Related papers: Finding and Fixing Spurious Patterns with Explanat…

Accuracy is one of the basic principles of journalism. However, it is increasingly hard to manage due to the diversity of news media. Some editors of online news tend to use catchy headlines which trick readers into clicking. These…

Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Classification and characterization of variable phenomena and transient phenomena are critical for astrophysics and cosmology. These objects are commonly studied using photometric time series or spectroscopic data. Given that many ongoing…

Despite of the recent success of neural networks for human pose estimation, current approaches are limited to pose estimation of a single person and cannot handle humans in groups or crowds. In this work, we propose a method that estimates…

We present "PATRED", a technique that uses the addition of redundant information to facilitate the detection of specific, generally described patterns in line-charts during the visual exploration of the charts. We compared different…

Fine-tuning a pretrained language model on a curated dataset can produce spurious correlations between the fine-tuning task and unintended latent factors -- such as misaligned personas or political slant -- that the curation procedure has…

Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed method can not only successfully learn the clean target…

Existing methods for pixel-wise labelling tasks generally disregard the underlying structure of labellings, often leading to predictions that are visually implausible. While incorporating structure into the model should improve prediction…

We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. We show that imperceptible additive perturbations can significantly alter the disparity map, and…

A new Bayesian approach to linear system identification has been proposed in a series of recent papers. The main idea is to frame linear system identification as predictor estimation in an infinite dimensional space, with the aid of…

The problem of pattern selection arises when the evolution equations have many solutions, whereas observed patterns constitute a much more restricted set. An approach is advanced for treating the problem of pattern selection by defining the…

Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query. Contrary to object detection, no prior information nor predefined class is given about the…

A new statistical procedure, based on a modified spline basis, is proposed to identify the linear components in the panel data model with fixed effects. Under some mild assumptions, the proposed procedure is shown to consistently estimate…

The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle…

Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address…

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work proposes MaskTune, a…

Model transformations operate on models conforming to precisely defined metamodels. Consequently, it often seems relatively easy to chain them: the output of a transformation may be given as input to a second one if metamodels match.…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks…