DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models

• URL: http://arxiv.org/abs/2302.10341v3
• Date: Wed, 15 May 2024 19:56:59 GMT
• Title: DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models
• Authors: Vivian Lin, Kuk Jin Jang, Souradeep Dutta, Michele Caprio, Oleg Sokolsky, Insup Lee,
• Abstract summary: We propose to use control for learned models to recover from distribution shifts online. Our method applies a sequence of semantic-preserving transformations to bring the shifted data closer in distribution to the training set. We show that our method generalizes to composites of shifts from the ImageNet-C benchmark, achieving improvements in average accuracy of up to 9.81%.
• Score: 4.374569172244273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have repeatedly been shown to be non-robust to the uncertainties of the real world, even to naturally occurring ones. A vast majority of current approaches have focused on data-augmentation methods to expand the range of perturbations that the classifier is exposed to while training. A relatively unexplored avenue that is equally promising involves sanitizing an image as a preprocessing step, depending on the nature of perturbation. In this paper, we propose to use control for learned models to recover from distribution shifts online. Specifically, our method applies a sequence of semantic-preserving transformations to bring the shifted data closer in distribution to the training set, as measured by the Wasserstein distance. Our approach is to 1) formulate the problem of distribution shift recovery as a Markov decision process, which we solve using reinforcement learning, 2) identify a minimum condition on the data for our method to be applied, which we check online using a binary classifier, and 3) employ dimensionality reduction through orthonormal projection to aid in our estimates of the Wasserstein distance. We provide theoretical evidence that orthonormal projection preserves characteristics of the data at the distributional level. We apply our distribution shift recovery approach to the ImageNet-C benchmark for distribution shifts, demonstrating an improvement in average accuracy of up to 14.21% across a variety of state-of-the-art ImageNet classifiers. We further show that our method generalizes to composites of shifts from the ImageNet-C benchmark, achieving improvements in average accuracy of up to 9.81%. Finally, we test our method on CIFAR-100-C and report improvements of up to 8.25%.

Related papers

• Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
  We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data. Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
  arXiv  Detail & Related papers  (2024-04-24T09:04:36Z)
• Target to Source: Guidance-Based Diffusion Model for Test-Time Adaptation [8.695439655048634]
  We propose a novel guidance-based diffusion-driven adaptation (GDDA) to overcome the data shift. GDDA significantly performs better than the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-12-08T02:31:36Z)
• Stable Target Field for Reduced Variance Score Estimation in Diffusion Models [5.9115407007859755]
  Diffusion models generate samples by reversing a fixed forward diffusion process. We argue that the source of such variance lies in the handling of intermediate noise-variance scales. We propose to remedy the problem by incorporating a reference batch which we use to calculate weighted conditional scores as more stable training targets.
  arXiv  Detail & Related papers  (2023-02-01T18:57:01Z)
• (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
  We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5. We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
  arXiv  Detail & Related papers  (2022-06-21T17:27:27Z)
• Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations [76.82124752950148]
  We develop a convenient gradient-based method for selecting the data augmentation. We use a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective.
  arXiv  Detail & Related papers  (2022-02-22T02:51:11Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Generalized Zero and Few-Shot Transfer for Facial Forgery Detection [3.8073142980733]
  We propose a new transfer learning approach to address the problem of zero and few-shot transfer in the context of forgery detection. We find this learning strategy to be surprisingly effective at domain transfer compared to a traditional classification or even state-of-the-art domain adaptation/few-shot learning methods.
  arXiv  Detail & Related papers  (2020-06-21T18:10:52Z)
• Deep Residual Flow for Out of Distribution Detection [27.218308616245164]
  We present a novel approach that improves upon the state-of-the-art by leveraging an expressive density model based on normalizing flows. We demonstrate the effectiveness of our method in ResNet and DenseNet architectures trained on various image datasets.
  arXiv  Detail & Related papers  (2020-01-15T16:38:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.