{"list":"other","total":75,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"2107.12028","title":"Parametric Contrastive Learning","created":"2021-07-26","cited_by_count":217},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"2001.01536","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","created":"2020-01-06","cited_by_count":175},{"id":"2012.00321","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","created":"2020-12-01","cited_by_count":172},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2207.09052","title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","created":"2022-07-19","cited_by_count":144},{"id":"2103.14267","title":"Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification","created":"2021-03-26","cited_by_count":130},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"2112.00412","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","created":"2021-12-01","cited_by_count":100},{"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":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96},{"id":"2107.09249","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","created":"2021-07-20","cited_by_count":95},{"id":"2104.03066","title":"Distributional Robustness Loss for Long-tail Learning","created":"2021-04-07","cited_by_count":84},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75},{"id":"2305.11733","title":"Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment","created":"2023-05-19","cited_by_count":75},{"id":"2103.15042","title":"Distilling Virtual Examples for Long-tailed Recognition","created":"2021-03-28","cited_by_count":72},{"id":"2210.01033","title":"LPT: Long-tailed Prompt Tuning for Image Classification","created":"2022-10-03","cited_by_count":69},{"id":"2111.13579","title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","created":"2021-11-26","cited_by_count":65},{"id":"2203.15359","title":"Nested Collaborative Learning for Long-Tailed Visual Recognition","created":"2022-03-29","cited_by_count":63},{"id":"2309.10019","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","created":"2023-09-18","cited_by_count":58},{"id":"2104.00885","title":"Adaptive Class Suppression Loss for Long-Tail Object Detection","created":"2021-04-02","cited_by_count":55},{"id":"2111.14745","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","created":"2021-11-29","cited_by_count":49},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46},{"id":"2303.13664","title":"Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data","created":"2023-03-23","cited_by_count":44},{"id":"2310.18236","title":"How Re-sampling Helps for Long-Tail Learning?","created":"2023-10-27","cited_by_count":36},{"id":"2304.01457","title":"Exploring Vision-Language Models for Imbalanced Learning","created":"2023-04-04","cited_by_count":35},{"id":"2212.02015","title":"Learning Imbalanced Data with Vision Transformers","created":"2022-12-05","cited_by_count":34},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34},{"id":"2104.06094","title":"Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition","created":"2021-04-13","cited_by_count":33},{"id":"2302.05499","title":"CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition","created":"2023-02-10","cited_by_count":30},{"id":"2304.05173","title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","created":"2023-04-11","cited_by_count":20},{"id":"2305.01160","title":"Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels","created":"2023-05-02","cited_by_count":16},{"id":"2305.04536","title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","created":"2023-05-08","cited_by_count":15},{"id":"2406.00345","title":"DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection","created":"2024-06-01","cited_by_count":14},{"id":"2304.09426","title":"Decoupled Training for Long-Tailed Classification With Stochastic Representations","created":"2023-04-19","cited_by_count":13},{"id":"2305.18732","title":"Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition","created":"2023-05-30","cited_by_count":11},{"id":"2410.15980","title":"Learning from Neighbors: Category Extrapolation for Long-Tail Learning","created":"2024-10-21","cited_by_count":9},{"id":"2308.12522","title":"Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognition","created":"2023-08-24","cited_by_count":3}],"next_cursor":null}