In this report, we present the first place solution to the ECCV 2024 BRAVO Challenge, where a model is trained on Cityscapes and its robustness is evaluated on several out-of-distribution datasets. Our solution leverages the powerful representations learned by vision foundation models, by attaching a simple segmentation decoder to DINOv2 and fine-tuning the entire model. This approach outperforms more complex existing approaches, and achieves first place in the challenge. Our code is publicly available at https://github.com/tue-mps/benchmark-vfm-ss.

Gaussian graphical models (GGMs) are widely used for recovering the conditional independence structure among random variables. Recently, several key advances have been made to exploit an additional set of variables for better estimating the GGMs of the variables of interest. For example, in co-expression quantitative trait locus (eQTL) studies, both the mean expression level of genes as well as their pairwise conditional independence structure may be adjusted by genetic variants local to those genes. Existing methods to estimate covariate-adjusted GGMs either allow only the mean to depend on covariates or suffer from poor scaling assumptions due to the inherent non-convexity of simultaneously estimating the mean and precision matrix. In this paper, we propose a convex formulation that jointly estimates the covariate-adjusted mean and precision matrix by utilizing the natural parametrization of the multivariate Gaussian likelihood. This convexity yields theoretically better performance as the sparsity and dimension of the covariates grow large relative to the number of samples. We verify our theoretical results with numerical simulations and perform a reanalysis of an eQTL study of glioblastoma multiforme (GBM), an aggressive form of brain cancer.

In an era where artificial intelligence and machine learning algorithms increasingly impact human life, it is crucial to develop models that account for potential discrimination in their predictions. This paper tackles this problem by introducing a new classification tree algorithm using a novel splitting criterion that incorporates fairness adjustments into the tree-building process. The proposed method integrates a fairness-aware impurity measure that balances predictive accuracy with fairness across protected groups. By ensuring that each splitting node considers both the gain in classification error and the fairness, our algorithm encourages splits that mitigate discrimination. Importantly, in penalizing unfair splits, we account for the uncertainty in the fairness metric by utilizing its confidence interval instead of relying on its point estimate. Experimental results on benchmark and synthetic datasets illustrate that our method effectively reduces discriminatory predictions compared to traditional classification trees, without significant loss in overall accuracy.

This article improves the Transformer model based on swarm intelligence optimization algorithm, aiming to predict the emotions of employment related text content on American social media. Through text preprocessing, feature extraction, and vectorization, the text data was successfully converted into numerical data and imported into the model for training. The experimental results show that during the training process, the accuracy of the model gradually increased from 49.27% to 82.83%, while the loss value decreased from 0.67 to 0.35, indicating a significant improvement in the performance of the model on the training set. According to the confusion matrix analysis of the training set, the accuracy of the training set is 86.15%. The confusion matrix of the test set also showed good performance, with an accuracy of 82.91%. The accuracy difference between the training set and the test set is only 3.24%, indicating that the model has strong generalization ability. In addition, the evaluation of polygon results shows that the model performs well in classification accuracy, sensitivity, specificity, and area under the curve (AUC), with a Kappa coefficient of 0.66 and an F-measure of 0.80, further verifying the effectiveness of the model in social media sentiment analysis. The improved model proposed in this article not only improves the accuracy of sentiment recognition in employment related texts on social media, but also has important practical significance. This social media based data analysis method can not only capture social dynamics in a timely manner, but also promote decision-makers to pay attention to public concerns and provide data support for improving employment conditions.

Summary: The authors present a parameterized model that generalizes precision and recall to "range-based" anomaly detection. A range-based anomaly is defined as "an anomaly that occurs over a consecutive sequence of time points, where no non-anomalous data points exist between the beginning and the end of the anomaly". The model is carefully and precisely defined. Then it is evaluated by comparing it against the metric proposed in the Numenta Anomaly Benchmark. The authors conclude that their metric is superior to the NAB metric.

The paper theoretically studies the suitability of achieving a particular definition of fairness, equalized odds (which relates to the false positive rate), in the context of online learning with experts advise (Cesa-Bianchi et al. 2006). In particular, the authors show that achieving an online algorithm that jointly satisfies zero-regret and equalized odds is not possible. Afterward, they show that this is not the case when considering fairness in terms of the total number of errors per group. They also discuss that unfortunately this definition of fairness (also previously discussed in Zafar et al., 2017) is not realistic (or even fair) in many real-world scenarios. In the positive side, I believe that (im)possibility theoretical studies on when a fairness definition can be accomplished is definitely a major contribution to the field. However, I also believe that the paper has important gaps to be filled: 1) Their definition of online learning comes from the game theory literature and does not corresponds to the standard ML view on online learning.

I enjoyed reading this paper and thought it was very well written. The one negative about the paper is that the results presented are somewhat simplistic (the author's acknowledge this point directly). The paper considers an interesting recent effort (specifically in the paper "The Case for Learned Index Structures") to use predictive machine learning models to improve the performance of basic data structures. In particular, this work focuses on the standard Bloom filter for quickly detecting set membership, possibly with some false positives. "The Case for Learned Index Structures" suggests a "learned" bloom filter, which essentially uses a learning pre-filter to guess if an input query is in the set of interest.

Climate change communication on social media increasingly employs microtargeting strategies to effectively reach and influence specific demographic groups. This study presents a post-hoc analysis of microtargeting practices within climate campaigns by leveraging large language models (LLMs) to examine Facebook advertisements. Our analysis focuses on two key aspects: demographic targeting and fairness. We evaluate the ability of LLMs to accurately predict the intended demographic targets, such as gender and age group, achieving an overall accuracy of 88.55%. Furthermore, we instruct the LLMs to generate explanations for their classifications, providing transparent reasoning behind each decision. These explanations reveal the specific thematic elements used to engage different demographic segments, highlighting distinct strategies tailored to various audiences. Our findings show that young adults are primarily targeted through messages emphasizing activism and environmental consciousness, while women are engaged through themes related to caregiving roles and social advocacy. In addition to evaluating the effectiveness of LLMs in detecting microtargeted messaging, we conduct a comprehensive fairness analysis to identify potential biases in model predictions. Our findings indicate that while LLMs perform well overall, certain biases exist, particularly in the classification of senior citizens and male audiences. By showcasing the efficacy of LLMs in dissecting and explaining targeted communication strategies and by highlighting fairness concerns, this study provides a valuable framework for future research aimed at enhancing transparency, accountability, and inclusivity in social media-driven climate campaigns.

Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face significant challenges that, if unaddressed, can result in lasting negative impacts. Traditionally, speech and language assessments (SLA) have been conducted by skilled speech-language pathologists (SLPs), but there is a growing need for efficient and scalable SLA methods powered by artificial intelligence. This position paper presents a survey of existing techniques suitable for automating SLA pipelines, with an emphasis on adapting automatic speech recognition (ASR) models for children's speech, an overview of current SLAs and their automated counterparts to demonstrate the feasibility of AI-enhanced SLA pipelines, and a discussion of practical considerations, including accessibility and privacy concerns, associated with the deployment of AI-powered SLAs.

LIFT-PD is an innovative self-supervised learning framework developed for real-time detection of Freezing of Gait (FoG) in Parkinson's Disease (PD) patients, using a single triaxial accelerometer. It minimizes the reliance on large labeled datasets by applying a Differential Hopping Windowing Technique (DHWT) to address imbalanced data during training. Additionally, an Opportunistic Inference Module is used to reduce energy consumption by activating the model only during active movement periods. Extensive testing on publicly available datasets showed that LIFT-PD improved precision by 7.25% and accuracy by 4.4% compared to supervised models, while using 40% fewer labeled samples and reducing inference time by 67%. These findings make LIFT-PD a highly practical and energy-efficient solution for continuous, in-home monitoring of PD patients.