{"list":"other","total":67,"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":"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"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":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264},{"id":"1511.02680","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","created":"2015-11-09","cited_by_count":218},{"id":"2111.09805","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","created":"2021-11-18","cited_by_count":166},{"id":"1811.10200","title":"IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments","created":"2018-11-26","cited_by_count":163},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"2003.02977","title":"Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder","created":"2020-03-06","cited_by_count":145},{"id":"2012.06575","title":"Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation","created":"2020-12-09","cited_by_count":133},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67},{"id":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"1910.04443","title":"Misbehaviour Prediction for Autonomous Driving Systems","created":"2019-10-10","cited_by_count":55},{"id":"2211.14512","title":"Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation","created":"2022-11-26","cited_by_count":55},{"id":"1811.00648","title":"Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities","created":"2018-11-01","cited_by_count":54},{"id":"1908.01098","title":"Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift","created":"2019-08-03","cited_by_count":54},{"id":"2301.03407","title":"On Advantages of Mask-level Recognition for Outlier-aware Segmentation","created":"2023-01-09","cited_by_count":42},{"id":"2208.13930","title":"SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection","created":"2022-08-29","cited_by_count":33},{"id":"2101.01364","title":"Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends","created":"2021-01-05","cited_by_count":26},{"id":"2312.09231","title":"Reliability in Semantic Segmentation: Can We Use Synthetic Data?","created":"2023-12-14","cited_by_count":24},{"id":"1908.05569","title":"Entropic Out-of-Distribution Detection","created":"2019-08-15","cited_by_count":21},{"id":"2309.04573","title":"Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation","created":"2023-09-08","cited_by_count":18},{"id":"2309.15065","title":"Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding","created":"2023-09-26","cited_by_count":15},{"id":"2312.05538","title":"CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen","created":"2023-12-09","cited_by_count":15},{"id":"2406.11835","title":"OoDIS: Anomaly Instance Segmentation and Detection Benchmark","created":"2024-06-17","cited_by_count":8},{"id":"2006.08613","title":"Self-Supervised Domain Mismatch Estimation for Autonomous Perception","created":"2020-06-15","cited_by_count":7},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7},{"id":"2408.11221","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","created":"2024-08-20","cited_by_count":5},{"id":"2411.03829","title":"Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts","created":"2024-11-06","cited_by_count":5},{"id":"2309.13475","title":"Detecting and Mitigating System-Level Anomalies of Vision-Based Controllers","created":"2023-09-23","cited_by_count":4},{"id":"2405.10350","title":"Monitizer: Automating Design and Evaluation of Neural Network Monitors","created":"2024-05-16","cited_by_count":2}],"next_cursor":null}