{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2009.11848","title":"How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks","created":"2020-09-24","cited_by_count":222},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2005.08104","title":"Single-Stage Semantic Segmentation from Image Labels","created":"2020-05-16","cited_by_count":167},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2105.08965","title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","created":"2021-05-19","cited_by_count":127},{"id":"1904.05373","title":"Pixel-Adaptive Convolutional Neural Networks","created":"2019-04-10","cited_by_count":126},{"id":"1803.09569","title":"On Regularized Losses for Weakly-supervised CNN Segmentation","created":"2018-03-26","cited_by_count":121},{"id":"2203.02664","title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","created":"2022-03-05","cited_by_count":118},{"id":"2205.12156","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","created":"2022-05-24","cited_by_count":106},{"id":"1911.08039","title":"Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach","created":"2019-11-19","cited_by_count":88},{"id":"2110.07110","title":"Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast","created":"2021-10-14","cited_by_count":85},{"id":"1906.07510","title":"Attention Guided Graph Convolutional Networks for Relation Extraction","created":"2019-06-18","cited_by_count":82},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2110.06530","title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","created":"2021-10-13","cited_by_count":65},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65},{"id":"2203.09653","title":"Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation","created":"2022-03-17","cited_by_count":64},{"id":"1911.01370","title":"Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation","created":"2019-11-04","cited_by_count":58},{"id":"2203.03860","title":"Weakly Supervised Semantic Segmentation using Out-of-Distribution Data","created":"2022-03-08","cited_by_count":58},{"id":"2204.03206","title":"L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation","created":"2022-04-07","cited_by_count":57},{"id":"2105.04550","title":"Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth","created":"2021-05-10","cited_by_count":55},{"id":"1911.03864","title":"Improving Transformer Models by Reordering their Sublayers","created":"2019-11-10","cited_by_count":52},{"id":"2212.10701","title":"A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks","created":"2022-12-21","cited_by_count":49},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","cited_by_count":39},{"id":"2303.06562","title":"ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond","created":"2023-03-12","cited_by_count":39},{"id":"2209.07761","title":"Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation","created":"2022-09-16","cited_by_count":37},{"id":"2304.14802","title":"ResiDual: Transformer with Dual Residual Connections","created":"2023-04-28","cited_by_count":31},{"id":"2109.03810","title":"Scaled ReLU Matters for Training Vision Transformers","created":"2021-09-08","cited_by_count":29},{"id":"1508.05133","title":"Steps Toward Deep Kernel Methods from Infinite Neural Networks","created":"2015-08-20","cited_by_count":28},{"id":"2212.04744","title":"Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud","created":"2022-12-09","cited_by_count":27},{"id":"2203.10278","title":"Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation","created":"2022-03-19","cited_by_count":21},{"id":"2202.04812","title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","created":"2022-02-10","cited_by_count":19},{"id":"2103.03457","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","created":"2021-03-05","cited_by_count":5}],"next_cursor":null}