Recent advancements in computer vision models have largely been driven by supervised training on labeled data. However, the process of labeling datasets remains both costly and time-intensive. This dissertation delves into enhancing the performance of deep neural networks when faced with limited or no labeling information. I address this challenge through four primary methodologies: domain adaptation, self-supervision, input regularization, and label regularization. In situations where labeled data is unavailable but a similar dataset exists, domain adaptation emerges as a valuable strategy for transferring knowledge from the labeled dataset to the target dataset. This dissertation introduces three innovative domain adaptation methods that operate at pixel, feature, and output levels.Another approach to tackle the absence of labels involves a novel self-supervision technique tailored to train Vision Transformers in extracting rich features. The third and fourth approaches focus on scenarios where only a limited amount of labeled data is available. In such cases, I present novel regularization techniques designed to mitigate overfitting by modifying the input data and the target labels, respectively.

3D perception poses a significant challenge in Intelligent Transportation Systems (ITS) due to occlusion and limited field of view. The necessity for real-time processing and alignment with existing traffic infrastructure compounds these limitations. To counter these issues, this work introduces a novel multi-camera Bird-Eye View (BEV) occupancy detection framework. This approach leverages multi-camera setups to overcome occlusion and field-of-view limitations while employing BEV occupancy to simplify the 3D perception task, ensuring critical information is retained. A noble dataset for BEV Occupancy detection, encompassing diverse scenes and varying camera configurations, was created using the CARLA simulator. Subsequent extensive evaluation of various Multiview occupancy detection models showcased the critical roles of scene diversity and occupancy grid resolution in enhancing model performance. A structured framework that complements the generated data is proposed for data collection in the real world. The trained model is validated against real-world conditions to ensure its practical application, demonstrating the influence of robust dataset design in refining ITS perception systems. This contributes to significant advancements in traffic management, safety, and operational efficiency.

Manipulator motion planning has conventionally been solved using sampling and optimization-based algorithms that are agnostic to embodiment and environment configurations. However, these algorithms plan on a fixed environment representation approximated using shape primitives, and hence struggle to find solutions for cluttered and dynamic environments. Furthermore, these algorithms fail to produce solutions for complex unstructured environments under real-time bounds. Neural Motion Planners (NMPs) are an appealing alternative to algorithmic approaches as they can leverage parallel computing for planning while incorporating arbitrary environmental constraints directly from raw sensor observations. Contemporary NMPs successfully transfer to different environment variations, however, fail to generalize across embodiments. This thesis proposes "AnyNMP'', a generalist motion planning policy for zero-shot transfer across different robotic manipulators and environments. The policy is conditioned on semantically segmented 3D pointcloud representation of the workspace thus enabling implicit sim2real transfer. In the proposed approach, templates are formulated for manipulator kinematics and ground truth motion plans are collected for over 3 million procedurally sampled robots in randomized environments. The planning pipeline consists of a state validation model for differentiable collision detection and a sampling based planner for motion generation. AnyNMP has been validated on 5 different commercially available manipulators and showcases successful cross-embodiment planning, achieving an 80% average success rate on baseline benchmarks.

Rapid advancements in artificial intelligence (AI) have revolutionized various do- mains, enabling the development of sophisticated models capable of solving complex problems. However, as AI systems increasingly participate in critical decision-making processes, concerns about their interpretability, robustness, and reliability have in- tensified. Interpretable AI models, such as the Concept-Centric Transformer (CCT), have emerged as promising solutions to enhance transparency in AI models. Yet, in- creasing model interpretability often requires enriching training data with concept ex- planations, escalating training costs. Therefore, intrinsically interpretable models like CCT must be designed to be data-efficient, generalizable—to accommodate smaller training sets—and robust against noise and adversarial attacks. Despite progress in interpretable AI, ensuring the robustness of these models remains a challenge.This thesis enhances the data efficiency and generalizability of the CCT model by integrating four techniques: Perturbation Random Masking (PRM), Attention Random Dropout (ARD), and the integration of manifold mixup and input mixup for memory broadcast. Comprehensive experiments on benchmark datasets such as CIFAR-100, CUB-200-2011, and ImageNet show that the enhanced CCT model achieves modest performance improvements over the original model when using a full training set. Furthermore, this performance gap increases as the training data volume decreases, particularly in few-shot learning scenarios. The enhanced CCT maintains high accuracy with limited data (even without explicitly training on ex- ample concept-level explanations), demonstrating its potential for real-world appli- cations where labeled data are scarce. These findings suggest that the enhancements enable more effective use of CCT in settings with data constraints. Ablation studies reveal that no single technique—PRM, ARD, or mixups—dominates in enhancing performance and data efficiency. Each contributes nearly equally, and their combined application yields the best results, indicating a synergistic effect that bolsters the model’s capabilities without any single method being predominant. The results of this research highlight the efficacy of the proposed enhancements in refining CCT models for greater performance, robustness, and data efficiency. By demonstrating improved performance and resilience, particularly in data-limited sce- narios, this thesis underscores the practical applicability of advanced AI systems in critical decision-making roles.

In the age of artificial intelligence, Machine Learning (ML) has become a pervasive force, impacting countless aspects of our lives. As ML’s influence expands, concerns about its reliability and trustworthiness have intensified, with security and robustness emerging as significant challenges. For instance, it has been demonstrated that slight perturbations to a stop sign can cause ML classifiers to misidentify it as a speed limit sign, raising concerns about whether ML algorithms are suitable for real-world deployments. To tackle these issues, Responsible Machine Learning (Responsible ML) has emerged with a clear mission: to develop secure and robust ML algorithms. This dissertation aims to develop Responsible Machine Learning algorithms under real-world constraints. Specifically, recognizing the role of adversarial attacks in exposing security vulnerabilities and robustifying the ML methods, it lays down the foundation of Responsible ML by outlining a novel taxonomy of adversarial attacks within real-world settings, categorizing them into black-box target-specific, and target-agnostic attacks. Subsequently, it proposes potent adversarial attacks in each category, aiming to obtain effectiveness and efficiency. Transcending conventional boundaries, it then introduces the notion of causality into Responsible ML (a.k.a., Causal Responsible ML), presenting the causal adversarial attack. This represents the first principled framework to explain the transferability of adversarial attacks to unknown models by identifying their common source of vulnerabilities, thereby exposing the pinnacle of threat and vulnerability: conducting successful attacks on any model with no prior knowledge. Finally, acknowledging the surge of Generative AI, this dissertation explores Responsible ML for Generative AI. It introduces a novel adversarial attack that unveils their adversarial vulnerabilities and devises a strong defense mechanism to bolster the models’ robustness against potential attacks.

With the exponential growth of multi-modal data in the field of computer vision, the ability to do inference effectively among multiple modalities—such as visual, textual, and auditory data—shows significant opportunities. The rapid development of cross-modal applications such as retrieval and association is primarily attributed to their ability to bridge the gap between different modalities of data. However, the current mainstream cross-modal methods always heavily rely on the availability of fully annotated paired data, presenting a significant challenge due to the scarcity of precisely matched datasets in real-world scenarios. In response to this bottleneck, several sophisticated deep learning algorithms are designed to substantially improve the inference capabilities across a broad spectrum of cross-modal applications. This dissertation introduces novel deep learning algorithms aimed at enhancing inference capabilities in cross-modal applications, which take four primary aspects. Firstly, it introduces the algorithm for image retrieval by learning hashing codes. This algorithm only utilizes the other modality data in weakly supervised tags format rather than the supervised label. Secondly, it designs a novel framework for learning the joint embeddings of images and texts for the cross-modal retrieval tasks. It efficiently learns the binary codes from the continuous CLIP feature space and can even deliver competitive performance compared with the results from non-hashing methods. Thirdly, it conducts a method to learn the fragment-level embeddings that capture fine-grained cross-modal association in images and texts. This method uses the fragment proposals in an unsupervised manner. Lastly, this dissertation also outlines the algorithm to enhance the mask-text association ability of pre-trained semantic segmentation models with zero examples provided. Extensive future plans to further improve this algorithm for semantic segmentation tasks will be discussed.

Recently developed large language models have achieved remarkable success on a wide range of natural language tasks. Furthermore, they have been shown to possess an impressive ability to generate fluent and coherent text. Despite all the notable abilities of these models, there exist several efficiency and reliability related challenges. For example, they are vulnerable to a phenomenon called 'hallucination' in which they generate text that is not factually correct and they also have a large number of parameters which makes their inference slow and computationally expensive. With the objective of taking a step closer towards further enabling the widespread adoption of the Natural Language Processing (NLP) systems, this dissertation studies the following question: how to effectively address the efficiency and reliability related concerns of the NLP systems? Specifically, to improve the reliability of models, this dissertation first presents an approach that actively detects and mitigates the hallucinations of LLMs using a retrieval augmented methodology. Note that another strategy to mitigate incorrect predictions is abstention from answering when error is likely, i.e., selective prediction. To this end, I present selective prediction approaches and conduct extensive experiments to demonstrate their effectiveness. Building on top of selective prediction, I also present post-abstention strategies that focus on reliably increasing the coverage of a selective prediction system without considerably impacting its accuracy. Furthermore, this dissertation covers multiple aspects of improving the efficiency including 'inference efficiency' (making model inferences in a computationally efficient manner without sacrificing the prediction accuracy), 'data sample efficiency' (efficiently collecting data instances for training a task-specific system), 'open-domain QA reader efficiency' (leveraging the external knowledge efficiently while answering open-domain questions), and 'evaluation efficiency' (comparing the performance of different models efficiently). In summary, this dissertation highlights several challenges pertinent to the efficiency and reliability involved in the development of NLP systems and provides effective solutions to address them.

The need for robust verification and validation of automated vehicles (AVs) to ensure driving safety grows more urgent as increasing numbers of AVs are allowed to operate on open roads. To address this need, AV developers can present a safety case to regulators and the public that provides an evidence-based justification of their assertion that an AV is safe to operate on open roads. This work aims to describe the development of a scenario-based testing methodology that contributes to this safety case. A high-level definition of this test selection and scoring methodology (TSSM) is first presented, along with an outline of its scope and key ideas. This is followed by a literature review that details the current state of the art in AV testing, including the driving performance metrics and equations that provide a basis for the TSSM. A chart-based method for quantifying an AV’s operational design domain (ODD) and behavioral competency portfolio is then described that provides the foundation for a scenario generation and filtration process. After outlining a method for the AV to progress through increasingly robust test methods based on its current technology readiness level (TRL), the generation and filtration of two sets of scenarios by the TSSM is outlined: a standardized set that can be used to compare the performance of vehicles with identical ODD and behavioral competency portfolios, and a set containing high-relevance scenarios that is partially randomized to ensure test integrity. A related framework for incorporating testing on open roads is subsequently specified. An equation for an overall AV driving performance score is then defined that quantifies the aggregate performance of the AV across all generated scenarios. The TSSM continues according to an iterative process, which includes a method for exploring edge and corner scenarios, until a stopping condition is achieved. Two proofs of concept are provided: a demonstration of the ability of the TSSM to pare scenarios from a preexisting database, and an example ODD and behavioral competency portfolio specification form. Finally, this work concludes by evaluating the TSSM and its proofs of concept and outlining possible future work on the methodology.

One of the challenges in Artificial Intelligence (AI) is to integrate fast, automatic, and intuitive System-1 thinking with slow, deliberate, and logical System-2 thinking. While deep learning approaches excel at perception tasks for System-1, their reasoning capabilities for System-2 are limited. Besides, deep learning approaches are usually data-hungry, hard to make use of explicit knowledge, and struggling with interpretability and justification. This dissertation presents three neuro-symbolic AI approaches that integrate neural networks (NNs) with symbolic AI methods to address these issues. The first approach presented in this dissertation is NeurASP, which combines NNs with Answer Set Programming (ASP), a logic programming formalism. NeurASP provides an effective way to integrate sub-symbolic and symbolic computation by treating NN outputs as probability distributions over atomic facts in ASP. The explicit knowledge encoded in ASP corrects mistakes in NN outputs and allows for better training with less data. To avoid NeurASP's bottleneck in symbolic computation, this dissertation presents a Constraint Loss via Straight-Through Estimators (CL-STE). CL-STE provides a systematic way to compile discrete logical constraints into a loss function over discretized NN outputs and scales significantly better than state-of-the-art neuro-symbolic methods. This dissertation also presents a finding when CL-STE was applied to Transformers. Transformers can be extended with recurrence to enhance its power for multi-step reasoning. Such Recurrent Transformer can straightforwardly be applied to visual constraint reasoning problems while successfully addressing the symbol grounding problem. Lastly, this dissertation addresses the limitation of pre-trained Large Language Models (LLMs) on multi-step logical reasoning problems with a dual-process neuro-symbolic reasoning system called LLM+ASP, where an LLM (e.g., GPT-3) serves as a highly effective few-shot semantic parser that turns natural language sentences into a logical form that can be used as input to ASP. LLM+ASP achieves state-of-the-art performance on several textual reasoning benchmarks and can handle robot planning tasks that an LLM alone fails to solve.

With the rise in social media usage and rapid communication, the proliferation of misinformation and fake news has become a pressing concern. The detection of multimodal fake news requires careful consideration of both image and textual semantics with proper alignment of the embedding space. Automated fake news detection has gained significant attention in recent years. Existing research has focused on either capturing cross-modal inconsistency information or leveraging the complementary information within image-text pairs. However, the potential of powerful cross-modal contrastive learning methods and effective modality mixing remains an open-ended question. The thesis proposes a novel two-leg single-tower architecture equipped with self-attention mechanisms and custom contrastive loss to efficiently aggregate multimodal features. Furthermore, pretraining and fine-tuning are employed on the custom transformer model to classify fake news across the popular Twitter multimodal fake news dataset. The experimental results demonstrate the efficacy and robustness of the proposed approach, offering promising advancements in multimodal fake news detection research.