VisBench probes Heads fitted on frozen features, one per (task, backbone). Evaluate without training. Each head is valid only against its named backbone. turhancan97/visbench-classification-dinov2_vits14 Updated 15 days ago turhancan97/visbench-classification-dinov2_vitb14 Updated 15 days ago turhancan97/visbench-semantic_segmentation-dinov2_vits14 Updated 15 days ago turhancan97/visbench-semantic_segmentation-dinov2_vitb14 Updated 15 days ago
SpaRRTa Spatial relation probing, given an image and an object triplet, it predicts whether the target is Left / Right / Between relative to reference objects turhancan97/SpaRRTa-probes Image Classification • Updated Mar 13 • 1 Sleeping Agents 1 SpaRRTA 🧭 1 Classify object direction (Front/Back/Left/Right) in images turhancan97/SpaRRTa Viewer • Updated Jun 26 • 149k • 306 • 1 SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models Paper • 2601.11729 • Published Jan 16 • 1
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models Paper • 2601.11729 • Published Jan 16 • 1
VisBench probes Heads fitted on frozen features, one per (task, backbone). Evaluate without training. Each head is valid only against its named backbone. turhancan97/visbench-classification-dinov2_vits14 Updated 15 days ago turhancan97/visbench-classification-dinov2_vitb14 Updated 15 days ago turhancan97/visbench-semantic_segmentation-dinov2_vits14 Updated 15 days ago turhancan97/visbench-semantic_segmentation-dinov2_vitb14 Updated 15 days ago
SpaRRTa Spatial relation probing, given an image and an object triplet, it predicts whether the target is Left / Right / Between relative to reference objects turhancan97/SpaRRTa-probes Image Classification • Updated Mar 13 • 1 Sleeping Agents 1 SpaRRTA 🧭 1 Classify object direction (Front/Back/Left/Right) in images turhancan97/SpaRRTa Viewer • Updated Jun 26 • 149k • 306 • 1 SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models Paper • 2601.11729 • Published Jan 16 • 1
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models Paper • 2601.11729 • Published Jan 16 • 1