{"list":"other","total":66,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"2010.15327","title":"Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth","created":"2020-10-29","cited_by_count":245},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141},{"id":"2204.07305","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","created":"2022-04-15","cited_by_count":126},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2002.03206","title":"Characterizing Structural Regularities of Labeled Data in Overparameterized Models","created":"2020-02-08","cited_by_count":93},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72},{"id":"1707.09870","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","created":"2017-07-24","cited_by_count":61},{"id":"1705.08280","title":"How hard can it be? Estimating the difficulty of visual search in an image","created":"2017-05-23","cited_by_count":52},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41},{"id":"2309.14356","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","created":"2023-09-23","cited_by_count":39},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35},{"id":"1706.06969","title":"Comparing deep neural networks against humans: object recognition when the signal gets weaker","created":"2017-06-21","cited_by_count":34},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20},{"id":"1803.09588","title":"Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy","created":"2018-03-26","cited_by_count":14},{"id":"1909.10818","title":"Constrained deep neural network architecture search for IoT devices accounting hardware calibration","created":"2019-09-24","cited_by_count":6},{"id":"2404.05981","title":"A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics","created":"2024-04-09","cited_by_count":4},{"id":"2308.13057","title":"Data-Side Efficiencies for Lightweight Convolutional Neural Networks","created":"2023-08-24","cited_by_count":3},{"id":"2410.11233","title":"Representation Similarity: A Better Guidance of DNN Layer Sharing for Edge Computing without Training","created":"2024-10-15","cited_by_count":2}],"next_cursor":null}