{"list":"other","total":82,"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"1904.04433","title":"Efficient Decision-based Black-box Adversarial Attacks on Face Recognition","created":"2019-04-09","cited_by_count":175},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101},{"id":"1907.09294","title":"The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations","created":"2019-07-22","cited_by_count":97},{"id":"2210.02025","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","created":"2022-10-05","cited_by_count":87},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66},{"id":"1709.06680","title":"Deep Lattice Networks and Partial Monotonic Functions","created":"2017-09-19","cited_by_count":63},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"2203.14309","title":"DeepDPM: Deep Clustering With an Unknown Number of Clusters","created":"2022-03-27","cited_by_count":52},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35},{"id":"2305.02187","title":"CLUSTSEG: Clustering for Universal Segmentation","created":"2023-05-03","cited_by_count":32},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24},{"id":"1912.05021","title":"Design and Interpretation of Universal Adversarial Patches in Face Detection","created":"2019-11-30","cited_by_count":23},{"id":"2307.14605","title":"Clustering based Point Cloud Representation Learning for 3D Analysis","created":"2023-07-27","cited_by_count":23},{"id":"1803.01449","title":"Deep Continuous Clustering","created":"2018-03-05","cited_by_count":21},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19},{"id":"2008.05678","title":"Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze","created":"2020-08-13","cited_by_count":18},{"id":"1908.03381","title":"Video Face Clustering with Unknown Number of Clusters","created":"2019-08-09","cited_by_count":17},{"id":"2303.10100","title":"Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation","created":"2023-03-17","cited_by_count":16},{"id":"2308.06712","title":"Compositional Feature Augmentation for Unbiased Scene Graph Generation","created":"2023-08-13","cited_by_count":15},{"id":"1501.03084","title":"Deep Learning with Nonparametric Clustering","created":"2015-01-13","cited_by_count":6}],"next_cursor":null}