disentangled Contrastive Learning","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2103.06583","title":"Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2111.03628","title":"Exploiting a Zoo of Checkpoints for Unseen Tasks","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2208.01358","title":"What can we Learn by Predicting Accuracy?","created":"2022-08-02","cited_by_count":3,"area":null},{"id":"2301.03844","title":"Look Beyond Bias with Entropic Adversarial Data Augmentation","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2306.09939","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2509.21464","title":"Residual Vector Quantization For Communication-Efficient Multi-Agent Perception","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2206.10562","title":"Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth","created":"2022-06-21","cited_by_count":2,"area":null},{"id":"2206.13130","title":"Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search","created":"2022-06-27","cited_by_count":2,"area":"distill"},{"id":"2406.16453","title":"Learning in Wilson-Cowan model for metapopulation","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2102.06186","title":"Quadric Hypersurface Intersection for Manifold Learning in Feature Space","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2112.14796","title":"Deep Learning meets Liveness Detection: Recent Advancements and Challenges","created":"2021-12-29","cited_by_count":1,"area":null},{"id":"2203.16772","title":"Learning Decoupling Features Through Orthogonality Regularization","created":"2022-03-31","cited_by_count":1,"area":null},{"id":"2207.09350","title":"Riemannian Stochastic Gradient Method for Nested Composition Optimization","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2211.08408","title":"On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2507.06650","title":"Deep Disentangled Representation Network for Treatment Effect Estimation","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2601.09185","title":"OrthoGeoLoRA: Geometric Parameter-Efficient Fine-Tuning for Structured Social Science Concept Retrieval on theWeb","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2603.19788","title":"Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2103.05385","title":"NaroNet: Discovery of tumor microenvironment elements from highly multiplexed images","created":"2021-03-09","cited_by_count":0,"area":null},{"id":"2104.08147","title":"Uncertainty Surrogates for Deep Learning","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2109.01731","title":"Acceleration Method for Learning Fine-Layered Optical Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2110.00216","title":"Beyond Neighbourhood-Preserving Transformations for Quantization-Based Unsupervised Hashing","created":"2021-10-01","cited_by_count":0,"area":null},{"id":"2112.03667","title":"Cross-domain User Preference Learning for Cold-start Recommendation","created":"2021-12-07","cited_by_count":0,"area":null},{"id":"2211.13902","title":"TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2306.07015","title":"Combining Primal and Dual Representations in Deep Restricted Kernel Machines Classifiers","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2402.18605","title":"FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2511.14282","title":"Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2601.04019","title":"Modeling Behavioral Patterns in News Recommendations Using Fuzzy Neural Networks","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2605.02838","title":"A second-order method landing on the Stiefel manifold via Newton$\\unicode{x2013}$Schulz iteration","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.28573","title":"Efficient Pre-Training of LLMs through Truncated SVD Representations","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}