Decorr: Environment partitioning for invariant learning and ood generalization
Invariant learning methods try to find an invariant predictor across several environments and
have become popular in OOD generalization. However, in situations where environments do …
have become popular in OOD generalization. However, in situations where environments do …
Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is
caused by the uneven temporal distribution of the target moments for samples with similar …
caused by the uneven temporal distribution of the target moments for samples with similar …
Robustness, Evaluation and Adaptation of Machine Learning Models in the Wild
V Piratla - arXiv preprint arXiv:2303.02781, 2023 - arxiv.org
Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML
models perform exceedingly well when test examples are similar to train examples …
models perform exceedingly well when test examples are similar to train examples …
Self-supervised knowledge distillation in counterfactual learning for VQA
As a popular cross-modal reasoning task, Visual Question Answering (VQA) has achieved
great progress in recent years. However, the issue of language bias has always affected the …
great progress in recent years. However, the issue of language bias has always affected the …
On Leakage in Machine Learning Pipelines
Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity
stems from the promise of sample-level prediction with applications across a variety of fields …
stems from the promise of sample-level prediction with applications across a variety of fields …
Methods for Estimating and improving robustness of language models
M Štefánik - arXiv preprint arXiv:2206.08446, 2022 - arxiv.org
Despite their outstanding performance, large language models (LLMs) suffer notorious flaws
related to their preference for simple, surface-level textual relations over full semantic …
related to their preference for simple, surface-level textual relations over full semantic …
ASPIRE: Language-Guided Augmentation for Robust Image Classification
Neural image classifiers can often learn to make predictions by overly relying on non-
predictive features that are spuriously correlated with the class labels in the training data …
predictive features that are spuriously correlated with the class labels in the training data …
[HTML][HTML] Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
Abstract Deep Neural Networks (DNNs) are prone to learning spurious features that
correlate with the label during training but are irrelevant to the learning problem. This hurts …
correlate with the label during training but are irrelevant to the learning problem. This hurts …
Frustratingly Easy Environment Discovery for Invariant Learning
Standard training via empirical risk minimization may result in making predictions that overly
rely on spurious correlations. This can degrade the generalization to out-of-distribution …
rely on spurious correlations. This can degrade the generalization to out-of-distribution …
Look beyond bias with entropic adversarial data augmentation
T Duboudin, E Dellandréa, C Abgrall… - 2022 26th …, 2022 - ieeexplore.ieee.org
Deep neural networks do not discriminate between spurious and causal patterns, and will
only learn the most predictive ones while ignoring the others. This shortcut learning …
only learn the most predictive ones while ignoring the others. This shortcut learning …