mlsanityData to 7 Oct 2026

Hybrid Discriminative-Generative Training via Contrastive Learning

arXiv 2007.09070 ↗First posted 17 Jul 2020cs.LG cs.CV stat.MLcited by 24

Not on the map. Why?

Abstract (arXiv)

Contrastive learning and supervised learning have both seen significant progress and success. However, thus far they have largely been treated as two separate objectives, brought together only by having a shared neural network. In this paper we show that through the perspective of hybrid discriminative-generative training of energy-based models we can make a direct connection between contrastive learning and supervised learning. Beyond presenting this unified view, we show our specific choice of approximation of the energy-based loss outperforms the existing practice in terms of classification accuracy of WideResNet on CIFAR-10 and CIFAR-100. It also leads to improved performance on robustness, out-of-distribution detection, and calibration.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 8; 2023: 6; 2024: 2; 2025: 1; 2026: 1.

24 papers.

Sort:

By area:

  1. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  2. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  3. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  4. 2022Consistent Representation Learning for Continual Relation Extractioncited by 28
  5. 2022Hybrid Predictive Coding: Inferring, Fast and Slowcited by 25
  6. 2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
  7. 2022Joint Optimization of Ranking and Calibration with Contextualized Hybrid Modelcited by 22
  8. 2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
  9. 2022CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learningcited by 11
  10. 2022Learning Probabilistic Models from Generator Latent Spaces with Hat EBMcited by 11
  11. 2022ELM: Embedding and Logit Margins for Long-Tail Learningcited by 10
  12. 2023Multiscale Flow for Robust and Optimal Cosmological Analysiscited by 10
12 more
  1. 2021Hybrid Generative-Contrastive Representation Learningcited by 8
  2. 2022GEDI: GEnerative and DIscriminative Training for Self-Supervised Learningcited by 6
  3. 2021Conjugate Energy-Based Modelscited by 2
  4. 2023Unifying Self-Supervised Clustering and Energy-Based Modelscited by 2
  5. 2025AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testingcited by 2
  6. 2021A Unified View of cGANs with and without Classifierscited by 1
  7. 2023How to Construct Energy for Images? Denoising Autoencoder Can Be Energy Based Modelcited by 1
  8. 2024Classification-Denoising Networkscited by 1
  9. 2023Stabilized training of joint energy-based models and their practical applicationscited by 0
  10. 2023DORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsingcited by 0
  11. 2024Projected Belief Networks With Discriminative Alignment for Acoustic Event Classification: Rivaling State of the Art CNNscited by 0
  12. 2026Contrastive Conformal Setscited by 0