Related papers: Nuisances via Negativa: Adjusting for Spurious Cor…
Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hinder generalization.…
We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label…
Humans exhibit disagreement during data labeling. We term this disagreement as human label uncertainty. In this work, we study the ramifications of human label uncertainty (HLU). Our evaluation of existing uncertainty estimation algorithms,…
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing…
Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…
One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the…
Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the…
While learning with limited labelled data can improve performance when the labels are lacking, it is also sensitive to the effects of uncontrolled randomness introduced by so-called randomness factors (e.g., varying order of data). We…
Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…
Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex…
Neural networks trained with stochastic gradient descent exhibit an inductive bias towards simpler decision boundaries, typically converging to a narrow family of functions, and often fail to capture more complex features. This phenomenon…
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. This leads to poor performance in real-world atypical…
Spurious correlations pose a major challenge for robust machine learning. Models trained with empirical risk minimization (ERM) may learn to rely on correlations between class labels and spurious attributes, leading to poor performance on…
Humans and other animals base their decisions on noisy sensory input. Much work has therefore been devoted to understanding the computations that underly such decisions. The problem has been studied in a variety of tasks and with stimuli of…
In supervised learning, low quality annotations lead to poorly performing classification and detection models, while also rendering evaluation unreliable. This is particularly apparent on temporal data, where annotation quality is affected…
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…
While existing social bot detectors perform well on benchmarks, their robustness across diverse real-world scenarios remains limited due to unclear ground truth and varied misleading cues. In particular, the impact of shortcut learning,…
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature…
Neural network models have recently received heated research attention in the natural language processing community. Compared with traditional models with discrete features, neural models have two main advantages. First, they take…
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…