{"list":"other","total":81,"rows":[{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1902.09063","title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","created":"2019-02-25","cited_by_count":373},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"1608.00853","title":"A study of the effect of JPG compression on adversarial images","created":"2016-08-02","cited_by_count":197},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"2304.04709","title":"Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection","created":"2023-04-10","cited_by_count":100},{"id":"2304.10261","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","created":"2023-04-19","cited_by_count":92},{"id":"2012.11207","title":"On Success and Simplicity: A Second Look at Transferable Targeted Attacks","created":"2020-12-21","cited_by_count":89},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84},{"id":"2201.12296","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","created":"2022-01-28","cited_by_count":80},{"id":"2303.13336","title":"A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI","created":"2023-03-23","cited_by_count":68},{"id":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61},{"id":"2007.06189","title":"Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations","created":"2020-07-13","cited_by_count":59},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57},{"id":"2304.11332","title":"Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model","created":"2023-04-22","cited_by_count":56},{"id":"2010.03630","title":"Revisiting Batch Normalization for Improving Corruption Robustness","created":"2020-10-07","cited_by_count":55},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45},{"id":"2111.10659","title":"Are Vision Transformers Robust to Patch Perturbations?","created":"2021-11-20","cited_by_count":39},{"id":"2303.17297","title":"Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving","created":"2023-03-30","cited_by_count":37},{"id":"2110.06513","title":"Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions","created":"2021-10-13","cited_by_count":34},{"id":"2211.09383","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":34},{"id":"2305.00278","title":"Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected","created":"2023-04-29","cited_by_count":34},{"id":"2108.06765","title":"Occlusion-Aware Video Object Inpainting","created":"2021-08-15","cited_by_count":30},{"id":"2304.13410","title":"Improving Adversarial Transferability via Intermediate-level Perturbation Decay","created":"2023-04-26","cited_by_count":29},{"id":"2010.03300","title":"CD-UAP: Class Discriminative Universal Adversarial Perturbation","created":"2020-10-07","cited_by_count":27},{"id":"2104.12378","title":"Delving into Data: Effectively Substitute Training for Black-box Attack","created":"2021-04-26","cited_by_count":27},{"id":"1610.08871","title":"Detecting People in Artwork with CNNs","created":"2016-10-27","cited_by_count":25},{"id":"2305.16220","title":"On the Robustness of Segment Anything","created":"2023-05-25","cited_by_count":25},{"id":"2305.06422","title":"An Empirical Study on the Robustness of the Segment Anything Model (SAM)","created":"2023-05-10","cited_by_count":23},{"id":"1908.06566","title":"Adversarial Defense by Suppressing High-frequency Components","created":"2019-08-19","cited_by_count":22},{"id":"2304.01950","title":"MP-FedCL: Multiprototype Federated Contrastive Learning for Edge Intelligence","created":"2023-04-01","cited_by_count":20},{"id":"1609.03057","title":"Style-Transfer via Texture-Synthesis","created":"2016-09-10","cited_by_count":17},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17},{"id":"2103.03438","title":"Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack","created":"2021-03-05","cited_by_count":15},{"id":"2311.11465","title":"Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape","created":"2023-06-03","cited_by_count":10},{"id":"2306.02094","title":"Segment Anything Meets Semantic Communication","created":"2023-06-03","cited_by_count":8},{"id":"2301.11912","title":"OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks","created":"2023-01-27","cited_by_count":5},{"id":"2304.11779","title":"Now You See Me: Robust approach to Partial Occlusions","created":"2023-04-24","cited_by_count":2},{"id":"2102.10534","title":"The Effects of Image Distribution and Task on Adversarial Robustness","created":"2021-02-21","cited_by_count":1},{"id":"2303.01309","title":"BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition","created":"2023-03-02","cited_by_count":1}],"next_cursor":null}