{"list":"other","total":65,"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"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":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"1803.08533","title":"Understanding Measures of Uncertainty for Adversarial Example Detection","created":"2018-03-22","cited_by_count":177},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"1811.11553","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","created":"2018-11-28","cited_by_count":143},{"id":"2011.11156","title":"Better Aggregation in Test-Time Augmentation","created":"2020-11-23","cited_by_count":122},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118},{"id":"2106.11230","title":"Can contrastive learning avoid shortcut solutions?","created":"2021-06-21","cited_by_count":114},{"id":"1602.03616","title":"Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks","created":"2016-02-11","cited_by_count":106},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2005.11295","title":"From ImageNet to Image Classification: Contextualizing Progress on Benchmarks","created":"2020-05-22","cited_by_count":90},{"id":"2002.11102","title":"On Feature Normalization and Data Augmentation","created":"2020-02-25","cited_by_count":71},{"id":"2002.09103","title":"Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation","created":"2020-02-21","cited_by_count":61},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"2010.11422","title":"Learning Loss for Test-Time Augmentation","created":"2020-10-22","cited_by_count":56},{"id":"1909.11515","title":"Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks","created":"2019-09-25","cited_by_count":54},{"id":"2003.00425","title":"Learning When and Where to Zoom with Deep Reinforcement Learning","created":"2020-03-01","cited_by_count":43},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39},{"id":"2208.11695","title":"Bugs in the Data: How ImageNet Misrepresents Biodiversity","created":"2022-08-24","cited_by_count":24},{"id":"1505.03229","title":"APAC: Augmented PAttern Classification with Neural Networks","created":"2015-05-13","cited_by_count":23},{"id":"2109.11071","title":"Learning to Downsample for Segmentation of Ultra-High Resolution Images","created":"2021-09-22","cited_by_count":19},{"id":"2106.02694","title":"Efficient Classification of Very Large Images with Tiny Objects","created":"2021-06-04","cited_by_count":17},{"id":"2006.09373","title":"The shape and simplicity biases of adversarially robust ImageNet-trained CNNs","created":"2020-06-16","cited_by_count":14},{"id":"2006.16705","title":"Classification Confidence Estimation with Test-Time Data-Augmentation","created":"2020-06-30","cited_by_count":12},{"id":"2303.15390","title":"Learning to Zoom and Unzoom","created":"2023-03-27","cited_by_count":11},{"id":"2102.11731","title":"Rethinking Natural Adversarial Examples for Classification Models","created":"2021-02-23","cited_by_count":9},{"id":"2108.10992","title":"OOWL500: Overcoming Dataset Collection Bias in the Wild","created":"2021-08-24","cited_by_count":2},{"id":"1912.07160","title":"DAmageNet: A Universal Adversarial Dataset","created":"2019-12-16","cited_by_count":1}],"next_cursor":null}