{"list":"other","total":62,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2004.09666","title":"Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images","created":"2020-04-20","cited_by_count":745},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2011.08939","title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","created":"2020-11-17","cited_by_count":478},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"1801.05401","title":"Low-Shot Learning from Imaginary Data","created":"2018-01-16","cited_by_count":181},{"id":"2009.11169","title":"Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks","created":"2020-09-23","cited_by_count":178},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"id":"2107.13048","title":"Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks","created":"2021-07-27","cited_by_count":124},{"id":"1606.02185","title":"Towards a Neural Statistician","created":"2016-06-07","cited_by_count":121},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"2010.10241","title":"BYOL works even without batch statistics","created":"2020-10-20","cited_by_count":95},{"id":"2006.13932","title":"Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary","created":"2020-06-24","cited_by_count":89},{"id":"2001.01599","title":"Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images","created":"2020-01-06","cited_by_count":81},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66},{"id":"2103.10626","title":"Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification","created":"2021-03-19","cited_by_count":65},{"id":"2206.01794","title":"Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology","created":"2022-06-03","cited_by_count":58},{"id":"1707.02610","title":"Few-Shot Learning Through an Information Retrieval Lens","created":"2017-07-09","cited_by_count":51},{"id":"1507.02592","title":"Fast rates in statistical and online learning","created":"2015-07-09","cited_by_count":47},{"id":"2209.15007","title":"Understanding Collapse in Non-Contrastive Siamese Representation Learning","created":"2022-09-29","cited_by_count":42},{"id":"2111.01556","title":"Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging","created":"2021-11-01","cited_by_count":31},{"id":"1709.00340","title":"Fine-grained Visual-textual Representation Learning","created":"2017-08-31","cited_by_count":27},{"id":"1512.08756","title":"Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems","created":"2015-12-29","cited_by_count":23},{"id":"2206.00092","title":"FHIST: A Benchmark for Few-shot Classification of Histological Images","created":"2022-05-31","cited_by_count":20},{"id":"2002.08483","title":"Strength from Weakness: Fast Learning Using Weak Supervision","created":"2020-02-19","cited_by_count":18},{"id":"2202.09059","title":"Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning","created":"2022-02-18","cited_by_count":16}],"next_cursor":null}