| Point Transformer V3: Simpler, Faster, Stronger | Dec 15, 2023 | 3D Semantic SegmentationLIDAR Semantic Segmentation | CodeCode Available | 3 |
| AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One | Dec 10, 2023 | AllBenchmarking | CodeCode Available | 3 |
| Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment | Dec 1, 2023 | Contrastive LearningFew-Shot Learning | CodeCode Available | 3 |
| UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition | Nov 27, 2023 | Image ClassificationObject Detection | CodeCode Available | 3 |
| SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks | Nov 20, 2023 | DiversityImage Segmentation | CodeCode Available | 3 |
| Putting the Object Back into Video Object Segmentation | Oct 19, 2023 | ObjectSegmentation | CodeCode Available | 3 |
| Tracking Anything with Decoupled Video Segmentation | Sep 7, 2023 | Open-Vocabulary Video SegmentationOpen-World Video Segmentation | CodeCode Available | 3 |
| SAM-Med2D | Aug 30, 2023 | DecoderImage Segmentation | CodeCode Available | 3 |
| VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation | Aug 28, 2023 | Instance SegmentationOptical Flow Estimation | CodeCode Available | 3 |
| Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning | May 18, 2023 | Adversarial RobustnessData Poisoning | CodeCode Available | 3 |
| ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities | May 18, 2023 | 1 Image, 2*2 StitchiAction Classification | CodeCode Available | 3 |
| Personalize Segment Anything Model with One Shot | May 4, 2023 | Image Generationmodel | CodeCode Available | 3 |
| Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation | Apr 25, 2023 | Image SegmentationMedical Image Segmentation | CodeCode Available | 3 |
| Anything-3D: Towards Single-view Anything Reconstruction in the Wild | Apr 19, 2023 | 3D ReconstructionDiversity | CodeCode Available | 3 |
| SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More | Apr 18, 2023 | General KnowledgeImage Segmentation | CodeCode Available | 3 |
| Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks | Mar 30, 2023 | Human ParsingPedestrian Attribute Recognition | CodeCode Available | 3 |
| FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization | Mar 24, 2023 | 3D Hand Pose EstimationGPU | CodeCode Available | 3 |
| PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360^ | Mar 23, 2023 | Image GenerationImage Segmentation | CodeCode Available | 3 |
| A Simple Framework for Open-Vocabulary Segmentation and Detection | Mar 14, 2023 | Instance SegmentationPanoptic Segmentation | CodeCode Available | 3 |
| Universal Instance Perception as Object Discovery and Retrieval | Mar 12, 2023 | Described Object DetectionGeneralized Referring Expression Comprehension | CodeCode Available | 3 |
| Cut and Learn for Unsupervised Object Detection and Instance Segmentation | Jan 26, 2023 | Instance Segmentationobject-detection | CodeCode Available | 3 |
| MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer | Jan 19, 2023 | Image GenerationImage Segmentation | CodeCode Available | 3 |
| Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling | Jan 9, 2023 | 2D Object DetectionContrastive Learning | CodeCode Available | 3 |
| ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders | Jan 2, 2023 | Object DetectionRepresentation Learning | CodeCode Available | 3 |
| PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg | Jan 1, 2023 | Image GenerationImage Segmentation | CodeCode Available | 3 |
