Ghassan AlRegib

Mohit Prabhushankar, Kiran Kokilepersaud, Yash-yee Logan et al.

Clinical diagnosis of the eye is performed over multifarious data modalities including scalar clinical labels, vectorized biomarkers, two-dimensional fundus images, and three-dimensional Optical Coherence Tomography (OCT) scans. Clinical practitioners use all available data modalities for diagnosing and treating eye diseases like Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). Enabling usage of machine learning algorithms within the ophthalmic medical domain requires research into the relationships and interactions between all relevant data over a treatment period. Existing datasets are limited in that they neither provide data nor consider the explicit relationship modeling between the data modalities. In this paper, we introduce the Ophthalmic Labels for Investigating Visual Eye Semantics (OLIVES) dataset that addresses the above limitation. This is the first OCT and near-IR fundus dataset that includes clinical labels, biomarker labels, disease labels, and time-series patient treatment information from associated clinical trials. The dataset consists of 1268 near-IR fundus images each with at least 49 OCT scans, and 16 biomarkers, along with 4 clinical labels and a disease diagnosis of DR or DME. In total, there are 96 eyes' data averaged over a period of at least two years with each eye treated for an average of 66 weeks and 7 injections. We benchmark the utility of OLIVES dataset for ophthalmic data as well as provide benchmarks and concrete research directions for core and emerging machine learning paradigms within medical image analysis.

Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar et al.

Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eigenspectra), and modality collapse where one dominant modality overwhelms the other. Applications like human action anticipation that require fusing multifarious sensor data are hindered by both feature and modality collapse. However, existing methods attempt to counter feature collapse and modality collapse separately. This is because there is no unifying framework that efficiently addresses feature and modality collapse in conjunction. In this paper, we posit the utility of effective rank as an informative measure that can be utilized to quantify and counter both the representation collapses. We propose \textit{Rank-enhancing Token Fuser}, a theoretically grounded fusion framework that selectively blends less informative features from one modality with complementary features from another modality. We show that our method increases the effective rank of the fused representation. To address modality collapse, we evaluate modality combinations that mutually increase each others' effective rank. We show that depth maintains representational balance when fused with RGB, avoiding modality collapse. We validate our method on action anticipation, where we present \texttt{R3D}, a depth-informed fusion framework. Extensive experiments on NTURGBD, UTKinect, and DARai demonstrate that our approach significantly outperforms prior state-of-the-art methods by up to 3.74\%. Our code is available at: \href{https://github.com/olivesgatech/R3D}{https://github.com/olivesgatech/R3D}.

Mohit Prabhushankar, Ghassan AlRegib

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The second stage is a slower reflection stage where we ask the network to reflect on its feed-forward decision by considering and evaluating all available choices. Together, we term the two stages as introspective learning. We use gradients of trained neural networks as a measurement of this reflection. A simple three-layered Multi Layer Perceptron is used as the second stage that predicts based on all extracted gradient features. We perceptually visualize the post-hoc explanations from both stages to provide a visual grounding to introspection. For the application of recognition, we show that an introspective network is 4% more robust and 42% less prone to calibration errors when generalizing to noisy data. We also illustrate the value of introspective networks in downstream tasks that require generalizability and calibration including active learning, out-of-distribution detection, and uncertainty estimation. Finally, we ground the proposed machine introspection to human introspection for the application of image quality assessment.

William Stevens, Mohit Prabhushankar, Ghassan AlRegib

Epistemic uncertainty estimation is essential for identifying regions where deep learning system outputs may be unreliable. However, existing approaches require computationally expensive ensemble methods or multiple stochastic forward passes, limiting their scalability to dense prediction tasks like segmentation. We propose Resolution-Aggregated Decoder Mutual Information (RADMI), a single-pass method that estimates prediction uncertainty by measuring mutual information (MI) between consecutive decoder layers in segmentation networks. We observe that elevated inter-layer MI correlates with prediction uncertainty, as the network must integrate conflicting contextual information at ambiguous regions such as class boundaries. Evaluating on a seismic facies segmentation benchmark, RADMI achieves the highest correlation with deep ensemble uncertainty among all single-pass methods, outperforming the next-best baselines by 5.5% in Pearson and 10.7% in Spearman correlation coefficients. Compared to baselines that either lack spatial precision or demand significant computational overhead, RADMI yields sharp, boundary-localized uncertainty maps without architectural modifications. Our results suggest that linear aggregation of normalized information flow provides a principled and efficient proxy for prediction uncertainty in encoder-decoder architectures.

Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain. As a result, there oftentimes exists a non-trivial quantity of unlabeled data that is left unused simply because traditional deep learning methods rely on access to fully labeled volumes. To rectify this problem, contrastive learning approaches have been proposed that use a self-supervised methodology in order to learn useful representations from unlabeled data. However, traditional contrastive learning approaches are based on assumptions from the domain of natural images that do not make use of seismic context. In order to incorporate this context within contrastive learning, we propose a novel positive pair selection strategy based on the position of slices within a seismic volume. We show that the learnt representations from our method out-perform a state of the art contrastive learning methodology in a semantic segmentation task.

Gukyeong Kwon, Ghassan AlRegib

Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by overfitting on only available seen class data during training. To overcome this issue, we propose a two-stream autoencoder-based gating model for GZSL. Our gating model predicts whether the query data is from seen classes or unseen classes, and utilizes separate seen and unseen experts to predict the class independently from each other. This framework avoids comparing the biased prediction scores for seen classes with the prediction scores for unseen classes. In particular, we measure the distance between visual and attribute representations in the latent space and the cross-reconstruction space of the autoencoder. These distances are utilized as complementary features to characterize unseen classes at different levels of data abstraction. Also, the two-stream autoencoder works as a unified framework for the gating model and the unseen expert, which makes the proposed method computationally efficient. We validate our proposed method in four benchmark image recognition datasets. In comparison with other state-of-the-art methods, we achieve the best harmonic mean accuracy in SUN and AWA2, and the second best in CUB and AWA1. Furthermore, our base model requires at least 20% less number of model parameters than state-of-the-art methods relying on generative models.

Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib

We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during training -- in gradient generation to probe the effective expressivity of neural networks. Gradients depict the amount of change required for a model to properly represent given inputs, providing insight into the representational power of the model established by network architectural properties as well as training data. By introducing a label of different design, we remove the dependency on ground truth labels for gradient generation during inference. We show that our gradient-based approach allows for capturing the anomaly in inputs based on the effective expressivity of the models with no hyperparameter tuning or additional processing, and outperforms state-of-the-art methods for adversarial and out-of-distribution detection.

Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib et al.

In active learning, acquisition functions define informativeness directly on the representation position within the model manifold. However, for most machine learning models (in particular neural networks) this representation is not fixed due to the training pool fluctuations in between active learning rounds. Therefore, several popular strategies are sensitive to experiment parameters (e.g. architecture) and do not consider model robustness to out-of-distribution settings. To alleviate this issue, we propose a grounded second-order definition of information content and sample importance within the context of active learning. Specifically, we define importance by how often a neural network "forgets" a sample during training - artifacts of second order representation shifts. We show that our definition produces highly accurate importance scores even when the model representations are constrained by the lack of training data. Motivated by our analysis, we develop Gaussian Switch Sampling (GauSS). We show that GauSS is setup agnostic and robust to anomalous distributions with exhaustive experiments on three in-distribution benchmarks, three out-of-distribution benchmarks, and three different architectures. We report an improvement of up to 5% when compared against four popular query strategies.

Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib

This paper considers deep out-of-distribution active learning. In practice, fully trained neural networks interact randomly with out-of-distribution (OOD) inputs and map aberrant samples randomly within the model representation space. Since data representations are direct manifestations of the training distribution, the data selection process plays a crucial role in outlier robustness. For paradigms such as active learning, this is especially challenging since protocols must not only improve performance on the training distribution most effectively but further render a robust representation space. However, existing strategies directly base the data selection on the data representation of the unlabeled data which is random for OOD samples by definition. For this purpose, we introduce forgetful active learning with switch events (FALSE) - a novel active learning protocol for out-of-distribution active learning. Instead of defining sample importance on the data representation directly, we formulate "informativeness" with learning difficulty during training. Specifically, we approximate how often the network "forgets" unlabeled samples and query the most "forgotten" samples for annotation. We report up to 4.5\% accuracy improvements in over 270 experiments, including four commonly used protocols, two OOD benchmarks, one in-distribution benchmark, and three different architectures.

Jinsol Lee, Charlie Lehman, Mohit Prabhushankar et al.

We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. The notion of data-dependent capacity allows for analyzing the knowledge base of a model populated by learned features from training data. We define purview as the additional capacity necessary to characterize inference samples that differ from the training data. To probe the purview of a network, we utilize gradients to measure the amount of change required for the model to characterize the given inputs more accurately. To eliminate the dependency on ground-truth labels in generating gradients, we introduce confounding labels that are formulated by combining multiple categorical labels. We demonstrate that our gradient-based approach can effectively differentiate inputs that cannot be accurately represented with learned features. We utilize our approach in applications of detecting anomalous inputs, including out-of-distribution, adversarial, and corrupted samples. Our approach requires no hyperparameter tuning or additional data processing and outperforms state-of-the-art methods by up to 2.7%, 19.8%, and 35.6% of AUROC scores, respectively.

Zoe Fowler, Kiran Kokilepersaud, Mohit Prabhushankar et al.

This paper presents a novel approach to active learning that takes into account the non-independent and identically distributed (non-i.i.d.) structure of a clinical trial setting. There exists two types of clinical trials: retrospective and prospective. Retrospective clinical trials analyze data after treatment has been performed; prospective clinical trials collect data as treatment is ongoing. Typically, active learning approaches assume the dataset is i.i.d. when selecting training samples; however, in the case of clinical trials, treatment results in a dependency between the data collected at the current and past visits. Thus, we propose prospective active learning to overcome the limitations present in traditional active learning methods and apply it to disease detection in optical coherence tomography (OCT) images, where we condition on the time an image was collected to enforce the i.i.d. assumption. We compare our proposed method to the traditional active learning paradigm, which we refer to as retrospective in nature. We demonstrate that prospective active learning outperforms retrospective active learning in two different types of test settings.

Yash-yee Logan, Ryan Benkert, Ahmad Mustafa et al.

This paper considers making active learning more sensible from a medical perspective. In practice, a disease manifests itself in different forms across patient cohorts. Existing frameworks have primarily used mathematical constructs to engineer uncertainty or diversity-based methods for selecting the most informative samples. However, such algorithms do not present themselves naturally as usable by the medical community and healthcare providers. Thus, their deployment in clinical settings is very limited, if any. For this purpose, we propose a framework that incorporates clinical insights into the sample selection process of active learning that can be incorporated with existing algorithms. Our medically interpretable active learning framework captures diverse disease manifestations from patients to improve generalization performance of OCT classification. After comprehensive experiments, we report that incorporating patient insights within the active learning framework yields performance that matches or surpasses five commonly used paradigms on two architectures with a dataset having imbalanced patient distributions. Also, the framework integrates within existing medical practices and thus can be used by healthcare providers.

Kiran Kokilepersaud, Yash-Yee Logan, Ryan Benkert et al.

In this paper, we introduce the FOCAL (Ford-OLIVES Collaboration on Active Learning) dataset which enables the study of the impact of annotation-cost within a video active learning setting. Annotation-cost refers to the time it takes an annotator to label and quality-assure a given video sequence. A practical motivation for active learning research is to minimize annotation-cost by selectively labeling informative samples that will maximize performance within a given budget constraint. However, previous work in video active learning lacks real-time annotation labels for accurately assessing cost minimization and instead operates under the assumption that annotation-cost scales linearly with the amount of data to annotate. This assumption does not take into account a variety of real-world confounding factors that contribute to a nonlinear cost such as the effect of an assistive labeling tool and the variety of interactions within a scene such as occluded objects, weather, and motion of objects. FOCAL addresses this discrepancy by providing real annotation-cost labels for 126 video sequences across 69 unique city scenes with a variety of weather, lighting, and seasonal conditions. We also introduce a set of conformal active learning algorithms that take advantage of the sequential structure of video data in order to achieve a better trade-off between annotation-cost and performance while also reducing floating point operations (FLOPS) overhead by at least 77.67%. We show how these approaches better reflect how annotations on videos are done in practice through a sequence selection framework. We further demonstrate the advantage of these approaches by introducing two performance-cost metrics and show that the best conformal active learning method is cheaper than the best traditional active learning method by 113 hours.

Kiran Kokilepersaud, Mohit Prabhushankar, Yavuz Yarici et al.

In this work, we present a methodology to shape a fisheye-specific representation space that reflects the interaction between distortion and semantic context present in this data modality. Fisheye data has the wider field of view advantage over other types of cameras, but this comes at the expense of high radial distortion. As a result, objects further from the center exhibit deformations that make it difficult for a model to identify their semantic context. While previous work has attempted architectural and training augmentation changes to alleviate this effect, no work has attempted to guide the model towards learning a representation space that reflects this interaction between distortion and semantic context inherent to fisheye data. We introduce an approach to exploit this relationship by first extracting distortion class labels based on an object's distance from the center of the image. We then shape a backbone's representation space with a weighted contrastive loss that constrains objects of the same semantic class and distortion class to be close to each other within a lower dimensional embedding space. This backbone trained with both semantic and distortion information is then fine-tuned within an object detection setting to empirically evaluate the quality of the learnt representation. We show this method leads to performance improvements by as much as 1.1% mean average precision over standard object detection strategies and .6% improvement over other state of the art representation learning approaches.

Chen Zhou, Mohit Prabhushankar, Ghassan AlRegib

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, with the presence of HLU, indicates the limitations of existing uncertainty metrics and algorithms themselves in response to HLU. Meanwhile, we observe undue effects in predictive uncertainty and generalizability. To mitigate the undue effects, we introduce a novel natural scene statistics (NSS) based label dilution training scheme without requiring massive human labels. Specifically, we first select a subset of samples with low perceptual quality ranked by statistical regularities of images. We then assign separate labels to each sample in this subset to obtain a training set with diluted labels. Our experiments and analysis demonstrate that training with NSS-based label dilution alleviates the undue effects caused by HLU.

Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety of labels for data that serve different purposes at different stages of a diagnostic and treatment process. Clinical labels and biomarker labels are two examples. In general, clinical labels are easier to obtain in larger quantities because they are regularly collected during routine clinical care, while biomarker labels require expert analysis and interpretation to obtain. Within the field of ophthalmology, previous work has shown that clinical values exhibit correlations with biomarker structures that manifest within optical coherence tomography (OCT) scans. We exploit this relationship between clinical and biomarker data to improve performance for biomarker classification. This is accomplished by leveraging the larger amount of clinical data as pseudo-labels for our data without biomarker labels in order to choose positive and negative instances for training a backbone network with a supervised contrastive loss. In this way, a backbone network learns a representation space that aligns with the clinical data distribution available. Afterwards, we fine-tune the network trained in this manner with the smaller amount of biomarker labeled data with a cross-entropy loss in order to classify these key indicators of disease directly from OCT scans. Our method is shown to outperform state of the art self-supervised methods by as much as 5% in terms of accuracy on individual biomarker detection.

Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib

Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address this issue by steering model's attention allocation, implicitly assuming that all modalities provide sufficient information. However, attention only determines where the model focuses, and cannot enrich information that is missing or ambiguous. In the real world, input modalities often differ in information density and their signal-to-noise ratios. In such cases, simply adjusting model's attention does not resolve the underlying lack of information. In this paper, we propose \textsc{MoIR}: \textit{Multi-modal Information Router}, an information-level fusion method that explicitly reduces information disparity prior to fusion. \textsc{MoIR} identifies less informative tokens and routes complementary information from a stronger modality, constructing information-dense token representations before they are processed by a large language model. By modifying information availability, \textsc{MoIR} enables reliable shifts in modality dominance, even when one modality is degraded. We evaluate \textsc{MoIR} on three widely used multi-modal benchmarks across multiple model backbones. Experimental results show that \textsc{MoIR} consistently demonstrates more balanced modality contribution, and improves robustness and downstream performance, particularly even under modality degradation. These findings demonstrate that explicitly modifying cross-modal information is an effective and complementary strategy for mitigating modality dominance in multi-modal reasoning models.

Mohit Prabhushankar, Ghassan AlRegib

This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done by reducing free energy and its associated surprisal during training. However, the bottom-up inference nature of supervised networks is a passive process that renders them fallible to noise. In this paper, we provide a thorough background of supervised neural networks, both generative and discriminative, and discuss their functionality from the perspective of free energy principle. We then provide a framework for introducing action during inference. We introduce a new measurement called stochastic surprisal that is a function of the network, the input, and any possible action. This action can be any one of the outputs that the neural network has learnt, thereby lending stochasticity to the measurement. Stochastic surprisal is validated on two applications: Image Quality Assessment and Recognition under noisy conditions. We show that, while noise characteristics are ignored to make robust recognition, they are analyzed to estimate image quality scores. We apply stochastic surprisal on two applications, three datasets, and as a plug-in on twelve networks. In all, it provides a statistically significant increase among all measures. We conclude by discussing the implications of the proposed stochastic surprisal in other areas of cognitive psychology including expectancy-mismatch and abductive reasoning.

Ahmad Mustafa, Ghassan AlRegib

Deep learning can extract rich data representations if provided sufficient quantities of labeled training data. For many tasks however, annotating data has significant costs in terms of time and money, owing to the high standards of subject matter expertise required, for example in medical and geophysical image interpretation tasks. Active Learning can identify the most informative training examples for the interpreter to train, leading to higher efficiency. We propose an Active learning method based on jointly learning representations for supervised and unsupervised tasks. The learned manifold structure is later utilized to identify informative training samples most dissimilar from the learned manifold from the error profiles on the unsupervised task. We verify the efficiency of the proposed method on a seismic facies segmentation dataset from the Netherlands F3 block survey, significantly outperforming contemporary methods to achieve the highest mean Intersection-Over-Union value of 0.773.

Mohit Prabhushankar, Kiran Kokilepersaud, Jorge Quesada et al.

Crowdsourcing annotations has created a paradigm shift in the availability of labeled data for machine learning. Availability of large datasets has accelerated progress in common knowledge applications involving visual and language data. However, specialized applications that require expert labels lag in data availability. One such application is fault segmentation in subsurface imaging. Detecting, tracking, and analyzing faults has broad societal implications in predicting fluid flows, earthquakes, and storing excess atmospheric CO$_2$. However, delineating faults with current practices is a labor-intensive activity that requires precise analysis of subsurface imaging data by geophysicists. In this paper, we propose the $\texttt{CRACKS}$ dataset to detect and segment faults in subsurface images by utilizing crowdsourced resources. We leverage Amazon Mechanical Turk to obtain fault delineations from sections of the Netherlands North Sea subsurface images from (i) $26$ novices who have no exposure to subsurface data and were shown a video describing and labeling faults, (ii) $8$ practitioners who have previously interacted and worked on subsurface data, (iii) one geophysicist to label $7636$ faults in the region. Note that all novices, practitioners, and the expert segment faults on the same subsurface volume with disagreements between and among the novices and practitioners. Additionally, each fault annotation is equipped with the confidence level of the annotator. The paper provides benchmarks on detecting and segmenting the expert labels, given the novice and practitioner labels. Additional details along with the dataset links and codes are available at $\href{https://alregib.ece.gatech.edu/cracks-crowdsourcing-resources-for-analysis-and-categorization-of-key-subsurface-faults/}{link}$.

Prithwijit Chowdhury, Ahmad Mustafa, Mohit Prabhushankar et al.

In geophysics, hydrocarbon prospect risking involves assessing the risks associated with hydrocarbon exploration by integrating data from various sources. Machine learning-based classifiers trained on tabular data have been recently used to make faster decisions on these prospects. The lack of transparency in the decision-making processes of such models has led to the emergence of explainable AI (XAI). LIME and SHAP are two such examples of these XAI methods which try to generate explanations of a particular decision by ranking the input features in terms of importance. However, explanations of the same scenario generated by these two different explanation strategies have shown to disagree or be different, particularly for complex data. This is because the definitions of "importance" and "relevance" differ for different explanation strategies. Thus, grounding these ranked features using theoretically backed causal ideas of necessity and sufficiency can prove to be a more reliable and robust way to improve the trustworthiness of the concerned explanation strategies.We propose a unified framework to generate counterfactuals as well as quantify necessity and sufficiency and use these to perform a robustness evaluation of the explanations provided by LIME and SHAP on high dimensional structured prospect risking data. This robustness test gives us deeper insights into the models capabilities to handle erronous data and which XAI module works best in pair with which model for our dataset for hydorcarbon indication.

Ryan Benkert, Oluwaseun Joseph Aribido, Ghassan AlRegib

In recent years, deep neural networks have significantly impacted the seismic interpretation process. Due to the simple implementation and low interpretation costs, deep neural networks are an attractive component for the common interpretation pipeline. However, neural networks are frequently met with distrust due to their property of producing semantically incorrect outputs when exposed to sections the model was not trained on. We address this issue by explaining model behaviour and improving generalization properties through example forgetting: First, we introduce a method that effectively relates semantically malfunctioned predictions to their respectful positions within the neural network representation manifold. More concrete, our method tracks how models "forget" seismic reflections during training and establishes a connection to the decision boundary proximity of the target class. Second, we use our analysis technique to identify frequently forgotten regions within the training volume and augment the training set with state-of-the-art style transfer techniques from computer vision. We show that our method improves the segmentation performance on underrepresented classes while significantly reducing the forgotten regions in the F3 volume in the Netherlands.

Ryan Benkert, Oluwaseun Joseph Aribido, Ghassan AlRegib

Even though deep neural networks have shown tremendous success in countless applications, explaining model behaviour or predictions is an open research problem. In this paper, we address this issue by employing a simple yet effective method by analysing the learning dynamics of deep neural networks in semantic segmentation tasks. Specifically, we visualize the learning behaviour during training by tracking how often samples are learned and forgotten in subsequent training epochs. This further allows us to derive important information about the proximity to the class decision boundary and identify regions that pose a particular challenge to the model. Inspired by this phenomenon, we present a novel segmentation method that actively uses this information to alter the data representation within the model by increasing the variety of difficult regions. Finally, we show that our method consistently reduces the amount of regions that are forgotten frequently. We further evaluate our method in light of the segmentation performance.

Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib

The Segment Anything Model (SAM) has revolutionized interactive segmentation through spatial prompting. While existing work primarily focuses on automating prompts in various settings, real-world annotation workflows involve iterative refinement where annotators observe model outputs and strategically place prompts to resolve ambiguities. Current pipelines typically rely on the annotator's visual assessment of the predicted mask quality. We postulate that a principled approach for automated interactive prompting is to use a model-derived criterion to identify the most informative region for the next prompt. In this work, we establish active prompting: a spatial active learning approach where locations within images constitute an unlabeled pool and prompts serve as queries to prioritize information-rich regions, increasing the utility of each interaction. We further present BALD-SAM: a principled framework adapting Bayesian Active Learning by Disagreement (BALD) to spatial prompt selection by quantifying epistemic uncertainty. To do so, we freeze the entire model and apply Bayesian uncertainty modeling only to a small learned prediction head, making intractable uncertainty estimation practical for large multi-million parameter foundation models. Across 16 datasets spanning natural, medical, underwater, and seismic domains, BALD-SAM demonstrates strong cross-domain performance, ranking first or second on 14 of 16 benchmarks. We validate these gains through a comprehensive ablation suite covering 3 SAM backbones and 35 Laplace posterior configurations, amounting to 38 distinct ablation settings. Beyond strong average performance, BALD-SAM surpasses human prompting and, in several categories, even oracle prompting, while consistently outperforming one-shot baselines in final segmentation quality, particularly on thin and structurally complex objects.

Jinsol Lee, Ghassan AlRegib

Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of unknown classes. Open-set recognition aims to solve this problem by rejecting unknown classes while classifying known classes correctly. In this paper, we propose to utilize gradient-based representations obtained from a known classifier to train an unknown detector with instances of known classes only. Gradients correspond to the amount of model updates required to properly represent a given sample, which we exploit to understand the model's capability to characterize inputs with its learned features. Our approach can be utilized with any classifier trained in a supervised manner on known classes without the need to model the distribution of unknown samples explicitly. We show that our gradient-based approach outperforms state-of-the-art methods by up to 11.6% in open-set classification.

Ahmad Mustafa, Ghassan AlRegib

Hydrocarbon prospect risking is a critical application in geophysics predicting well outcomes from a variety of data including geological, geophysical, and other information modalities. Traditional routines require interpreters to go through a long process to arrive at the probability of success of specific outcomes. AI has the capability to automate the process but its adoption has been limited thus far owing to a lack of transparency in the way complicated, black box models generate decisions. We demonstrate how LIME -- a model-agnostic explanation technique -- can be used to inject trust in model decisions by uncovering the model's reasoning process for individual predictions. It generates these explanations by fitting interpretable models in the local neighborhood of specific datapoints being queried. On a dataset of well outcomes and corresponding geophysical attribute data, we show how LIME can induce trust in model's decisions by revealing the decision-making process to be aligned to domain knowledge. Further, it has the potential to debug mispredictions made due to anomalous patterns in the data or faulty training datasets.

Jorge Quesada, Zoe Fowler, Mohammad Alotaibi et al.

The remarkable capabilities of the Segment Anything Model (SAM) for tackling image segmentation tasks in an intuitive and interactive manner has sparked interest in the design of effective visual prompts. Such interest has led to the creation of automated point prompt selection strategies, typically motivated from a feature extraction perspective. However, there is still very little understanding of how appropriate these automated visual prompting strategies are, particularly when compared to humans, across diverse image domains. Additionally, the performance benefits of including such automated visual prompting strategies within the finetuning process of SAM also remains unexplored, as does the effect of interpretable factors like distance between the prompt points on segmentation performance. To bridge these gaps, we leverage a recently released visual prompting dataset, PointPrompt, and introduce a number of benchmarking tasks that provide an array of opportunities to improve the understanding of the way human prompts differ from automated ones and what underlying factors make for effective visual prompts. We demonstrate that the resulting segmentation scores obtained by humans are approximately 29% higher than those given by automated strategies and identify potential features that are indicative of prompting performance with $R^2$ scores over 0.5. Additionally, we demonstrate that performance when using automated methods can be improved by up to 68% via a finetuning approach. Overall, our experiments not only showcase the existing gap between human prompts and automated methods, but also highlight potential avenues through which this gap can be leveraged to improve effective visual prompt design. Further details along with the dataset links and codes are available at https://github.com/olivesgatech/PointPrompt

Chen Zhou, Ghassan AlRegib, Armin Parchami et al.

In smart transportation, intelligent systems avoid potential collisions by predicting the intent of traffic agents, especially pedestrians. Pedestrian intent, defined as future action, e.g., start crossing, can be dependent on traffic surroundings. In this paper, we develop a framework to incorporate such dependency given observed pedestrian trajectory and scene frames. Our framework first encodes regional joint information between a pedestrian and surroundings over time into feature-map vectors. The global relation representations are then extracted from pairwise feature-map vectors to estimate intent with past trajectory condition. We evaluate our approach on two public datasets and compare against two state-of-the-art approaches. The experimental results demonstrate that our method helps to inform potential risks during crossing events with 0.04 improvement in F1-score on JAAD dataset and 0.01 improvement in recall on PIE dataset. Furthermore, we conduct ablation experiments to confirm the contribution of the relation extraction in our framework.

Seulgi Kim, Ghazal Kaviani, Mohit Prabhushankar et al.

Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates on fully observed videos, action anticipation must handle incomplete information. Hence, it requires temporal reasoning, and inherent uncertainty handling. While recent advances have been made, traditional methods often focus solely on visual modalities, neglecting the potential of integrating multiple sources of information. Drawing inspiration from human behavior, we introduce \textit{Multi-level and Multi-modal Action Anticipation (m\&m-Ant)}, a novel multi-modal action anticipation approach that combines both visual and textual cues, while explicitly modeling hierarchical semantic information for more accurate predictions. To address the challenge of inaccurate coarse action labels, we propose a fine-grained label generator paired with a specialized temporal consistency loss function to optimize performance. Extensive experiments on widely used datasets, including Breakfast, 50 Salads, and DARai, demonstrate the effectiveness of our approach, achieving state-of-the-art results with an average anticipation accuracy improvement of 3.08\% over existing methods. This work underscores the potential of multi-modal and hierarchical modeling in advancing action anticipation and establishes a new benchmark for future research in the field. Our code is available at: https://github.com/olivesgatech/mM-ant.

Mohit Prabhushankar, Ghassan AlRegib

The widespread adoption of deep neural networks in machine learning calls for an objective quantification of esoteric trust. In this paper we propose GradTrust, a classification trust measure for large-scale neural networks at inference. The proposed method utilizes variance of counterfactual gradients, i.e. the required changes in the network parameters if the label were different. We show that GradTrust is superior to existing techniques for detecting misprediction rates on $50000$ images from ImageNet validation dataset. Depending on the network, GradTrust detects images where either the ground truth is incorrect or ambiguous, or the classes are co-occurring. We extend GradTrust to Video Action Recognition on Kinetics-400 dataset. We showcase results on $14$ architectures pretrained on ImageNet and $5$ architectures pretrained on Kinetics-400. We observe the following: (i) simple methodologies like negative log likelihood and margin classifiers outperform state-of-the-art uncertainty and out-of-distribution detection techniques for misprediction rates, and (ii) the proposed GradTrust is in the Top-2 performing methods on $37$ of the considered $38$ experimental modalities. The code is available at: https://github.com/olivesgatech/GradTrust

Mohit Prabhushankar, Ghassan AlRegib

In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the input. Visual post hoc explainability techniques highlight features within an image to justify a network's prediction. We theoretically show that existing evaluation strategies of visual explanatory techniques partially reduce the predictive uncertainty of neural networks. This analysis allows us to construct a plug in approach to visualize and quantify the remaining predictive uncertainty of any gradient-based explanatory technique. We show that every image, network, prediction, and explanatory technique has a unique uncertainty. The proposed uncertainty visualization and quantification yields two key observations. Firstly, oftentimes under incorrect predictions, explanatory techniques are uncertain about the same features that they are attributing the predictions to, thereby reducing the trustworthiness of the explanation. Secondly, objective metrics of an explanation's uncertainty, empirically behave similarly to epistemic uncertainty. We support these observations on two datasets, four explanatory techniques, and six neural network architectures. The code is available at https://github.com/olivesgatech/VOICE-Uncertainty.

Ghassan AlRegib, Mohit Prabhushankar

In this article, we present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to abstract reasoning-based questions. With $P$ as the prediction from a neural network, these questions are `Why P?', `What if not P?', and `Why P, rather than Q?' for a given contrast prediction $Q$. The answers to these questions are observed correlations, observed counterfactuals, and observed contrastive explanations respectively. Together, these explanations constitute the abductive reasoning scheme. We term the three explanatory schemes as observed explanatory paradigms. The term observed refers to the specific case of post-hoc explainability, when an explanatory technique explains the decision $P$ after a trained neural network has made the decision $P$. The primary advantage of viewing explanations through the lens of abductive reasoning-based questions is that explanations can be used as reasons while making decisions. The post-hoc field of explainability, that previously only justified decisions, becomes active by being involved in the decision making process and providing limited, but relevant and contextual interventions. The contributions of this article are: ($i$) realizing explanations as reasoning paradigms, ($ii$) providing a probabilistic definition of observed explanations and their completeness, ($iii$) creating a taxonomy for evaluation of explanations, and ($iv$) positioning gradient-based complete explanainability's replicability and reproducibility across multiple applications and data modalities, ($v$) code repositories, publicly available at https://github.com/olivesgatech/Explanatory-Paradigms.

Min-Hung Chen, Baopu Li, Yingze Bao et al.

Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal variations (e.g. different people may perform the same activity in various ways). Therefore, we exploit unlabeled videos to address this problem by reformulating the action segmentation task as a cross-domain problem with domain discrepancy caused by spatio-temporal variations. To reduce the discrepancy, we propose Self-Supervised Temporal Domain Adaptation (SSTDA), which contains two self-supervised auxiliary tasks (binary and sequential domain prediction) to jointly align cross-domain feature spaces embedded with local and global temporal dynamics, achieving better performance than other Domain Adaptation (DA) approaches. On three challenging benchmark datasets (GTEA, 50Salads, and Breakfast), SSTDA outperforms the current state-of-the-art method by large margins (e.g. for the F1@25 score, from 59.6% to 69.1% on Breakfast, from 73.4% to 81.5% on 50Salads, and from 83.6% to 89.1% on GTEA), and requires only 65% of the labeled training data for comparable performance, demonstrating the usefulness of adapting to unlabeled target videos across variations. The source code is available at https://github.com/cmhungsteve/SSTDA.

Dogancan Temel, Min-Hung Chen, Ghassan AlRegib

Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in terms of type and severity of challenging conditions. Metadata corresponding to these conditions are unavailable and it is not possible to investigate the effect of a single factor because of simultaneous changes in numerous conditions. To overcome the shortcomings in existing datasets, we introduced the CURE-TSD-Real dataset, which is based on simulated challenging conditions that correspond to adversaries that can occur in real-world environments and systems. We test the performance of two benchmark algorithms and show that severe conditions can result in an average performance degradation of 29% in precision and 68% in recall. We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics. Moreover, we show that mean magnitude spectrum of changes in video sequences under challenging conditions can be an indicator of detection performance. CURE-TSD-Real dataset is available online at https://github.com/olivesgatech/CURE-TSD.

Min-Hung Chen, Zsolt Kira, Ghassan AlRegib et al.

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose two large-scale video DA datasets with much larger domain discrepancy: UCF-HMDB_full and Kinetics-Gameplay. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e.g. 7.9% accuracy gain over "Source only" from 73.9% to 81.8% on "HMDB --> UCF", and 10.3% gain on "Kinetics --> Gameplay"). The code and data are released at http://github.com/cmhungsteve/TA3N.

Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib et al.

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model. The most common way of relating image regions with words in caption models is through an attention mechanism over the regions that are used as input to predict the next word. The model must therefore learn to predict the attentional weights without knowing the word it should localize. This is difficult to train without grounding supervision since recurrent models can propagate past information and there is no explicit signal to force the captioning model to properly ground the individual decoded words. In this work, we help the model to achieve this via a novel cyclical training regimen that forces the model to localize each word in the image after the sentence decoder generates it, and then reconstruct the sentence from the localized image region(s) to match the ground-truth. Our proposed framework only requires learning one extra fully-connected layer (the localizer), a layer that can be removed at test time. We show that our model significantly improves grounding accuracy without relying on grounding supervision or introducing extra computation during inference, for both image and video captioning tasks. Code is available at https://github.com/chihyaoma/cyclical-visual-captioning .

Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets. The code and data are released at http://github.com/cmhungsteve/TA3N.

Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib et al.

As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making. Specifically, the Vision and Language Navigation (VLN) task involves navigating to a goal purely from language instructions and visual information without explicit knowledge of the goal. Recent successful approaches have made in-roads in achieving good success rates for this task but rely on beam search, which thoroughly explores a large number of trajectories and is unrealistic for applications such as robotics. In this paper, inspired by the intuition of viewing the problem as search on a navigation graph, we propose to use a progress monitor developed in prior work as a learnable heuristic for search. We then propose two modules incorporated into an end-to-end architecture: 1) A learned mechanism to perform backtracking, which decides whether to continue moving forward or roll back to a previous state (Regret Module) and 2) A mechanism to help the agent decide which direction to go next by showing directions that are visited and their associated progress estimate (Progress Marker). Combined, the proposed approach significantly outperforms current state-of-the-art methods using greedy action selection, with 5% absolute improvement on the test server in success rates, and more importantly 8% on success rates normalized by the path length. Our code is available at https://github.com/chihyaoma/regretful-agent .

Dogancan Temel, Tariq Alshawi, Min-Hung Chen et al.

State-of-the-art algorithms successfully localize and recognize traffic signs over existing datasets, which are limited in terms of challenging condition type and severity. Therefore, it is not possible to estimate the performance of traffic sign detection algorithms under overlooked challenging conditions. Another shortcoming of existing datasets is the limited utilization of temporal information and the unavailability of consecutive frames and annotations. To overcome these shortcomings, we generated the CURE-TSD video dataset and hosted the first IEEE Video and Image Processing (VIP) Cup within the IEEE Signal Processing Society. In this paper, we provide a detailed description of the CURE-TSD dataset, analyze the characteristics of the top performing algorithms, and provide a performance benchmark. Moreover, we investigate the robustness of the benchmarked algorithms with respect to sign size, challenge type and severity. Benchmarked algorithms are based on state-of-the-art and custom convolutional neural networks that achieved a precision of 0.55 and a recall of 0.32, F0.5 score of 0.48 and F2 score of 0.35. Experimental results show that benchmarked algorithms are highly sensitive to tested challenging conditions, which result in an average performance drop of 0.17 in terms of precision and a performance drop of 0.28 in recall under severe conditions. The dataset is publicly available at https://github.com/olivesgatech/CURE-TSD.

Yazeed Alaudah, Patrycja Michalowicz, Motaz Alfarraj et al.

The recent interest in using deep learning for seismic interpretation tasks, such as facies classification, has been facing a significant obstacle, namely the absence of large publicly available annotated datasets for training and testing models. As a result, researchers have often resorted to annotating their own training and testing data. However, different researchers may annotate different classes, or use different train and test splits. In addition, it is common for papers that apply machine learning for facies classification to not contain quantitative results, and rather rely solely on visual inspection of the results. All of these practices have lead to subjective results and have greatly hindered the ability to compare different machine learning models against each other and understand the advantages and disadvantages of each approach. To address these issues, we open-source a fully-annotated 3D geological model of the Netherlands F3 Block. This model is based on the study of the 3D seismic data in addition to 26 well logs, and is grounded on the careful study of the geology of the region. Furthermore, we propose two baseline models for facies classification based on a deconvolution network architecture and make their codes publicly available. Finally, we propose a scheme for evaluating different models on this dataset, and we share the results of our baseline models. In addition to making the dataset and the code publicly available, this work helps advance research in this area by creating an objective benchmark for comparing the results of different machine learning approaches for facies classification.

Chih-Yao Ma, Jiasen Lu, Zuxuan Wu et al.

The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments. This challenging task demands that the agent be aware of which instruction was completed, which instruction is needed next, which way to go, and its navigation progress towards the goal. In this paper, we introduce a self-monitoring agent with two complementary components: (1) visual-textual co-grounding module to locate the instruction completed in the past, the instruction required for the next action, and the next moving direction from surrounding images and (2) progress monitor to ensure the grounded instruction correctly reflects the navigation progress. We test our self-monitoring agent on a standard benchmark and analyze our proposed approach through a series of ablation studies that elucidate the contributions of the primary components. Using our proposed method, we set the new state of the art by a significant margin (8% absolute increase in success rate on the unseen test set). Code is available at https://github.com/chihyaoma/selfmonitoring-agent .

Yavuz Yarici, Ghassan AlRegib

Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ separate encoders for each modality and a fusion module, training the system end-to-end by optimizing on the fused features. In this paper, we identify that such joint optimization causes encoders to exploit cross-modal co-occurrences, statistical relationships between modalities that arise from source-specific recording conditions, rather than learning domain-invariant features. We term this failure mode Fusion Overfitting. To address this, we propose Modality-Entropy Regularization for Domain Generalization (MER-DG), which maximizes the entropy of each encoder's feature distribution to preserve feature diversity. MER-DG is architecture-agnostic and integrates into existing multimodal frameworks as an additive loss term. Extensive experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of approximately 5% over standard fusion and approximately 2% over state-of-the-art methods.

Zoe Fowler, Ghassan AlRegib

Federated learning (FL) holds great potential for medical applications. However, statistical heterogeneity across healthcare institutions poses a major challenge for FL, as the global model struggles both to generalize across unseen patient populations and to adapt to the unique data distributions of individual hospitals. This heterogeneity also exacerbates forgetting at both the global and local level, resulting in previous learned patient patterns to be misclassified after model updates. While prior work has largely treated generalization and personalization as separate challenges, we show that a better balance between the two can be achieved through selective alignment with the global model and a modified aggregation scheme, which together mitigate the effects of statistical heterogeneity. Specifically, we introduce FedKPer, which introduces knowledge personalization into the training stage of each local device. Afterwards, generalization is considered via the global model aggregation process, where local updates that are reliable and label-diverse are emphasized. We evaluate the performance of FedKPer, devising additional metrics that relate to common consequences of forgetting. Overall, we demonstrate FedKPer improves the generalization-personalization trade-off without sacrificing retention.

Ghazal Kaviani, Reza Marzban, Ghassan AlRegib

This paper investigates image denoising, comparing traditional non-learning-based techniques, represented by Block-Matching 3D (BM3D), with modern learning-based methods, exemplified by NBNet. We assess these approaches across diverse datasets, including CURE-OR, CURE-TSR, SSID+, Set-12, and Chest-Xray, each presenting unique noise challenges. Our analysis employs seven Image Quality Assessment (IQA) metrics and examines the impact on object detection performance. We find that while BM3D excels in scenarios like blur challenges, NBNet is more effective in complex noise environments such as under-exposure and over-exposure. The study reveals the strengths and limitations of each method, providing insights into the effectiveness of different denoising strategies in varied real-world applications.

Kiran Kokilepersaud, Seulgi Kim, Mohit Prabhushankar et al.

In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some invariance term to ensure consistency between similar samples and a regularization term to prevent global dimensional collapse. Dimensional collapse refers to data representations spanning a lower-dimensional subspace. Recent work has demonstrated that the representation space of these algorithms gradually reflects a semantic hierarchical structure as training progresses. Data samples of the same hierarchical grouping tend to exhibit greater dimensional collapse locally compared to the dataset as a whole due to sharing features in common with each other. Ideally, SSL algorithms would take advantage of this hierarchical emergence to have an additional regularization term to account for this local dimensional collapse effect. However, the construction of existing SSL algorithms does not account for this property. To address this, we propose an adaptive algorithm that performs a weighted decomposition of the denominator of the InfoNCE loss into two terms: local hierarchical and global collapse regularization respectively. This decomposition is based on an adaptive threshold that gradually lowers to reflect the emerging hierarchical structure of the representation space throughout training. It is based on an analysis of the cosine similarity distribution of samples in a batch. We demonstrate that this hierarchical emergence exploitation (HEX) approach can be integrated across a wide variety of SSL algorithms. Empirically, we show performance improvements of up to 5.6% relative improvement over baseline SSL approaches on classification accuracy on Imagenet with 100 epochs of training.

Chen Zhou, Ghassan AlRegib, Armin Parchami et al.

Forecasting human trajectories in traffic scenes is critical for safety within mixed or fully autonomous systems. Human future trajectories are driven by two major stimuli, social interactions, and stochastic goals. Thus, reliable forecasting needs to capture these two stimuli. Edge-based relation modeling represents social interactions using pairwise correlations from precise individual states. Nevertheless, edge-based relations can be vulnerable under perturbations. To alleviate these issues, we propose a region-based relation learning paradigm that models social interactions via region-wise dynamics of joint states, i.e., the changes in the density of crowds. In particular, region-wise agent joint information is encoded within convolutional feature grids. Social relations are modeled by relating the temporal changes of local joint information from a global perspective. We show that region-based relations are less susceptible to perturbations. In order to account for the stochastic individual goals, we exploit a conditional variational autoencoder to realize multi-goal estimation and diverse future prediction. Specifically, we perform variational inference via the latent distribution, which is conditioned on the correlation between input states and associated target goals. Sampling from the latent distribution enables the framework to reliably capture the stochastic behavior in test data. We integrate multi-goal estimation and region-based relation learning to model the two stimuli, social interactions, and stochastic goals, in a prediction framework. We evaluate our framework on the ETH-UCY dataset and Stanford Drone Dataset (SDD). We show that the diverse prediction better fits the ground truth when incorporating the relation module. Our framework outperforms the state-of-the-art models on SDD by $27.61\%$/$18.20\%$ of ADE/FDE metrics.

Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib et al.

In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy.

Ghazal Kaviani, Yavuz Yarici, Seulgi Kim et al.

Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in real-world settings. DARai consists of continuous scripted and unscripted recordings of 50 participants in 10 different environments, totaling over 200 hours of data from 20 sensors including multiple camera views, depth and radar sensors, wearable inertial measurement units (IMUs), electromyography (EMG), insole pressure sensors, biomonitor sensors, and gaze tracker. To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between activities, and (iii) fine-grained procedures (L3) that detail the exact execution steps for actions. The dataset annotations and recordings are designed so that 22.7% of L2 actions are shared between L1 activities and 14.2% of L3 procedures are shared between L2 actions. The overlap and unscripted nature of DARai allows counterfactual activities in the dataset. Experiments with various machine learning models showcase the value of DARai in uncovering important challenges in human-centered applications. Specifically, we conduct unimodal and multimodal sensor fusion experiments for recognition, temporal localization, and future action anticipation across all hierarchical annotation levels. To highlight the limitations of individual sensors, we also conduct domain-variant experiments that are enabled by DARai's multi-sensor and counterfactual activity design setup. The code, documentation, and dataset are available at the dedicated DARai website: https://alregib.ece.gatech.edu/software-and-datasets/darai-daily-activity-recordings-for-artificial-intelligence-and-machine-learning/

Chen Zhou, Mohit Prabhushankar, Ghassan AlRegib

Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. Annotator label uncertainty manifests in variations of labeling quality. Training with a single low-quality annotation per sample induces model reliability degradations. In this work, we first examine the effects of annotator label uncertainty in terms of the model's generalizability and prediction uncertainty. We observe that the model's generalizability and prediction uncertainty degrade with the presence of low-quality noisy labels. Meanwhile, our evaluation of existing uncertainty estimation algorithms indicates their incapability in response to annotator label uncertainty. To mitigate performance degradation, prior methods show that training models with labels collected from multiple independent annotators can enhance generalizability. However, they require massive annotations. Hence, we introduce a novel perceptual quality-based model training framework to objectively generate multiple labels for model training to enhance reliability, while avoiding massive annotations. Specifically, we first select a subset of samples with low perceptual quality scores ranked by statistical regularities of visual signals. We then assign de-aggregated labels to each sample in this subset to obtain a training set with multiple labels. Our experiments and analysis demonstrate that training with the proposed framework alleviates the degradation of generalizability and prediction uncertainty caused by annotator label uncertainty.

Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar et al.

The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learning relies on selecting informative positive and negative samples. However, HAR sensor signals are subject to significant domain shifts caused by subject variability. These domain shifts hinder model generalization to unseen subjects by embedding subject-specific variations rather than activity-specific features. As a result, human activity recognition models trained with contrastive learning often struggle to generalize to new subjects. We introduce Subject-Invariant Contrastive Learning (SICL), a simple yet effective loss function to improve generalization in human activity recognition. SICL re-weights negative pairs drawn from the same subject to suppress subject-specific cues and emphasize activity-specific information. We evaluate our loss function on three public benchmarks: UTD-MHAD, MMAct, and DARai. We show that SICL improves performance by up to 11% over traditional contrastive learning methods. Additionally, we demonstrate the adaptability of our loss function across various settings, including multiple self-supervised methods, multimodal scenarios, and supervised learning frameworks.