{"total":183,"rows":[{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351,"area":null},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152,"area":null},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300,"area":null},{"id":"2104.01893","title":"Adaptive Prototype Learning and Allocation for Few-Shot Segmentation","created":"2021-04-05","cited_by_count":207,"area":null},{"id":"2204.13132","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","created":"2022-04-27","cited_by_count":164,"area":null},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152,"area":null},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142,"area":null},{"id":"2112.05140","title":"NeRF for Outdoor Scene Relighting","created":"2021-12-09","cited_by_count":114,"area":null},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102,"area":null},{"id":"2304.03266","title":"Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes","created":"2023-04-06","cited_by_count":90,"area":null},{"id":"2103.11298","title":"Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors","created":"2021-03-21","cited_by_count":82,"area":null},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2204.01446","title":"WildNet: Learning Domain Generalized Semantic Segmentation from the Wild","created":"2022-04-04","cited_by_count":76,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65,"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":"2205.04903","title":"Learning Non-target Knowledge for Few-shot Semantic Segmentation","created":"2022-05-10","cited_by_count":57,"area":null},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55,"area":null},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54,"area":"mllm"},{"id":"2308.06954","title":"Global Features are All You Need for Image Retrieval and Reranking","created":"2023-08-14","cited_by_count":41,"area":null},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39,"area":null},{"id":"2203.08566","title":"EDTER: Edge Detection with Transformer","created":"2022-03-16","cited_by_count":36,"area":null},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35,"area":null},{"id":"2306.04557","title":"PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2103.03891","title":"LOHO: Latent Optimization of Hairstyles via Orthogonalization","created":"2021-03-05","cited_by_count":30,"area":null},{"id":"2206.13199","title":"MGNet: Monocular Geometric Scene Understanding for Autonomous Driving","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2408.09702","title":"Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering","created":"2024-08-19","cited_by_count":27,"area":"diffusion"},{"id":"2108.06337","title":"Dual Path Learning for Domain Adaptation of Semantic Segmentation","created":"2021-08-13","cited_by_count":26,"area":null},{"id":"2304.13615","title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","created":"2023-04-26","cited_by_count":26,"area":null},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25,"area":null},{"id":"2211.10754","title":"HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities","created":"2022-11-19","cited_by_count":25,"area":null},{"id":"2305.04208","title":"Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network","created":"2023-05-07","cited_by_count":21,"area":null},{"id":"2109.12265","title":"Label-Assemble: Leveraging Multiple Datasets with Partial Labels","created":"2021-09-25","cited_by_count":20,"area":null},{"id":"2207.06104","title":"Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification","created":"2022-07-13","cited_by_count":20,"area":null},{"id":"2312.02021","title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","created":"2023-12-04","cited_by_count":20,"area":"mllm"},{"id":"2109.11071","title":"Learning to Downsample for Segmentation of Ultra-High Resolution Images","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2105.03830","title":"Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior","created":"2021-05-09","cited_by_count":18,"area":null},{"id":"2305.16580","title":"TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection","created":"2023-05-26","cited_by_count":18,"area":null},{"id":"2203.08881","title":"Hyperbolic Uncertainty Aware Semantic Segmentation","created":"2022-03-16","cited_by_count":17,"area":null},{"id":"2111.13280","title":"Efficient Self-Ensemble for Semantic Segmentation","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2112.11685","title":"Cost Aggregation Is All You Need for Few-Shot Segmentation","created":"2021-12-22","cited_by_count":16,"area":null},{"id":"2203.10730","title":"Semantic Segmentation with Active Semi-Supervised Learning","created":"2022-03-21","cited_by_count":16,"area":null},{"id":"2106.15287","title":"Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2106.01629","title":"Semantic Palette: Guiding Scene Generation with Class Proportions","created":"2021-06-03","cited_by_count":14,"area":null},{"id":"2110.02871","title":"ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods","created":"2021-10-06","cited_by_count":14,"area":null},{"id":"2309.05192","title":"Towards Viewpoint Robustness in Bird's Eye View Segmentation","created":"2023-09-11","cited_by_count":13,"area":null},{"id":"2312.14733","title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts","created":"2023-12-22","cited_by_count":13,"area":"diffusion"},{"id":"2104.08717","title":"Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses","created":"2021-04-18","cited_by_count":12,"area":null},{"id":"2110.12385","title":"Perceptual Consistency in Video Segmentation","created":"2021-10-24","cited_by_count":12,"area":null},{"id":"2111.02333","title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","created":"2021-11-03","cited_by_count":12,"area":null},{"id":"2405.00250","title":"SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations","created":"2024-04-30","cited_by_count":12,"area":null},{"id":"2209.01327","title":"Semi-Supervised Semantic Segmentation with Cross Teacher Training","created":"2022-09-03","cited_by_count":11,"area":null},{"id":"2312.06474","title":"Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation","created":"2023-12-11","cited_by_count":11,"area":null},{"id":"2110.14759","title":"Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2203.09594","title":"Delta Distillation for Efficient Video Processing","created":"2022-03-17","cited_by_count":10,"area":"distill"},{"id":"2309.10815","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes","created":"2023-09-19","cited_by_count":10,"area":null},{"id":"2102.02771","title":"Mask Guided Attention For Fine-Grained Patchy Image Classification","created":"2021-02-04","cited_by_count":9,"area":null},{"id":"2104.10412","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2112.07146","title":"PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2212.11123","title":"THMA: Tencent HD Map AI System for Creating HD Map Annotations","created":"2022-12-14","cited_by_count":9,"area":null},{"id":"2303.01573","title":"DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2303.06209","title":"SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2306.01980","title":"Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2403.16788","title":"HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2503.14537","title":"Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey","created":"2025-03-17","cited_by_count":9,"area":"driving"},{"id":"2201.02260","title":"CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials","created":"2022-01-06","cited_by_count":8,"area":null},{"id":"2203.10528","title":"Stochastic Video Prediction with Structure and Motion","created":"2022-03-20","cited_by_count":8,"area":null},{"id":"2212.00787","title":"Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion","created":"2022-12-01","cited_by_count":8,"area":null},{"id":"2501.02763","title":"LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2104.04606","title":"RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes","created":"2021-04-09","cited_by_count":7,"area":null},{"id":"2108.11128","title":"Semantic Scene Segmentation for Robotics Applications","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2108.13702","title":"SemIE: Semantically-aware Image Extrapolation","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2109.13432","title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2111.04949","title":"A Survey and Empirical Evaluation of Parallel Deep Learning Frameworks","created":"2021-11-09","cited_by_count":7,"area":null},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2301.02393","title":"Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation","created":"2023-01-06","cited_by_count":7,"area":null},{"id":"2401.15741","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","created":"2024-01-28","cited_by_count":7,"area":null},{"id":"2406.14255","title":"DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2407.12395","title":"Efficient Depth-Guided Urban View Synthesis","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2103.10858","title":"Toward Compact Deep Neural Networks via Energy-Aware Pruning","created":"2021-03-19","cited_by_count":6,"area":null},{"id":"2106.13974","title":"Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images","created":"2021-06-26","cited_by_count":6,"area":null},{"id":"2110.09267","title":"Boosting Image Outpainting with Semantic Layout Prediction","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2201.04019","title":"Pyramid Fusion Transformer for Semantic Segmentation","created":"2022-01-11","cited_by_count":6,"area":null},{"id":"2206.14098","title":"RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2309.00460","title":"dacl10k: Benchmark for Semantic Bridge Damage Segmentation","created":"2023-09-01","cited_by_count":6,"area":null},{"id":"2409.15107","title":"The BRAVO Semantic Segmentation Challenge Results in UNCV2024","created":"2024-09-23","cited_by_count":6,"area":null},{"id":"2112.05351","title":"Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2112.06596","title":"SAC-GAN: Structure-Aware Image Composition","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2212.04579","title":"3D Inception-Based TransMorph: Pre- and Post-operative Multi-contrast MRI Registration in Brain Tumors","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2212.14306","title":"Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models","created":"2022-12-29","cited_by_count":5,"area":"diffusion"},{"id":"2302.13961","title":"Soft labelling for semantic segmentation: Bringing coherence to label down-sampling","created":"2023-02-27","cited_by_count":5,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2104.05588","title":"Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2105.05530","title":"Winograd Algorithm for AdderNet","created":"2021-05-12","cited_by_count":4,"area":null},{"id":"2111.00770","title":"Dense Prediction with Attentive Feature Aggregation","created":"2021-11-01","cited_by_count":4,"area":null},{"id":"2203.01087","title":"Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications","created":"2022-03-02","cited_by_count":4,"area":null}],"next_cursor":"100"}