mlsanityData to 14 Oct 2026

Reduction of Class Activation Uncertainty with Background Information

arXiv 2305.03238 ↗First posted 5 May 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class activation mappings (CAMs) of the trained models, we observed the tendency towards looking at a bigger picture with the proposed model training methodology. Applying the vision transformer with the proposed background class, we receive state-of-the-art (SOTA) performance on CIFAR-10C, Caltech-101, and CINIC-10 datasets. Example scripts are available in the `CAM' folder of the following GitHub Repository: github.com/dipuk0506/UQ

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 88 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

39 of 88 references.

References · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016Wide Residual Networkscited by 3,070
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2021Vision Transformers for Dense Predictioncited by 1,803
  9. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  11. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  12. 2014How transferable are features in deep neural networks?cited by 1,225
27 more
  1. 2021Multiscale Vision Transformerscited by 897
  2. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  3. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  4. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  5. 2021Domain Generalization: A Surveycited by 764
  6. 2022Continual Test-Time Domain Adaptationcited by 525
  7. 2018Deep Learning for Classical Japanese Literaturecited by 422
  8. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  9. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  10. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 294
  11. 2022Contrastive Test-Time Adaptationcited by 261
  12. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  13. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 168
  14. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  15. 2018On the importance of single directions for generalizationcited by 99
  16. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  17. 2018An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixingcited by 66
  18. 2015The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognitioncited by 48
  19. 2020SpinalNet: Deep Neural Network with Gradual Inputcited by 40
  20. 2018Revisiting the Importance of Individual Units in CNNs via Ablationcited by 32
  21. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
  22. 2019Multitask Learning to Improve Egocentric Action Recognitioncited by 23
  23. 2022Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusioncited by 18
  24. 2022An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systemscited by 16
  25. 2019Optimal Uncertainty-guided Neural Network Trainingcited by 7
  26. 2019Generalization in multitask deep neural classifiers: a statistical physics approachcited by 6
  27. 2023Provable Pathways: Learning Multiple Tasks over Multiple Pathscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
  2. 2025Cross Knowledge Distillation between Artificial and Spiking Neural Networkscited by 4
  3. 2024Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layercited by 0