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/ReCon

ReCon

Reported on 115 benchmarks across 7 tasks · 2 papers · 69 SOTA

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

Computer Vision52 results

Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-02-05
95.35
best: 99.48 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-02-05
93.8
best: 97.76 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2023-02-05
91.26
best: 97.2 (OmniVec2)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
95.8
best: 96.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
97.3
best: 98 (PointGPT)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
98.9
best: 99.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet10
Accuracy (%)· uses extra data· 2023-02-05
75.6
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-02-05
95.35
best: 99.48 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-02-05
93.8
best: 97.76 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2023-02-05
91.26
best: 97.2 (OmniVec2)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
95.8
best: 96.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
97.3
best: 98 (PointGPT)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
98.9
best: 99.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet10
Accuracy (%)· uses extra data· 2023-02-05
75.6
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-02-05
95.35
best: 99.48 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-02-05
93.8
best: 97.76 (PointGST)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2023-02-05
91.26
best: 97.2 (OmniVec2)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
95.8
best: 96.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
97.3
best: 98 (PointGPT)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-02-05
98.9
best: 99.5 (ReCon++)
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet10
Accuracy (%)· uses extra data· 2023-02-05
75.6
SOTA
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· uses extra data· 2023-02-05
94.7
best: 95.3 (PointGST)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
3
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
1.9
best: 16 (PointNet++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
93.3
best: 95 (Point-JEPA)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
3.9
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
1.2
best: 15.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ_BG Accuracy(%)· uses extra data· 2023-02-05
40.4
best: 41.22 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2023-02-05
43.7
best: 65.4 (ReCon++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonScanObjectNN
PB_T50_RS Accuracy (%)· uses extra data· 2023-02-05
30.5
best: 35.36 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
Shape Representation Of 3D Point CloudsonModelNet40
Accuracy (%)· uses extra data· 2023-02-05
61.7
best: 88.2 (Uni3D)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· uses extra data· 2023-02-05
94.7
best: 95.3 (PointGST)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
3
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
1.9
best: 16 (PointNet++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
93.3
best: 95 (Point-JEPA)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
3.9
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
1.2
best: 15.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
OBJ_BG Accuracy(%)· uses extra data· 2023-02-05
40.4
best: 41.22 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2023-02-05
43.7
best: 65.4 (ReCon++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonScanObjectNN
PB_T50_RS Accuracy (%)· uses extra data· 2023-02-05
30.5
best: 35.36 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ClassificationonModelNet40
Accuracy (%)· uses extra data· 2023-02-05
61.7
best: 88.2 (Uni3D)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud Linear ClassificationonModelNet40
Overall Accuracy· uses extra data· 2023-02-05
93.4
best: 93.6 (ReCon++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· uses extra data· 2023-02-05
94.7
best: 95.3 (PointGST)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
3
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
1.9
best: 16 (PointNet++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-02-05
93.3
best: 95 (Point-JEPA)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-02-05
3.9
best: 13.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-02-05
1.2
best: 15.5 (PointNet)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
OBJ_BG Accuracy(%)· uses extra data· 2023-02-05
40.4
best: 41.22 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2023-02-05
43.7
best: 65.4 (ReCon++)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononScanObjectNN
PB_T50_RS Accuracy (%)· uses extra data· 2023-02-05
30.5
best: 35.36 (PointCLIP V2)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318
3D Point Cloud ReconstructiononModelNet40
Accuracy (%)· uses extra data· 2023-02-05
61.7
best: 88.2 (Uni3D)
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining arXiv:2302.02318

Miscellaneous42 results

Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Image-to-text R@1· 2025-02-27
80.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
R-Sum· 2025-02-27
528.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Text-to-image R@1· 2025-02-27
65.2
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Text-to-image R@10· 2025-02-27
96
best: 96.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Text-to-image R@5· 2025-02-27
91
best: 91.2 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Image-to-text R@1· 2025-02-27
43.1
best: 43.6 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Image-to-text R@10· 2025-02-27
78.1
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Image-to-text R@5· 2025-02-27
68.7
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
R-Sum· 2025-02-27
380.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Text-to-image R@1· 2025-02-27
44.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Text-to-image R@5· 2025-02-27
68.3
best: 68.4 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Image-to-text R@1· 2025-02-27
80.3
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
R-Sum· 2025-02-27
511.8
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Text-to-image R@1· 2025-02-27
61.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Text-to-image R@10· 2025-02-27
91.3
best: 92.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Text-to-image R@5· 2025-02-27
85.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Image-to-text R@1· 2025-02-27
80.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
R-Sum· 2025-02-27
528.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Text-to-image R@1· 2025-02-27
65.2
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Text-to-image R@10· 2025-02-27
96
best: 96.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Text-to-image R@5· 2025-02-27
91
best: 91.2 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Image-to-text R@1· 2025-02-27
43.1
best: 43.6 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Image-to-text R@10· 2025-02-27
78.1
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Image-to-text R@5· 2025-02-27
68.7
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
R-Sum· 2025-02-27
380.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Text-to-image R@1· 2025-02-27
44.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Text-to-image R@5· 2025-02-27
68.3
best: 68.4 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Image-to-text R@1· 2025-02-27
80.3
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
R-Sum· 2025-02-27
511.8
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Text-to-image R@1· 2025-02-27
61.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Text-to-image R@10· 2025-02-27
91.3
best: 92.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Text-to-image R@5· 2025-02-27
85.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Image-to-text R@10· 2025-02-27
98.8
best: 99 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCOCO-Noisy
Image-to-text R@5· 2025-02-27
96.6
best: 97.2 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonCC152K
Text-to-image R@10· 2025-02-27
77.4
best: 78.4 (CRCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Image-to-text R@10· 2025-02-27
97.8
best: 98.3 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Image Retrieval with Multi-Modal QueryonFlickr30K-Noisy
Image-to-text R@5· 2025-02-27
95.3
best: 95.8 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Image-to-text R@10· 2025-02-27
98.8
best: 99 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCOCO-Noisy
Image-to-text R@5· 2025-02-27
96.6
best: 97.2 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonCC152K
Text-to-image R@10· 2025-02-27
77.4
best: 78.4 (CRCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Image-to-text R@10· 2025-02-27
97.8
best: 98.3 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal Information RetrievalonFlickr30K-Noisy
Image-to-text R@5· 2025-02-27
95.3
best: 95.8 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962

Natural Language Processing21 results

Cross-Modal RetrievalonCOCO-Noisy
Image-to-text R@1· 2025-02-27
80.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
R-Sum· 2025-02-27
528.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
Text-to-image R@1· 2025-02-27
65.2
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
Text-to-image R@10· 2025-02-27
96
best: 96.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
Text-to-image R@5· 2025-02-27
91
best: 91.2 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Image-to-text R@1· 2025-02-27
43.1
best: 43.6 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Image-to-text R@10· 2025-02-27
78.1
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Image-to-text R@5· 2025-02-27
68.7
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
R-Sum· 2025-02-27
380.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Text-to-image R@1· 2025-02-27
44.9
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Text-to-image R@5· 2025-02-27
68.3
best: 68.4 (UGNCL)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Image-to-text R@1· 2025-02-27
80.3
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
R-Sum· 2025-02-27
511.8
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Text-to-image R@1· 2025-02-27
61.6
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Text-to-image R@10· 2025-02-27
91.3
best: 92.7 (CTPR-SGR)
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Text-to-image R@5· 2025-02-27
85.5
SOTA
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
Image-to-text R@10· 2025-02-27
98.8
best: 99 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCOCO-Noisy
Image-to-text R@5· 2025-02-27
96.6
best: 97.2 (UGNCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonCC152K
Text-to-image R@10· 2025-02-27
77.4
best: 78.4 (CRCL)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Image-to-text R@10· 2025-02-27
97.8
best: 98.3 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962
Cross-Modal RetrievalonFlickr30K-Noisy
Image-to-text R@5· 2025-02-27
95.3
best: 95.8 (CTPR-SGR)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning arXiv:2502.19962