Explainable image classification: The journey so far and the road ahead
Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address
the interpretability challenges posed by complex machine learning models. In this survey …
the interpretability challenges posed by complex machine learning models. In this survey …
Automated classification of model errors on imagenet
While the ImageNet dataset has been driving computer vision research over the past
decade, significant label noise and ambiguity have made top-1 accuracy an insufficient …
decade, significant label noise and ambiguity have made top-1 accuracy an insufficient …
Masking strategies for background bias removal in computer vision models
Abstract Models for fine-grained image classification tasks, where the difference between
some classes can be extremely subtle and the number of samples per class tends to be low …
some classes can be extremely subtle and the number of samples per class tends to be low …
Identifying Systematic Errors in Object Detectors with the SCROD Pipeline
The identification and removal of systematic errors in object detectors can be a prerequisite
for their deployment in safety-critical applications like automated driving and robotics. Such …
for their deployment in safety-critical applications like automated driving and robotics. Such …
Fast diffusion-based counterfactuals for shortcut removal and generation
Shortcut learning is when a model–eg a cardiac disease classifier–exploits correlations
between the target label and a spurious shortcut feature, eg a pacemaker, to predict the …
between the target label and a spurious shortcut feature, eg a pacemaker, to predict the …
Clarify: Improving model robustness with natural language corrections
The standard way to teach models is by feeding them lots of data. However, this approach
often teaches models incorrect ideas because they pick up on misleading signals in the …
often teaches models incorrect ideas because they pick up on misleading signals in the …
Spuriousness-Aware Meta-Learning for Learning Robust Classifiers
Spurious correlations are brittle associations between certain attributes of inputs and target
variables, such as the correlation between an image background and an object class. Deep …
variables, such as the correlation between an image background and an object class. Deep …
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
Abstract Deep Neural Networks are prone to learning and relying on spurious correlations in
the training data which for high-risk applications can have fatal consequences. Various …
the training data which for high-risk applications can have fatal consequences. Various …
Antibody domainbed: Out-of-distribution generalization in therapeutic protein design
Machine learning (ML) has demonstrated significant promise in accelerating drug design.
Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model …
Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model …
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Abstract Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks
yet they often struggle with reliable uncertainty quantification-a critical requirement for real …
yet they often struggle with reliable uncertainty quantification-a critical requirement for real …