mlsanityData to 14 Oct 2026

Zero-Shot Logit Adjustment

arXiv 2204.11822 ↗First posted 25 Apr 2022cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier. However, existing generation-based methods focus on enhancing the generator's effect while neglecting the improvement of the classifier. In this paper, we first analyze of two properties of the generated pseudo unseen samples: bias and homogeneity. Then, we perform variational Bayesian inference to back-derive the evaluation metrics, which reflects the balance of the seen and unseen classes. As a consequence of our derivation, the aforementioned two properties are incorporated into the classifier training as seen-unseen priors via logit adjustment. The Zero-Shot Logit Adjustment further puts semantic-based classifiers into effect in generation-based GZSL. Our experiments demonstrate that the proposed technique achieves state-of-the-art when combined with the basic generator, and it can improve various generative Zero-Shot Learning frameworks. Our codes are available on https://github.com/cdb342/IJCAI-2022-ZLA.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

20 of 44 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Improved Training of Wasserstein GANscited by 2,235
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  5. 2020Long-tail learning via logit adjustmentcited by 618
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  7. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  8. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  9. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
  10. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  11. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  12. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
8 more
  1. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  2. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  3. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  4. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  5. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  6. 2020Invertible Zero-Shot Recognition Flowscited by 48
  7. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  8. 2016Reviving Threshold-Moving: a Simple Plug-in Bagging Ensemble for Binary and Multiclass Imbalanced Datacited by 23

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
  2. 2023Data Optimization in Deep Learning: A Surveycited by 6
  3. 2022Evolutionary Generalized Zero-Shot Learningcited by 3
  4. 2024Unleashing the Potential of Model Bias for Generalized Category Discoverycited by 1
  5. 2023SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learningcited by 0
  6. 2025Class Similarity-Based Multimodal Classification under Heterogeneous Category Setscited by 0
  7. 2026Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cuescited by 0