{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2010.15277","title":"Class-incremental learning: survey and performance evaluation on image classification","created":"2020-10-28","cited_by_count":449},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2103.16788","title":"DER: Dynamically Expandable Representation for Class Incremental Learning","created":"2021-03-31","cited_by_count":355},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"1911.07053","title":"Maintaining Discrimination and Fairness in Class Incremental Learning","created":"2019-11-16","cited_by_count":283},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2004.10956","title":"Few-Shot Class-Incremental Learning","created":"2020-04-23","cited_by_count":251},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209},{"id":"2104.03047","title":"Few-Shot Incremental Learning with Continually Evolved Classifiers","created":"2021-04-07","cited_by_count":187},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2003.12060","title":"Negative Margin Matters: Understanding Margin in Few-shot Classification","created":"2020-03-26","cited_by_count":129},{"id":"2203.06953","title":"Forward Compatible Few-Shot Class-Incremental Learning","created":"2022-03-14","cited_by_count":127},{"id":"2302.03004","title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning","created":"2023-02-06","cited_by_count":116},{"id":"2103.04059","title":"Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning","created":"2021-03-06","cited_by_count":115},{"id":"2004.00713","title":"Memory-Efficient Incremental Learning Through Feature Adaptation","created":"2020-04-01","cited_by_count":107},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2107.08918","title":"Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning","created":"2021-07-19","cited_by_count":96},{"id":"2203.16588","title":"Constrained Few-shot Class-incremental Learning","created":"2022-03-30","cited_by_count":94},{"id":"2003.11652","title":"iTAML: An Incremental Task-Agnostic Meta-learning Approach","created":"2020-03-25","cited_by_count":90},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88},{"id":"2208.00147","title":"Few-Shot Class-Incremental Learning from an Open-Set Perspective","created":"2022-07-30","cited_by_count":84},{"id":"2207.11213","title":"Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay","created":"2022-07-22","cited_by_count":72},{"id":"2006.15524","title":"MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning","created":"2020-06-28","cited_by_count":62},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60},{"id":"2110.07059","title":"Subspace Regularizers for Few-Shot Class Incremental Learning","created":"2021-10-13","cited_by_count":56},{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55},{"id":"2304.00426","title":"Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning","created":"2023-04-02","cited_by_count":55},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2304.08130","title":"A Survey on Few-Shot Class-Incremental Learning","created":"2023-04-17","cited_by_count":48},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46},{"id":"2312.05229","title":"Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration","created":"2023-12-08","cited_by_count":46},{"id":"2210.04524","title":"Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation","created":"2022-10-10","cited_by_count":45},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44},{"id":"2309.13414","title":"State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory","created":"2023-09-23","cited_by_count":39},{"id":"2203.14952","title":"Energy-based Latent Aligner for Incremental Learning","created":"2022-03-28","cited_by_count":37},{"id":"2307.11888","title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","created":"2023-07-21","cited_by_count":36},{"id":"2404.02117","title":"Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners","created":"2024-04-02","cited_by_count":36},{"id":"2403.16536","title":"VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting","created":"2024-03-25","cited_by_count":35},{"id":"2010.08657","title":"Class-incremental Learning with Pre-allocated Fixed Classifiers","created":"2020-10-16","cited_by_count":33},{"id":"2003.08561","title":"XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning","created":"2020-03-19","cited_by_count":31},{"id":"2403.00567","title":"Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning","created":"2024-03-01","cited_by_count":26},{"id":"2403.18550","title":"OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning","created":"2024-03-27","cited_by_count":26},{"id":"2308.06764","title":"Few-shot Class-incremental Learning for Classification and Object Detection: A Survey","created":"2023-08-13","cited_by_count":25},{"id":"2205.13954","title":"Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation","created":"2022-05-27","cited_by_count":22},{"id":"2303.09674","title":"DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection","created":"2023-03-16","cited_by_count":21},{"id":"2104.13614","title":"Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors","created":"2021-04-28","cited_by_count":19},{"id":"2303.04751","title":"Multimodal Parameter-Efficient Few-Shot Class Incremental Learning","created":"2023-03-08","cited_by_count":19},{"id":"2405.17022","title":"Compositional Few-Shot Class-Incremental Learning","created":"2024-05-27","cited_by_count":18},{"id":"2008.06365","title":"An Overview of Deep Learning Architectures in Few-Shot Learning Domain","created":"2020-08-12","cited_by_count":16},{"id":"2111.11672","title":"Few-shot Image Generation with Mixup-based Distance Learning","created":"2021-11-23","cited_by_count":16},{"id":"2404.01628","title":"Learning Equi-angular Representations for Online Continual Learning","created":"2024-04-02","cited_by_count":15},{"id":"2406.05427","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","created":"2024-06-08","cited_by_count":15},{"id":"2308.01746","title":"Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants","created":"2023-08-03","cited_by_count":14},{"id":"2104.02281","title":"Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning","created":"2021-04-06","cited_by_count":11},{"id":"2404.06622","title":"Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers","created":"2024-04-09","cited_by_count":9}],"next_cursor":"100"}