mlsanityData to 14 Oct 2026

SCoRe: Submodular Combinatorial Representation Learning

arXiv 2310.00165 ↗First posted 29 Sep 2023cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to representation learning, by introducing a family of loss functions based on set-based submodular information measures. We develop two novel combinatorial formulations for loss functions, using the Total Information and Total Correlation, that naturally minimize intra-class variance and inter-class bias. Several commonly used metric/contrastive learning loss functions like supervised contrastive loss, orthogonal projection loss, and N-pairs loss, are all instances of SCoRe, thereby underlining the versatility and applicability of SCoRe in a broad spectrum of learning scenarios. Novel objectives in SCoRe naturally model class-imbalance with up to 7.6% improvement in classification on CIFAR-10-LT, CIFAR-100-LT, MedMNIST, 2.1% on ImageNet-LT, and 19.4% in object detection on IDD and LVIS (v1.0), demonstrating its effectiveness over existing approaches.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 53 of its 82 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

53 of 82 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  8. 2017Mask R-CNNcited by 7,277
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  11. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  12. 2020Supervised Contrastive Learningcited by 2,829
38 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,659
  2. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  3. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  4. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  6. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  7. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  8. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  9. 2020Long-tail learning via logit adjustmentcited by 618
  10. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  11. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  12. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  13. 2021GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Trainingcited by 274
  14. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  15. 2021Parametric Contrastive Learningcited by 217
  16. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  17. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  18. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  19. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  20. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  21. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  22. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  23. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  24. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  25. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  26. 2019Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Visioncited by 64
  27. 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 51
  28. 2022Generalized Parametric Contrastive Learningcited by 45
  29. 2021Orthogonal Projection Losscited by 44
  30. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  31. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  32. 2021Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classificationcited by 24
  33. 2020Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3cited by 22
  34. 2022AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuningcited by 22
  35. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  36. 2023Improving Image Recognition by Retrieving from Web-Scale Image-Text Datacited by 20
  37. 2019Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importancecited by 14
  38. 2021Few-Shot Learning for Road Object Detectioncited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 4.

7 papers.

  1. 2024SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detectioncited by 8
  2. 2025Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detectioncited by 4
  3. 2025InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversitycited by 1
  4. 2026SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognitioncited by 1
  5. 2026Reframing Long-Tailed Learning via Loss Landscape Geometrycited by 1
  6. 2026SMA: Submodular Modality Aligner For Data Efficient Multimodal Learningcited by 1
  7. 2026Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspectivecited by 0