{"list":"other","total":56,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"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":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"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":"1709.03410","title":"One-Shot Learning for Semantic Segmentation","created":"2017-09-11","cited_by_count":337},{"id":"1903.03096","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","created":"2019-03-07","cited_by_count":315},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201},{"id":"1909.13140","title":"Feature Weighting and Boosting for Few-Shot Segmentation","created":"2019-09-28","cited_by_count":189},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114},{"id":"2003.13193","title":"Adversarial Feature Hallucination Networks for Few-Shot Learning","created":"2020-03-30","cited_by_count":110},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93},{"id":"2107.00358","title":"Cross-domain Few-shot Learning with Task-specific Adapters","created":"2021-07-01","cited_by_count":80},{"id":"2103.15402","title":"Mining Latent Classes for Few-shot Segmentation","created":"2021-03-29","cited_by_count":69},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56},{"id":"2108.02958","title":"Learning Meta-class Memory for Few-Shot Semantic Segmentation","created":"2021-08-06","cited_by_count":56},{"id":"2206.06122","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","created":"2022-06-13","cited_by_count":50},{"id":"2301.12246","title":"A Closer Look at Few-shot Classification Again","created":"2023-01-28","cited_by_count":46},{"id":"2204.02681","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","created":"2022-04-06","cited_by_count":33},{"id":"2311.02239","title":"Using DUCK-Net for Polyp Image Segmentation","created":"2023-11-03","cited_by_count":31},{"id":"2401.08407","title":"Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining","created":"2024-01-16","cited_by_count":30},{"id":"2211.08681","title":"Interclass Prototype Relation for Few-Shot Segmentation","created":"2022-11-16","cited_by_count":25},{"id":"2109.05749","title":"Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning","created":"2021-09-13","cited_by_count":19},{"id":"2308.07539","title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","created":"2023-08-15","cited_by_count":19},{"id":"2311.14671","title":"SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation","created":"2023-11-24","cited_by_count":19},{"id":"2111.09957","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","created":"2021-11-18","cited_by_count":11},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7},{"id":"1805.00138","title":"Semantic Binary Segmentation using Convolutional Networks without Decoders","created":"2018-05-01","cited_by_count":3},{"id":"2304.05832","title":"Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges","created":"2023-04-12","cited_by_count":3},{"id":"1905.04307","title":"Semantic Segmentation of Seismic Images","created":"2019-05-10","cited_by_count":2}],"next_cursor":null}