Robustness via Cross-Domain Ensembles

• URL: http://arxiv.org/abs/2103.10919v1
• Date: Fri, 19 Mar 2021 17:28:03 GMT
• Title: Robustness via Cross-Domain Ensembles
• Authors: Teresa Yeo, O\u{g}uzhan Fatih Kar, Amir Zamir
• Abstract summary: We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues and ensembling them into one strong prediction.
• Score: 0.5801044612920816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are performed using multiple tasks and datasets (Taskonomy, Replica, ImageNet, CIFAR) under a wide range of adversarial and non-adversarial distribution shifts which demonstrate the proposed method is considerably more robust than its standard learning counterpart, conventional deep ensembles, and several other baselines.

Related papers

• Distributionally Robust Machine Learning with Multi-source Data [6.383451076043423]
  We introduce a group distributionally robust prediction model to optimize an adversarial reward about explained variance with respect to a class of target distributions. Compared to classical empirical risk minimization, the proposed robust prediction model improves the prediction accuracy for target populations with distribution shifts. We demonstrate the performance of our proposed group distributionally robust method on simulated and real data with random forests and neural networks as base-learning algorithms.
  arXiv  Detail & Related papers  (2023-09-05T13:19:40Z)
• Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
  We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
  arXiv  Detail & Related papers  (2023-08-03T12:43:21Z)
• Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport [89.61692654941106]
  We propose a new approach to predicting such mass flow over time using optimal transport. We apply our approach to the task of predicting how communities will evolve over time in social network settings.
  arXiv  Detail & Related papers  (2023-03-14T07:25:44Z)
• End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps [29.67295706224478]
  In this paper, we aim to forecast a future trajectory distribution of a moving agent in the real world, given the social scene images and historical trajectories. We learn the distribution with symmetric cross-entropy using occupancy grid maps as an explicit and scene-compliant approximation to the ground-truth distribution. In experiments, our method achieves state-of-the-art performance on the Stanford Drone dataset and Intersection Drone dataset.
  arXiv  Detail & Related papers  (2022-03-31T09:24:32Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
  We propose a neural network-based system to predict human trajectory in crowds. We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual. Our architecture is tested on the interaction-centric benchmark TrajNet++.
  arXiv  Detail & Related papers  (2021-05-07T09:22:34Z)
• Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration [2.8935588665357077]
  We propose an efficient yet general modelling approach for obtaining well-calibrated, trustworthy probabilities for samples obtained after a domain shift. We introduce a new training strategy combining an entropy-encouraging loss term with an adversarial calibration loss term and demonstrate that this results in well-calibrated and technically trustworthy predictions.
  arXiv  Detail & Related papers  (2020-12-20T13:39:29Z)
• Uncertainty Estimation and Sample Selection for Crowd Counting [87.29137075538213]
  We present a method for image-based crowd counting that can predict a crowd density map together with the uncertainty values pertaining to the predicted density map. A key advantage of our method over existing crowd counting methods is its ability to quantify the uncertainty of its predictions. We show that our sample selection strategy drastically reduces the amount of labeled data needed to adapt a counting network trained on a source domain to the target domain.
  arXiv  Detail & Related papers  (2020-09-30T03:40:07Z)
• Calibrated Adversarial Refinement for Stochastic Semantic Segmentation [5.849736173068868]
  We present a strategy for learning a calibrated predictive distribution over semantic maps, where the probability associated with each prediction reflects its ground truth correctness likelihood. We demonstrate the versatility and robustness of the approach by achieving state-of-the-art results on the multigrader LIDC dataset and on a modified Cityscapes dataset with injected ambiguities. We show that the core design can be adapted to other tasks requiring learning a calibrated predictive distribution by experimenting on a toy regression dataset.
  arXiv  Detail & Related papers  (2020-06-23T16:39:59Z)
• Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation [25.97333838935589]
  Uncertainty estimates are an important tool for helping autonomous agents or human decision makers understand and leverage predictive models. Existing algorithms can overestimate certainty, possibly yielding a false sense of confidence in the predictive model.
  arXiv  Detail & Related papers  (2020-02-29T20:31:04Z)

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.