TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/SCAN

SCAN

Simplified versions of the CommAI Navigation tasks

TextsBSD License

SCAN is a dataset for grounded navigation which consists of a set of simple compositional navigation commands paired with the corresponding action sequences.

Source: Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks

Related Benchmarks

Scan2CAD/3D/Average AccuracyScan2CAD/3D Reconstruction/Average AccuracyScanNet/10-shot image generation/3DIoUScanNet/10-shot image generation/Average AccuracyScanNet/10-shot image generation/PQScanNet/10-shot image generation/PQ_stScanNet/10-shot image generation/PQ_thScanNet/10-shot image generation/test mIoUScanNet/10-shot image generation/val mIoUScanNet/2D Semantic Segmentation/Average RecallScanNet/2D Semantic Segmentation/mIoUScanNet/3D/3DIoUScanNet/3D/Chamfer DistanceScanNet/3D/L1ScanNet/3D/RMSEScanNet/3D/absolute relative errorScanNet/3D Character Animation From A Single Photo/Average RecallScanNet/3D Instance Segmentation/mAPScanNet/3D Reconstruction/3DIoUScanNet/3D Reconstruction/Chamfer DistanceScanNet/3D Reconstruction/L1ScanNet/Animation/Average RecallScanNet/Continual Semantic Segmentation/mIoUScanNet/Depth Estimation/RMSEScanNet/Depth Estimation/absolute relative errorScanNet/Instance Segmentation/mAPScanNet/Panoptic Segmentation/PQScanNet/Panoptic Segmentation/PQ_stScanNet/Panoptic Segmentation/PQ_thScanNet/Scene Parsing/Average RecallScanNet/Scene Segmentation/3DIoUScanNet/Scene Segmentation/Average AccuracyScanNet/Semantic Segmentation/3DIoUScanNet/Semantic Segmentation/Average AccuracyScanNet/Semantic Segmentation/PQScanNet/Semantic Segmentation/PQ_stScanNet/Semantic Segmentation/PQ_thScanNet/Semantic Segmentation/test mIoUScanNet/Semantic Segmentation/val mIoUScanNet/Zero-Shot Learning/HmIoUScanNet(v2)/3D Instance Segmentation/mAPScanNet(v2)/3D Instance Segmentation/mAP @ 50ScanNet(v2)/3D Instance Segmentation/mAP@25ScanNet(v2)/3D Instance Segmentation/mRecScanNet(v2)/Instance Segmentation/mAPScanNet(v2)/Instance Segmentation/mAP @ 50ScanNet(v2)/Instance Segmentation/mAP@25ScanNet(v2)/Instance Segmentation/mRecScanNet++/10-shot image generation/Top-1 IoUScanNet++/10-shot image generation/Top-3 IoUScanNet++/16k/mAP@0.25ScanNet++/16k/mAP@0.5ScanNet++/2D Classification/mAP@0.25ScanNet++/2D Classification/mAP@0.5ScanNet++/2D Object Detection/mAP@0.25ScanNet++/2D Object Detection/mAP@0.5ScanNet++/3D/mAP@0.25ScanNet++/3D/mAP@0.5ScanNet++/3D Instance Segmentation/mAPScanNet++/3D Object Detection/mAP@0.25ScanNet++/3D Object Detection/mAP@0.5ScanNet++/3D Semantic Segmentation/Top-1 IoUScanNet++/3D Semantic Segmentation/Top-3 IoUScanNet++/Instance Segmentation/mAPScanNet++/Novel View Synthesis/LPIPSScanNet++/Novel View Synthesis/PSNRScanNet++/Novel View Synthesis/SSIMScanNet++/Object Detection/mAP@0.25ScanNet++/Object Detection/mAP@0.5ScanNet++/Semantic Segmentation/Top-1 IoUScanNet++/Semantic Segmentation/Top-3 IoUScanNet++ (trained on 3DMatch)/3D Point Cloud Interpolation/Recall ( correspondence RMSE below 0.2)ScanNet++ (trained on 3DMatch)/Point Cloud Registration/Recall ( correspondence RMSE below 0.2)ScanNet200/10-shot image generation/test mIoUScanNet200/10-shot image generation/val mIoUScanNet200/3D Instance Segmentation/mAPScanNet200/3D Instance Segmentation/mAP@25ScanNet200/3D Instance Segmentation/mAP@50ScanNet200/3D Open-Vocabulary Instance Segmentation/AP CommonScanNet200/3D Open-Vocabulary Instance Segmentation/AP HeadScanNet200/3D Open-Vocabulary Instance Segmentation/AP TailScanNet200/3D Open-Vocabulary Instance Segmentation/AP25ScanNet200/3D Open-Vocabulary Instance Segmentation/AP50ScanNet200/3D Open-Vocabulary Instance Segmentation/mAPScanNet200/3D Semantic Segmentation/test mIoUScanNet200/3D Semantic Segmentation/val mIoUScanNet200/Instance Segmentation/mAPScanNet200/Instance Segmentation/mAP@25ScanNet200/Instance Segmentation/mAP@50ScanNet200/Semantic Segmentation/test mIoUScanNet200/Semantic Segmentation/val mIoUScanNetV1/Instance Segmentation/mAP@0.25ScanNetV2/10-shot image generation/Mean IoUScanNetV2/10-shot image generation/Mean IoU (test)ScanNetV2/10-shot image generation/Mean IoU (val)ScanNetV2/10-shot image generation/PQScanNetV2/10-shot image generation/Params (M)ScanNetV2/10-shot image generation/Pixel AccuracyScanNetV2/10-shot image generation/RQScanNetV2/10-shot image generation/SQScanNetV2/10-shot image generation/mIoUScanNetV2/16k/mAP@0.25ScanNetV2/16k/mAP@0.5ScanNetV2/2D Classification/mAP@0.25ScanNetV2/2D Classification/mAP@0.5ScanNetV2/2D Object Detection/mAP@0.25ScanNetV2/2D Object Detection/mAP@0.5ScanNetV2/2D Panoptic Segmentation/PQScanNetV2/3D/Delta < 1.25ScanNetV2/3D/absolute relative errorScanNetV2/3D/mAP@0.25ScanNetV2/3D/mAP@0.5ScanNetV2/3D Instance Segmentation/NoC@80ScanNetV2/3D Object Detection/mAP@0.25ScanNetV2/3D Object Detection/mAP@0.5ScanNetV2/3D Semantic Segmentation/mIoUScanNetV2/Depth Estimation/Delta < 1.25ScanNetV2/Depth Estimation/absolute relative errorScanNetV2/Instance Segmentation/NoC@80ScanNetV2/Instance Segmentation/mAP@0.50ScanNetV2/Interactive 3D Instance Segmentation/NoC@80ScanNetV2/Object Detection/mAP@0.25ScanNetV2/Object Detection/mAP@0.5ScanNetV2/Panoptic Segmentation/PQScanNetV2/Panoptic Segmentation/Params (M)ScanNetV2/Panoptic Segmentation/RQScanNetV2/Panoptic Segmentation/SQScanNetV2/Semantic Segmentation/Mean IoUScanNetV2/Semantic Segmentation/Mean IoU (test)ScanNetV2/Semantic Segmentation/Mean IoU (val)ScanNetV2/Semantic Segmentation/PQScanNetV2/Semantic Segmentation/Params (M)ScanNetV2/Semantic Segmentation/Pixel AccuracyScanNetV2/Semantic Segmentation/RQScanNetV2/Semantic Segmentation/SQScanNetV2/Semantic Segmentation/mIoUScanNetV2/Surface Normals Estimation/% < 11.25ScanNetV2/Surface Normals Estimation/% < 22.5ScanNetV2/Surface Normals Estimation/% < 30ScanNetV2/Surface Normals Estimation/Mean Angle ErrorScanObjectNN/3D Point Cloud Classification/FLOPsScanObjectNN/3D Point Cloud Classification/GFLOPsScanObjectNN/3D Point Cloud Classification/Mean AccuracyScanObjectNN/3D Point Cloud Classification/Number of paramsScanObjectNN/3D Point Cloud Classification/Number of params (M)ScanObjectNN/3D Point Cloud Classification/OBJ-BG (OA)ScanObjectNN/3D Point Cloud Classification/OBJ-ONLY (OA)ScanObjectNN/3D Point Cloud Classification/OBJ_BG Accuracy(%)ScanObjectNN/3D Point Cloud Classification/OBJ_ONLY Accuracy(%)ScanObjectNN/3D Point Cloud Classification/Overall AccuracyScanObjectNN/3D Point Cloud Classification/Overall Accuracy (PB_T50_RS)ScanObjectNN/3D Point Cloud Classification/PB_T50_RS Accuracy (%)ScanObjectNN/3D Point Cloud Linear Classification/Overall AccuracyScanObjectNN/3D Point Cloud Reconstruction/FLOPsScanObjectNN/3D Point Cloud Reconstruction/GFLOPsScanObjectNN/3D Point Cloud Reconstruction/Mean AccuracyScanObjectNN/3D Point Cloud Reconstruction/Number of paramsScanObjectNN/3D Point Cloud Reconstruction/Number of params (M)ScanObjectNN/3D Point Cloud Reconstruction/OBJ-BG (OA)ScanObjectNN/3D Point Cloud Reconstruction/OBJ-ONLY (OA)ScanObjectNN/3D Point Cloud Reconstruction/OBJ_BG Accuracy(%)ScanObjectNN/3D Point Cloud Reconstruction/OBJ_ONLY Accuracy(%)ScanObjectNN/3D Point Cloud Reconstruction/Overall AccuracyScanObjectNN/3D Point Cloud Reconstruction/Overall Accuracy (PB_T50_RS)ScanObjectNN/3D Point Cloud Reconstruction/PB_T50_RS Accuracy (%)ScanObjectNN/Point Cloud Classification/Top-1 Accuracy(5-Way-1-Shot)ScanObjectNN/Shape Representation Of 3D Point Clouds/FLOPsScanObjectNN/Shape Representation Of 3D Point Clouds/GFLOPsScanObjectNN/Shape Representation Of 3D Point Clouds/Mean AccuracyScanObjectNN/Shape Representation Of 3D Point Clouds/Number of paramsScanObjectNN/Shape Representation Of 3D Point Clouds/Number of params (M)ScanObjectNN/Shape Representation Of 3D Point Clouds/OBJ-BG (OA)ScanObjectNN/Shape Representation Of 3D Point Clouds/OBJ-ONLY (OA)ScanObjectNN/Shape Representation Of 3D Point Clouds/OBJ_BG Accuracy(%)ScanObjectNN/Shape Representation Of 3D Point Clouds/OBJ_ONLY Accuracy(%)ScanObjectNN/Shape Representation Of 3D Point Clouds/Overall AccuracyScanObjectNN/Shape Representation Of 3D Point Clouds/Overall Accuracy (PB_T50_RS)ScanObjectNN/Shape Representation Of 3D Point Clouds/PB_T50_RS Accuracy (%)ScanObjectNN/Training-free 3D Point Cloud Classification/Accuracy (%)ScanObjectNN/Training-free 3D Point Cloud Classification/Need 3D Data?ScanObjectNN/Training-free 3D Point Cloud Classification/ParametersScanObjectNN 10-way (10-shot)/3D Point Cloud Classification/Overall AccuracyScanObjectNN 10-way (10-shot)/3D Point Cloud Reconstruction/Overall AccuracyScanObjectNN 10-way (10-shot)/Shape Representation Of 3D Point Clouds/Overall AccuracyScanObjectNN 10-way (20-shot)/3D Point Cloud Classification/Overall AccuracyScanObjectNN 10-way (20-shot)/3D Point Cloud Reconstruction/Overall AccuracyScanObjectNN 10-way (20-shot)/Shape Representation Of 3D Point Clouds/Overall AccuracyScanObjectNN 5-way (10-shot)/3D Point Cloud Classification/Overall AccuracyScanObjectNN 5-way (10-shot)/3D Point Cloud Reconstruction/Overall AccuracyScanObjectNN 5-way (10-shot)/Shape Representation Of 3D Point Clouds/Overall AccuracyScanObjectNN 5-way (20-shot)/3D Point Cloud Classification/Overall AccuracyScanObjectNN 5-way (20-shot)/3D Point Cloud Reconstruction/Overall AccuracyScanObjectNN 5-way (20-shot)/Shape Representation Of 3D Point Clouds/Overall AccuracyScanQA Test w/ objects/Visual Question Answering (VQA)/BLEU-1ScanQA Test w/ objects/Visual Question Answering (VQA)/BLEU-4ScanQA Test w/ objects/Visual Question Answering (VQA)/CIDErScanQA Test w/ objects/Visual Question Answering (VQA)/Exact MatchScanQA Test w/ objects/Visual Question Answering (VQA)/METEORScanQA Test w/ objects/Visual Question Answering (VQA)/ROUGEScanRefer Dataset/Image Captioning/BLEU-4ScanRefer Dataset/Image Captioning/CIDErScanRefer Dataset/Image Captioning/METEORScanRefer Dataset/Image Captioning/ROUGE-L

Statistics

Papers
148
Benchmarks
0

Links

Homepage

Tasks

Semantic ParsingSystematic Generalization