{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"1909.13226","title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","created":"2019-09-29","cited_by_count":188},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"2303.17559","title":"DDP: Diffusion Model for Dense Visual Prediction","created":"2023-03-30","cited_by_count":148},{"id":"2404.03425","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","created":"2024-04-04","cited_by_count":120},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"1603.06201","title":"A Survey on Object Detection in Optical Remote Sensing Images","created":"2016-03-20","cited_by_count":78},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77},{"id":"1909.12579","title":"Pruning from Scratch","created":"2019-09-27","cited_by_count":72},{"id":"2405.14224","title":"DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis","created":"2024-05-23","cited_by_count":72},{"id":"2306.06370","title":"AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder","created":"2023-06-10","cited_by_count":70},{"id":"1909.07829","title":"AdaptIS: Adaptive Instance Selection Network","created":"2019-09-17","cited_by_count":64},{"id":"2108.09084","title":"Fastformer: Additive Attention Can Be All You Need","created":"2021-08-20","cited_by_count":61},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60},{"id":"2312.09579","title":"MobileSAMv2: Faster Segment Anything to Everything","created":"2023-12-15","cited_by_count":42},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40},{"id":"2012.10150","title":"SCNet: Training Inference Sample Consistency for Instance Segmentation","created":"2020-12-18","cited_by_count":38},{"id":"2404.18895","title":"RSCaMa: Remote Sensing Image Change Captioning with State Space Model","created":"2024-04-29","cited_by_count":35},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","cited_by_count":35},{"id":"2011.09808","title":"Unmixing Convolutional Features for Crisp Edge Detection","created":"2020-11-19","cited_by_count":32},{"id":"2303.11316","title":"Generative Semantic Segmentation","created":"2023-03-20","cited_by_count":32},{"id":"2212.01579","title":"Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution","created":"2022-12-03","cited_by_count":22},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20},{"id":"2507.06231","title":"RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models","created":"2025-07-08","cited_by_count":17},{"id":"2111.11057","title":"Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images","created":"2021-11-22","cited_by_count":12},{"id":"2310.04964","title":"Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling","created":"2023-10-08","cited_by_count":7},{"id":"2402.00703","title":"Vehicle Perception from Satellite","created":"2024-02-01","cited_by_count":7}],"next_cursor":null}