Related papers: SLIM: Spuriousness Mitigation with Minimal Human A…
Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than…
We introduce Projection-based Reduction of Implicit Spurious bias in vision-language Models (PRISM), a new data-free and task-agnostic solution for bias mitigation in VLMs like CLIP. VLMs often inherit and amplify biases in their training…
In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…
AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label…
Active learning (AL) is a human-and-model-in-the-loop paradigm that iteratively selects informative unlabeled data for human annotation, aiming to improve over random sampling. However, performing AL experiments with human annotations…
Medical image analysis using deep learning is often challenged by limited labeled data and high annotation costs. Fine-tuning the entire network in label-limited scenarios can lead to overfitting and suboptimal performance. Recently, prompt…
Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…
Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as…
Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems. However, click interactions inherently contain substantial noise, including accidental clicks, clickbait-induced interactions, and…
Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts. For this reason, weakly supervised learning aims at optimising machine learning models using weaker forms of annotations, such as…
Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…
To address the problem of NLP classifiers learning spurious correlations between training features and target labels, a common approach is to make the model's predictions invariant to these features. However, this can be counter-productive…
Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…
Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their scalability and usability in large scale deployments. In…
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied…
Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in…
Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…
We propose SLOT (Sample-specific Language Model Optimization at Test-time), a novel and parameter-efficient test-time inference approach that enhances a language model's ability to more accurately respond to individual prompts. Existing…
We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data one already has by…