{"total":50,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2204.12511","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","created":"2022-04-26","cited_by_count":63,"area":null},{"id":"2104.08418","title":"FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling","created":"2021-04-17","cited_by_count":47,"area":null},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2103.17220","title":"Scale-aware Automatic Augmentation for Object Detection","created":"2021-03-31","cited_by_count":23,"area":null},{"id":"2103.04507","title":"OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection","created":"2021-03-08","cited_by_count":19,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2204.04654","title":"Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2306.09011","title":"CAD-Estate: Large-scale CAD Model Annotation in RGB Videos","created":"2023-06-15","cited_by_count":14,"area":null},{"id":"2104.00613","title":"The surprising impact of mask-head architecture on novel class segmentation","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2110.13713","title":"YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs","created":"2021-10-26","cited_by_count":12,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2111.07535","title":"T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging","created":"2021-11-15","cited_by_count":11,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9,"area":null},{"id":"2304.12406","title":"AutoFocusFormer: Image Segmentation off the Grid","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2109.01123","title":"Benchmarking the Robustness of Instance Segmentation Models","created":"2021-09-02","cited_by_count":8,"area":null},{"id":"2203.10747","title":"EAutoDet: Efficient Architecture Search for Object Detection","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2110.12423","title":"NAS-FCOS: Efficient Search for Object Detection Architectures","created":"2021-10-24","cited_by_count":6,"area":null},{"id":"2107.03719","title":"Bag of Tricks for Neural Architecture Search","created":"2021-07-08","cited_by_count":4,"area":null},{"id":"2407.12891","title":"Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2109.11874","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2302.06052","title":"CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction","created":"2023-02-13","cited_by_count":3,"area":null},{"id":"2312.14200","title":"Efficient Architecture Search via Bi-level Data Pruning","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2103.12270","title":"Dilated SpineNet for Semantic Segmentation","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2204.02033","title":"Learning to Reduce Information Bottleneck for Object Detection in Aerial Images","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2205.05583","title":"TDT: Teaching Detectors to Track without Fully Annotated Videos","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2304.08107","title":"DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2404.08582","title":"FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2103.09891","title":"The Untapped Potential of Off-the-Shelf Convolutional Neural Networks","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2108.00784","title":"Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling","created":"2021-08-02","cited_by_count":0,"area":null},{"id":"2208.06062","title":"Optimizing Anchor-based Detectors for Autonomous Driving Scenes","created":"2022-08-11","cited_by_count":0,"area":null},{"id":"2210.11725","title":"AROS: Affordance Recognition with One-Shot Human Stances","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2210.14460","title":"PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2407.01012","title":"Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2407.21498","title":"MaskUno: Switch-Split Block For Enhancing Instance Segmentation","created":"2024-07-31","cited_by_count":0,"area":null}],"next_cursor":null}