mlsanityData to 7 Oct 2026

CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback

arXiv 2210.09505 ↗First posted 18 Oct 2022cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in classification) at a random noise level (from small to large noise). At inference time, since we do not know the target, we run the network with only noise in place of the noisy target. CNT provides hints through the noisy label (with less noise, we can more easily infer the true target). This give two main benefits: 1) the top-down feedback allows the model to focus on simpler and more digestible sub-problems and 2) rather than learning to solve the task from scratch, the model will first learn to master easy examples (with less noise), while slowly progressing toward harder examples (with more noise).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

30 of 43 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  11. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  12. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
18 more
  1. 2016Progressive Neural Networkscited by 1,332
  2. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  4. 2016Deep Variational Information Bottleneckcited by 915
  5. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  6. 2017A simple neural network module for relational reasoningcited by 345
  7. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  8. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  9. 2017Noisy Networks for Explorationcited by 262
  10. 2021Curriculum Learning: A Surveycited by 257
  11. 2017Modulating early visual processing by languagecited by 167
  12. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  13. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  14. 2020Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modulescited by 38
  15. 2019An Optimistic Perspective on Offline Reinforcement Learningcited by 37
  16. 2019Knowledge transfer in deep block-modular neural networkscited by 14
  17. 2018On the Transferability of Representations in Neural Networks Between Datasets and Taskscited by 4
  18. 2020Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layerscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Active Imitation Learning with Noisy Guidance
  2. 2023Selective Sampling and Imitation Learning via Online Regression
  3. 2024CANDERE-COACH: Reinforcement Learning from Noisy Feedback
  4. 2020Robust Imitation Learning from Noisy Demonstrations
  5. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
  6. 2023Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations
  7. 2021Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU
  8. 2024DIDA: Denoised Imitation Learning based on Domain Adaptation