Related papers: Focusing Image Generation to Mitigate Spurious Cor…

Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats with bed backgrounds can fail to predict the existence of cats…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…

Scene Graph Generation (SGG) aims to detect all the visual relation triplets $<$\texttt{sub}, \texttt{pred}, \texttt{obj}$>$ in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and…

Diffusion models have gained prominence as state-of-the-art techniques for synthesizing images and videos, particularly due to their ability to scale effectively with large datasets. Recent studies have uncovered that these extensive…

We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's reliance on spurious signals in the training data. Specifically,…

Improving the performance on an imbalanced training set is one of the main challenges in nowadays Machine Learning. One way to augment and thus re-balance the image dataset is through existing deep generative models, like class-conditional…

Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images…

Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This…

Spurious features associated with class labels can lead image classifiers to rely on shortcuts that don't generalize well to new domains. This is especially problematic in medical settings, where biased models fail when applied to different…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive…

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address…

Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Generative Adversarial Networks (GAN) have been widely investigated for image synthesis based on their powerful representation learning ability. In this work, we explore the StyleGAN and its application of synthetic food image generation.…

Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs). Synthetic data from…

Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…