Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/EVP

EVP

Reported on 36 benchmarks across 4 tasks · 1 paper · 8 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision22 results

Instance SegmentationonRefCOCO
IoU· 2023-12-13
77.61
best: 81 (DETRIS)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Instance SegmentationonRefCOCO
IoU (%)· 2023-12-13
77.61
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Instance SegmentationonRefCOCO testA
Overall IoU· 2023-12-13
78.75
best: 86.49 (DeRIS-L)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Instance SegmentationonRefCOCO testB
Overall IoU· 2023-12-13
72.94
best: 83.4 (HyperSeg)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Referring Expression SegmentationonRefCOCO
IoU· 2023-12-13
77.61
best: 81 (DETRIS)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Referring Expression SegmentationonRefCOCO
IoU (%)· 2023-12-13
77.61
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Referring Expression SegmentationonRefCOCO testA
Overall IoU· 2023-12-13
78.75
best: 86.49 (DeRIS-L)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Referring Expression SegmentationonRefCOCO testB
Overall IoU· 2023-12-13
72.94
best: 83.4 (HyperSeg)
SOTA
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
RMS· 2023-12-13
0.224
best: 0.792 (PAD-Net)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
Delta < 1.25· 2023-12-13
0.976
best: 0.989 (UniK3D (FT, metric))
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· 2023-12-13
0.997
best: 1 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· 2023-12-13
0.999
best: 1 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
RMSE· 2023-12-13
0.224
best: 0.013 (Defocus/DepthNet (Normalized))
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
absolute relative error· 2023-12-13
0.061
best: 0.026 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonNYU-Depth V2
log 10· 2023-12-13
0.027
best: 0.059 (SC-DepthV2)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
Delta < 1.25· 2023-12-13
0.98
best: 0.99 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· 2023-12-13
0.998
best: 0.999 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· 2023-12-13
1
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
RMSE· 2023-12-13
2.015
best: 1.394 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
RMSE log· 2023-12-13
0.073
best: 0.048 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
Sq Rel· 2023-12-13
0.136
best: 0.224 (SfM-Revisited)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
Depth EstimationonKITTI Eigen split
absolute relative error· 2023-12-13
0.048
best: 0.029 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548

Methodology14 results

3DonNYU-Depth V2
RMS· 2023-12-13
0.224
best: 0.792 (PAD-Net)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
Delta < 1.25· 2023-12-13
0.976
best: 0.989 (UniK3D (FT, metric))
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
Delta < 1.25^2· 2023-12-13
0.997
best: 1 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
Delta < 1.25^3· 2023-12-13
0.999
best: 1 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
RMSE· 2023-12-13
0.224
best: 0.013 (Defocus/DepthNet (Normalized))
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
absolute relative error· 2023-12-13
0.061
best: 0.026 (HybridDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonNYU-Depth V2
log 10· 2023-12-13
0.027
best: 0.059 (SC-DepthV2)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
Delta < 1.25· 2023-12-13
0.98
best: 0.99 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
Delta < 1.25^2· 2023-12-13
0.998
best: 0.999 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
Delta < 1.25^3· 2023-12-13
1
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
RMSE· 2023-12-13
2.015
best: 1.394 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
RMSE log· 2023-12-13
0.073
best: 0.048 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
Sq Rel· 2023-12-13
0.136
best: 0.224 (SfM-Revisited)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548
3DonKITTI Eigen split
absolute relative error· 2023-12-13
0.048
best: 0.029 (SPIDepth)
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment arXiv:2312.08548