{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"1908.09822","title":"Confidence Regularized Self-Training","created":"2019-08-26","cited_by_count":419},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1904.10620","title":"Bidirectional Learning for Domain Adaptation of Semantic Segmentation","created":"2019-04-24","cited_by_count":308},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268},{"id":"2007.08702","title":"DACS: Domain Adaptation via Cross-domain Mixed Sampling","created":"2020-07-17","cited_by_count":226},{"id":"2003.03773","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","created":"2020-03-08","cited_by_count":222},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204},{"id":"2212.01322","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","created":"2022-12-02","cited_by_count":178},{"id":"2008.12197","title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","created":"2020-08-27","cited_by_count":177},{"id":"1910.13049","title":"Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation","created":"2019-10-29","cited_by_count":151},{"id":"2105.00097","title":"Self-supervised Augmentation Consistency for Adapting Semantic Segmentation","created":"2021-04-30","cited_by_count":149},{"id":"1909.13589","title":"Domain Adaptation for Semantic Segmentation with Maximum Squares Loss","created":"2019-09-30","cited_by_count":138},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"1909.00589","title":"Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation","created":"2019-09-02","cited_by_count":126},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85},{"id":"2108.05988","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","created":"2021-08-12","cited_by_count":81},{"id":"2105.08128","title":"PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training","created":"2021-05-17","cited_by_count":80},{"id":"2108.03557","title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","created":"2021-08-08","cited_by_count":79},{"id":"2206.07706","title":"Masked Frequency Modeling for Self-Supervised Visual Pre-Training","created":"2022-06-15","cited_by_count":71},{"id":"1706.00120","title":"Superhuman Accuracy on the SNEMI3D Connectomics Challenge","created":"2017-05-31","cited_by_count":64},{"id":"2003.04614","title":"Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation","created":"2020-03-10","cited_by_count":62},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50},{"id":"2004.08878","title":"Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation","created":"2020-04-19","cited_by_count":45},{"id":"2303.05251","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","created":"2023-03-09","cited_by_count":43},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2207.06654","title":"Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation","created":"2022-07-14","cited_by_count":40},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2003.04010","title":"Context-Aware Domain Adaptation in Semantic Segmentation","created":"2020-03-09","cited_by_count":36},{"id":"2204.08227","title":"The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training","created":"2022-04-18","cited_by_count":33},{"id":"2009.12559","title":"Affinity Space Adaptation for Semantic Segmentation Across Domains","created":"2020-09-26","cited_by_count":31},{"id":"2403.15992","title":"BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval","created":"2024-03-24","cited_by_count":30},{"id":"2010.12440","title":"Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training","created":"2020-10-21","cited_by_count":27},{"id":"2303.17386","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","created":"2023-03-30","cited_by_count":27},{"id":"2107.11004","title":"Domain Adaptive Video Segmentation via Temporal Consistency Regularization","created":"2021-07-23","cited_by_count":21},{"id":"2310.04148","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":19},{"id":"2401.06385","title":"SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization","created":"2024-01-12","cited_by_count":19},{"id":"2407.19323","title":"MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo","created":"2024-07-27","cited_by_count":17},{"id":"2308.09917","title":"Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation","created":"2023-08-19","cited_by_count":16},{"id":"2411.04656","title":"ICH-SCNet: Intracerebral Hemorrhage Segmentation and Prognosis Classification Network Using CLIP-guided SAM mechanism","created":"2024-11-07","cited_by_count":16},{"id":"2412.19080","title":"Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation","created":"2024-12-26","cited_by_count":15},{"id":"2103.15685","title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","created":"2021-03-29","cited_by_count":13},{"id":"2412.11578","title":"DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo","created":"2024-12-16","cited_by_count":12},{"id":"2506.23121","title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation","created":"2025-06-29","cited_by_count":12},{"id":"2502.09971","title":"Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression","created":"2025-02-14","cited_by_count":11},{"id":"2503.13721","title":"SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraint","created":"2025-03-17","cited_by_count":11},{"id":"2402.11307","title":"ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Network","created":"2024-02-17","cited_by_count":10},{"id":"2308.09990","title":"TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo","created":"2023-08-19","cited_by_count":9},{"id":"2410.13523","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","created":"2024-10-17","cited_by_count":7},{"id":"2405.06525","title":"SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation","created":"2024-05-10","cited_by_count":4},{"id":"2501.13130","title":"A Novel Scene Coupling Semantic Mask Network for Remote Sensing Image Segmentation","created":"2025-01-22","cited_by_count":4},{"id":"2308.16461","title":"Domain Adaptive Synapse Detection with Weak Point Annotations","created":"2023-08-31","cited_by_count":2}],"next_cursor":null}