Matching Items (48)
Filtering by
- All Subjects: artificial intelligence
- Genre: Academic theses
- Creators: Yang, Yezhou
Description
Vision Transformers (ViT) achieve state-of-the-art performance on image classification tasks. However, their massive size makes them unsuitable for edge devices. Unlike CNNs, limited research has been conducted on the compression of ViTs. This thesis work proposes the ”adjoined training technique” to compress any transformer based architecture. The architecture, Adjoined Vision Transformer (AN-ViT), achieves state-of-the-art performance on the ImageNet classification task. With the base network as Swin Transformer, AN-ViT with 4.1× fewer parameters and 5.5× fewer floating point operations (FLOPs) achieves similar accuracy (within 0.15%). This work further proposes Differentiable Adjoined ViT (DAN-ViT), whichuses neural architecture search to find hyper-parameters of our model. DAN-ViT outperforms the current state-of-the-art methods including Swin-Transformers by about ∼ 0.07% and achieves 85.27% top-1 accuracy on the ImageNet dataset while using 2.2× fewer parameters and with 2.2× fewer FLOPs.
ContributorsGoel, Rajeev (Author) / Yang, Yingzhen (Thesis advisor) / Yang, Yezhou (Committee member) / Zou, Jia (Committee member) / Arizona State University (Publisher)
Created2023
Description
This dissertation presents novel solutions for improving the generalization capabilities of deep learning based computer vision models. Neural networks are known to suffer a large drop in performance when tested on samples from a different distribution than the one on which they were trained. The proposed solutions, based on latent space geometry and meta-learning, address this issue by improving the robustness of these models to distribution shifts. Through the use of geometrical alignment, state-of-the-art domain adaptation and source-free test-time adaptation strategies are developed. Additionally, geometrical alignment can allow classifiers to be progressively adapted to new, unseen test domains without requiring retraining of the feature extractors. The dissertation also presents algorithms for enabling in-the-wild generalization without needing access to any samples from the target domain. Other causes of poor generalization, such as data scarcity in critical applications and training data with high levels of noise and variance, are also explored. To address data scarcity in fine-grained computer vision tasks such as object detection, novel context-aware augmentations are suggested. While the first four chapters focus on general-purpose computer vision models, strategies are also developed to improve robustness in specific applications. The efficiency of training autonomous agents for visual navigation is improved by incorporating semantic knowledge, and the integration of domain experts' knowledge allows for the realization of a low-cost, minimally invasive generalizable automated rehabilitation system. Lastly, new tools for explainability and model introspection using counter-factual explainers trained through interval-based uncertainty calibration objectives are presented.
ContributorsThopalli, Kowshik (Author) / Turaga, Pavan (Thesis advisor) / Thiagarajan, Jayaraman J (Committee member) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
Humans have the remarkable ability to solve different tasks by simply reading textual instructions that define the tasks and looking at a few examples. Natural Language Processing (NLP) models built with the conventional machine learning paradigm, however, often struggle to generalize across tasks (e.g., a question-answering system cannot solve classification tasks) despite training with lots of examples. A long-standing challenge in Artificial Intelligence (AI) is to build a model that learns a new task by understanding the human-readable instructions that define it. To study this, I led the development of NATURAL INSTRUCTIONS and SUPERNATURAL INSTRUCTIONS, large-scale datasets of diverse tasks, their human-authored instructions, and instances. I adopt generative pre-trained language models to encode task-specific instructions along with input and generate task output. Empirical results in my experiments indicate that the instruction-tuning helps models achieve cross-task generalization. This leads to the question: how to write good instructions? Backed by extensive empirical analysis on large language models, I observe important attributes for successful instructional prompts and propose several reframing techniques for model designers to create such prompts. Empirical results in my experiments show that reframing notably improves few-shot learning performance; this is particularly important on large language models, such as GPT3 where tuning models or prompts on large datasets is expensive. In another experiment, I observe that representing a chain of thought instruction of mathematical reasoning questions as a program improves model performance significantly. This observation leads to the development of a large scale mathematical reasoning model BHASKAR and a unified benchmark LILA. In case of program synthesis tasks, however, summarizing a question (instead of expanding as in chain of thought) helps models significantly. This thesis also contains the study of instruction-example equivalence, power of decomposition instruction to replace the need for new models and origination of dataset bias from crowdsourcing instructions to better understand the advantages and disadvantages of instruction paradigm. Finally, I apply the instruction paradigm to match real user needs and introduce a new prompting technique HELP ME THINK to help humans perform various tasks by asking questions.
ContributorsMishra, Swaroop (Author) / Baral, Chitta (Thesis advisor) / Mitra, Arindam (Committee member) / Blanco, Eduardo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
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.
ContributorsVarshney, Neeraj (Author) / Baral, Chitta (Thesis advisor) / Yang, Yezhou (Committee member) / Gopalan, Nakul (Committee member) / Banerjee, Pratyay (Committee member) / Arizona State University (Publisher)
Created2024
Description
Rapid growth of internet and connected devices ranging from cloud systems to internet of things have raised critical concerns for securing these systems. In the recent past, security attacks on different kinds of devices have evolved in terms of complexity and diversity. One of the challenges is establishing secure communication in the network among various devices and systems. Despite being protected with authentication and encryption, the network still needs to be protected against cyber-attacks. For this, the network traffic has to be closely monitored and should detect anomalies and intrusions. Intrusion detection can be categorized as a network traffic classification problem in machine learning. Existing network traffic classification methods require a lot of training and data preprocessing, and this problem is more serious if the dataset size is huge. In addition, the machine learning and deep learning methods that have been used so far were trained on datasets that contain obsolete attacks. In this thesis, these problems are addressed by using ensemble methods applied on an up to date network attacks dataset. Ensemble methods use multiple learning algorithms to get better classification accuracy that could be obtained when the corresponding learning algorithm is applied alone. This dataset for network traffic classification has recent attack scenarios and contains over fifteen attacks. This approach shows that ensemble methods can be used to classify network traffic and detect intrusions with less training times of the model, and lesser pre-processing without feature selection. In addition, this thesis also shows that only with less than ten percent of the total features of input dataset will lead to similar accuracy that is achieved on whole dataset. This can heavily reduce the training times and classification duration in real-time scenarios.
ContributorsPonneganti, Ramu (Author) / Yau, Stephen (Thesis advisor) / Richa, Andrea (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
Multimodal Representation Learning is a multi-disciplinary research field which aims to integrate information from multiple communicative modalities in a meaningful manner to help solve some downstream task. These modalities can be visual, acoustic, linguistic, haptic etc. The interpretation of ’meaningful integration of information from different modalities’ remains modality and task dependent. The downstream task can range from understanding one modality in the presence of information from other modalities, to that of translating input from one modality to another. In this thesis the utility of multimodal representation learning for understanding one modality vis-à-vis Image Understanding for Visual Reasoning given corresponding information in other modalities, as well as translating from one modality to the other, specifically, Text to Image Translation was investigated.
Visual Reasoning has been an active area of research in computer vision. It encompasses advanced image processing and artificial intelligence techniques to locate, characterize and recognize objects, regions and their attributes in the image in order to comprehend the image itself. One way of building a visual reasoning system is to ask the system to answer questions about the image that requires attribute identification, counting, comparison, multi-step attention, and reasoning. An intelligent system is thought to have a proper grasp of the image if it can answer said questions correctly and provide a valid reasoning for the given answers. In this work how a system can be built by learning a multimodal representation between the stated image and the questions was investigated. Also, how background knowledge, specifically scene-graph information, if available, can be incorporated into existing image understanding models was demonstrated.
Multimodal learning provides an intuitive way of learning a joint representation between different modalities. Such a joint representation can be used to translate from one modality to the other. It also gives way to learning a shared representation between these varied modalities and allows to provide meaning to what this shared representation should capture. In this work, using the surrogate task of text to image translation, neural network based architectures to learn a shared representation between these two modalities was investigated. Also, the ability that such a shared representation is capable of capturing parts of different modalities that are equivalent in some sense is proposed. Specifically, given an image and a semantic description of certain objects present in the image, a shared representation between the text and the image modality capable of capturing parts of the image being mentioned in the text was demonstrated. Such a capability was showcased on a publicly available dataset.
Visual Reasoning has been an active area of research in computer vision. It encompasses advanced image processing and artificial intelligence techniques to locate, characterize and recognize objects, regions and their attributes in the image in order to comprehend the image itself. One way of building a visual reasoning system is to ask the system to answer questions about the image that requires attribute identification, counting, comparison, multi-step attention, and reasoning. An intelligent system is thought to have a proper grasp of the image if it can answer said questions correctly and provide a valid reasoning for the given answers. In this work how a system can be built by learning a multimodal representation between the stated image and the questions was investigated. Also, how background knowledge, specifically scene-graph information, if available, can be incorporated into existing image understanding models was demonstrated.
Multimodal learning provides an intuitive way of learning a joint representation between different modalities. Such a joint representation can be used to translate from one modality to the other. It also gives way to learning a shared representation between these varied modalities and allows to provide meaning to what this shared representation should capture. In this work, using the surrogate task of text to image translation, neural network based architectures to learn a shared representation between these two modalities was investigated. Also, the ability that such a shared representation is capable of capturing parts of different modalities that are equivalent in some sense is proposed. Specifically, given an image and a semantic description of certain objects present in the image, a shared representation between the text and the image modality capable of capturing parts of the image being mentioned in the text was demonstrated. Such a capability was showcased on a publicly available dataset.
ContributorsSaha, Rudra (Author) / Yang, Yezhou (Thesis advisor) / Singh, Maneesh Kumar (Committee member) / Baral, Chitta (Committee member) / Arizona State University (Publisher)
Created2018
Description
Image Understanding is a long-established discipline in computer vision, which encompasses a body of advanced image processing techniques, that are used to locate (“where”), characterize and recognize (“what”) objects, regions, and their attributes in the image. However, the notion of “understanding” (and the goal of artificial intelligent machines) goes beyond factual recall of the recognized components and includes reasoning and thinking beyond what can be seen (or perceived). Understanding is often evaluated by asking questions of increasing difficulty. Thus, the expected functionalities of an intelligent Image Understanding system can be expressed in terms of the functionalities that are required to answer questions about an image. Answering questions about images require primarily three components: Image Understanding, question (natural language) understanding, and reasoning based on knowledge. Any question, asking beyond what can be directly seen, requires modeling of commonsense (or background/ontological/factual) knowledge and reasoning.
Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods.
Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods.
ContributorsAditya, Somak (Author) / Baral, Chitta (Thesis advisor) / Yang, Yezhou (Thesis advisor) / Aloimonos, Yiannis (Committee member) / Lee, Joohyung (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2018
Description
Reinforcement learning (RL) is a powerful methodology for teaching autonomous agents complex behaviors and skills. A critical component in most RL algorithms is the reward function -- a mathematical function that provides numerical estimates for desirable and undesirable states. Typically, the reward function must be hand-designed by a human expert and, as a result, the scope of a robot's autonomy and ability to safely explore and learn in new and unforeseen environments is constrained by the specifics of the designed reward function. In this thesis, I design and implement a stateful collision anticipation model with powerful predictive capability based upon my research of sequential data modeling and modern recurrent neural networks. I also develop deep reinforcement learning methods whose rewards are generated by self-supervised training and intrinsic signals. The main objective is to work towards the development of resilient robots that can learn to anticipate and avoid damaging interactions by combining visual and proprioceptive cues from internal sensors. The introduced solutions are inspired by pain pathways in humans and animals, because such pathways are known to guide decision-making processes and promote self-preservation. A new "robot dodge ball' benchmark is introduced in order to test the validity of the developed algorithms in dynamic environments.
ContributorsRichardson, Trevor W (Author) / Ben Amor, Heni (Thesis advisor) / Yang, Yezhou (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2018
Description
Reasoning with commonsense knowledge is an integral component of human behavior. It is due to this capability that people know that a weak person may not be able to lift someone. It has been a long standing goal of the Artificial Intelligence community to simulate such commonsense reasoning abilities in machines. Over the years, many advances have been made and various challenges have been proposed to test their abilities. The Winograd Schema Challenge (WSC) is one such Natural Language Understanding (NLU) task which was also proposed as an alternative to the Turing Test. It is made up of textual question answering problems which require resolution of a pronoun to its correct antecedent.
In this thesis, two approaches of developing NLU systems to solve the Winograd Schema Challenge are demonstrated. To this end, a semantic parser is presented, various kinds of commonsense knowledge are identified, techniques to extract commonsense knowledge are developed and two commonsense reasoning algorithms are presented. The usefulness of the developed tools and techniques is shown by applying them to solve the challenge.
In this thesis, two approaches of developing NLU systems to solve the Winograd Schema Challenge are demonstrated. To this end, a semantic parser is presented, various kinds of commonsense knowledge are identified, techniques to extract commonsense knowledge are developed and two commonsense reasoning algorithms are presented. The usefulness of the developed tools and techniques is shown by applying them to solve the challenge.
ContributorsSharma, Arpita (Author) / Baral, Chitta (Thesis advisor) / Lee, Joohyung (Committee member) / Papotti, Paolo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
The ubiquity of single camera systems in society has made improving monocular depth estimation a topic of increasing interest in the broader computer vision community. Inspired by recent work in sparse-to-dense depth estimation, this thesis focuses on sparse patterns generated from feature detection based algorithms as opposed to regular grid sparse patterns used by previous work. This work focuses on using these feature-based sparse patterns to generate additional depth information by interpolating regions between clusters of samples that are in close proximity to each other. These interpolated sparse depths are used to enforce additional constraints on the network’s predictions. In addition to the improved depth prediction performance observed from incorporating the sparse sample information in the network compared to pure RGB-based methods, the experiments show that actively retraining a network on a small number of samples that deviate most from the interpolated sparse depths leads to better depth prediction overall.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
ContributorsRai, Anshul (Author) / Yang, Yezhou (Thesis advisor) / Zhang, Wenlong (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2019