{"list":"other","total":66,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2110.00218","title":"On the Importance of Gradients for Detecting Distributional Shifts in the Wild","created":"2021-10-01","cited_by_count":339},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2304.10517","title":"Segment Anything Model for Medical Image Analysis: an Experimental Study","created":"2023-04-20","cited_by_count":291},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146},{"id":"1801.03454","title":"Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks","created":"2018-01-10","cited_by_count":129},{"id":"1711.09856","title":"On the Robustness of Semantic Segmentation Models to Adversarial Attacks","created":"2017-11-27","cited_by_count":126},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96},{"id":"1807.09685","title":"Grounding Visual Explanations","created":"2018-07-25","cited_by_count":93},{"id":"1903.11816","title":"FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation","created":"2019-03-28","cited_by_count":70},{"id":"2004.07769","title":"SCOUT: Self-aware Discriminant Counterfactual Explanations","created":"2020-04-16","cited_by_count":52},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45},{"id":"2212.02774","title":"Adaptive Testing of Computer Vision Models","created":"2022-12-06","cited_by_count":39},{"id":"2302.07865","title":"Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation","created":"2023-02-15","cited_by_count":35},{"id":"2307.12730","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","created":"2023-07-24","cited_by_count":34},{"id":"2303.17096","title":"ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing","created":"2023-03-30","cited_by_count":30},{"id":"2308.06725","title":"CLE Diffusion: Controllable Light Enhancement Diffusion Model","created":"2023-08-13","cited_by_count":30},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28},{"id":"2309.07944","title":"Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach","created":"2023-09-14","cited_by_count":28},{"id":"2303.15441","title":"Zero-shot Model Diagnosis","created":"2023-03-27","cited_by_count":23},{"id":"2108.00968","title":"Robust Semantic Segmentation with Superpixel-Mix","created":"2021-08-02","cited_by_count":19},{"id":"2303.11298","title":"Reliability in Semantic Segmentation: Are We on the Right Track?","created":"2023-03-20","cited_by_count":16},{"id":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","cited_by_count":10},{"id":"2307.00648","title":"Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization","created":"2023-07-02","cited_by_count":8},{"id":"2310.02988","title":"Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples","created":"2023-10-04","cited_by_count":5}],"next_cursor":null}