ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks

• URL: http://arxiv.org/abs/2201.02263v1
• Date: Thu, 6 Jan 2022 22:03:50 GMT
• Title: ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks
• Authors: WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, Alireza Bab-Hadiashar, David Suter
• Abstract summary: We show that learning of feature representations in stereo matching networks is heavily influenced by synthetic data artefacts. We propose an Information-Theoretic Shortcut Avoidance(ITSA) approach to automatically restrict shortcut-related information from being encoded into the feature representations. We show that using this method, state-of-the-art stereo matching networks that are trained purely on synthetic data can effectively generalize to challenging and previously unseen real data scenarios.
• Score: 14.306250516592305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. In this paper, we attempt to unfold an important factor that hinders the networks from generalizing across domains: through the lens of shortcut learning. We demonstrate that the learning of feature representations in stereo matching networks is heavily influenced by synthetic data artefacts (shortcut attributes). To mitigate this issue, we propose an Information-Theoretic Shortcut Avoidance~(ITSA) approach to automatically restrict shortcut-related information from being encoded into the feature representations. As a result, our proposed method learns robust and shortcut-invariant features by minimizing the sensitivity of latent features to input variations. To avoid the prohibitive computational cost of direct input sensitivity optimization, we propose an effective yet feasible algorithm to achieve robustness. We show that using this method, state-of-the-art stereo matching networks that are trained purely on synthetic data can effectively generalize to challenging and previously unseen real data scenarios. Importantly, the proposed method enhances the robustness of the synthetic trained networks to the point that they outperform their fine-tuned counterparts (on real data) for challenging out-of-domain stereo datasets.

Related papers

• Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning [49.417414031031264]
  This paper studies learning fair encoders in a self-supervised learning setting. All data are unlabeled and only a small portion of them are annotated with sensitive attributes.
  arXiv  Detail & Related papers  (2024-06-09T08:11:12Z)
• Automatic Input Feature Relevance via Spectral Neural Networks [0.9236074230806581]
  We propose a novel method to estimate the relative importance of the input components for a Deep Neural Network. This is achieved by leveraging on a spectral re-parametrization of the optimization process. The technique is successfully challenged against both synthetic and real data.
  arXiv  Detail & Related papers  (2024-06-03T10:39:12Z)
• Autosen: improving automatic wifi human sensing through cross-modal autoencoder [56.44764266426344]
  WiFi human sensing is highly regarded for its low-cost and privacy advantages in recognizing human activities. Traditional cross-modal methods, aimed at enabling self-supervised learning without labeled data, struggle to extract meaningful features from amplitude-phase combinations. We introduce AutoSen, an innovative automatic WiFi sensing solution that departs from conventional approaches.
  arXiv  Detail & Related papers  (2024-01-08T19:50:02Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Shortcut Detection with Variational Autoencoders [1.3174512123890016]
  We present a novel approach to detect shortcuts in image and audio datasets by leveraging variational autoencoders (VAEs) The disentanglement of features in the latent space of VAEs allows us to discover feature-target correlations in datasets and semi-automatically evaluate them for ML shortcuts. We demonstrate the applicability of our method on several real-world datasets and identify shortcuts that have not been discovered before.
  arXiv  Detail & Related papers  (2023-02-08T18:26:10Z)
• Localized Shortcut Removal [4.511561231517167]
  High performance on held-out test data does not necessarily indicate that a model generalizes or learns anything meaningful. This is often due to the existence of machine learning shortcuts - features in the data that are predictive but unrelated to the problem at hand. We use an adversarially trained lens to detect and eliminate highly predictive but semantically unconnected clues in images.
  arXiv  Detail & Related papers  (2022-11-24T13:05:33Z)
• Attention-based Adversarial Appearance Learning of Augmented Pedestrians [49.25430012369125]
  We propose a method to synthesize realistic data for the pedestrian recognition task. Our approach utilizes an attention mechanism driven by an adversarial loss to learn domain discrepancies. Our experiments confirm that the proposed adaptation method is robust to such discrepancies and reveals both visual realism and semantic consistency.
  arXiv  Detail & Related papers  (2021-07-06T15:27:00Z)
• Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning [14.497880004212979]
  We show that learning of features in the synthetic domain is heavily influenced by two "shortcuts" presented in the synthetic data. We will show that by removing such shortcuts, we can achieve domain robustness in the state-of-the-art stereo matching frameworks.
  arXiv  Detail & Related papers  (2021-06-15T23:22:54Z)
• Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
  We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting. We show that our method allows forgetting without having to trade off the model accuracy.
  arXiv  Detail & Related papers  (2020-12-24T19:34:56Z)
• Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence [8.110949636804772]
  Smartphones, wearables, and Internet of Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models. We propose a self-supervised approach termed textitscalogram-signal correspondence learning based on wavelet transform to learn useful representations from unlabeled sensor inputs. We extensively assess the quality of learned features with our multi-view strategy on diverse public datasets, achieving strong performance in all domains.
  arXiv  Detail & Related papers  (2020-07-25T21:59:17Z)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)

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.