Matching Items (114)
Filtering by
- Creators: Yang, Yezhou
- Member of: ASU Electronic Theses and Dissertations
- Resource Type: Text
Description
Feature embeddings differ from raw features in the sense that the former obey certain properties like notion of similarity/dissimilarity in it's embedding space. word2vec is a preeminent example in this direction, where the similarity in the embedding space is measured in terms of the cosine similarity. Such language embedding models have seen numerous applications in both language and vision community as they capture the information in the modality (English language) efficiently. Inspired by these language models, this work focuses on learning embedding spaces for two visual computing tasks, 1. Image Hashing 2. Zero Shot Learning. The training set was used to learn embedding spaces over which similarity/dissimilarity is measured using several distance metrics like hamming / euclidean / cosine distances. While the above-mentioned language models learn generic word embeddings, in this work task specific embeddings were learnt which can be used for Image Retrieval and Classification separately.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
ContributorsGattupalli, Jaya Vijetha (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2019
Description
With the substantial development of intelligent robots, human-robot interaction (HRI) has become ubiquitous in applications such as collaborative manufacturing, surgical robotic operations, and autonomous driving. In all these applications, a human behavior model, which can provide predictions of human actions, is a helpful reference that helps robots to achieve intelligent interaction with humans. The requirement elicits an essential problem of how to properly model human behavior, especially when individuals are interacting or cooperating with each other. The major objective of this thesis is to utilize the human intention decoding method to help robots enhance their performance while interacting with humans. Preliminary work on integrating human intention estimation with an HRI scenario is shown to demonstrate the benefit. In order to achieve this goal, the research topic is divided into three phases. First, a novel method of an online measure of the human's reliance on the robot, which can be estimated through the intention decoding process from human actions，is described. An experiment that requires human participants to complete an object-moving task with a robot manipulator was conducted under different conditions of distractions. A relationship is discovered between human intention and trust while participants performed a familiar task with no distraction. This finding suggests a relationship between the psychological construct of trust and joint physical coordination, which bridges the human's action to its mental states. Then, a novel human collaborative dynamic model is introduced based on game theory and bounded rationality, which is a novel method to describe human dyadic behavior with the aforementioned theories. The mutual intention decoding process was also considered to inform this model. Through this model, the connection between the mental states of the individuals to their cooperative actions is indicated. A haptic interface is developed with a virtual environment and the experiments are conducted with 30 human subjects. The result suggests the existence of mutual intention decoding during the human dyadic cooperative behaviors. Last, the empirical results show that allowing agents to have empathy in inference, which lets the agents understand that others might have a false understanding of their intentions, can help to achieve correct intention inference. It has been verified that knowledge about vehicle dynamics was also important to correctly infer intentions. A new courteous policy is proposed that bounded the courteous motion using its inferred set of equilibrium motions. A simulation, which is set to reproduce an intersection passing case between an autonomous car and a human driving car, is conducted to demonstrate the benefit of the novel courteous control policy.
ContributorsWang, Yiwei (Author) / Zhang, Wenlong (Thesis advisor) / Berman, Spring (Committee member) / Lee, Hyunglae (Committee member) / Ren, Yi (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Machine learning models can pick up biases and spurious correlations from training data and projects and amplify these biases during inference, thus posing significant challenges in real-world settings. One approach to mitigating this is a class of methods that can identify filter out bias-inducing samples from the training datasets to force models to avoid being exposed to biases. However, the filtering leads to a considerable wastage of resources as most of the dataset created is discarded as biased. This work deals with avoiding the wastage of resources by identifying and quantifying the biases. I further elaborate on the implications of dataset filtering on robustness (to adversarial attacks) and generalization (to out-of-distribution samples). The findings suggest that while dataset filtering does help to improve OOD(Out-Of-Distribution) generalization, it has a significant negative impact on robustness to adversarial attacks. It also shows that transforming bias-inducing samples into adversarial samples (instead of eliminating them from the dataset) can significantly boost robustness without sacrificing generalization.
ContributorsSachdeva, Bhavdeep Singh (Author) / Baral, Chitta (Thesis advisor) / Liu, Huan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
There has been an explosion in the amount of data on the internet because of modern technology – especially image data – as a consequence of an exponential growth in the number of cameras existing in the world right now; from more extensive surveillance camera systems to billions of people walking around with smartphones in their pockets that come with built-in cameras. With this sudden increase in the accessibility of cameras, most of the data that is getting captured through these devices is ending up on the internet. Researchers soon took leverage of this data by creating large-scale datasets. However, generating a dataset – let alone a large-scale one – requires a lot of man-hours. This work presents an algorithm that makes use of optical flow and feature matching, along with utilizing localization outputs from a Mask R-CNN, to generate large-scale vehicle datasets without much human supervision. Additionally, this work proposes a novel multi-view vehicle dataset (MVVdb) of 500 vehicles which is also generated using the aforementioned algorithm.There are various research problems in computer vision that can leverage a multi-view dataset, e.g., 3D pose estimation, and 3D object detection. On the other hand, a multi-view vehicle dataset can be used for a 2D image to 3D shape prediction, generation of 3D vehicle models, and even a more robust vehicle make and model recognition. In this work, a ResNet is trained on the multi-view vehicle dataset to perform vehicle re-identification, which is fundamentally similar to a vehicle make and recognition problem – also showcasing the usability of the MVVdb dataset.
ContributorsGuha, Anubhab (Author) / Yang, Yezhou (Thesis advisor) / Lu, Duo (Committee member) / Banerjee, Ayan (Committee member) / Arizona State University (Publisher)
Created2022
Description
In recent years, there has been significant progress in deep learning and computer vision, with many models proposed that have achieved state-of-art results on various image recognition tasks. However, to explore the full potential of the advances in this field, there is an urgent need to push the processing of deep networks from the cloud to edge devices. Unfortunately, many deep learning models cannot be efficiently implemented on edge devices as these devices are severely resource-constrained. In this thesis, I present QU-Net, a lightweight binary segmentation model based on the U-Net architecture. Traditionally, neural networks consider the entire image to be significant. However, in real-world scenarios, many regions in an image do not contain any objects of significance. These regions can be removed from the original input allowing a network to focus on the relevant regions and thus reduce computational costs. QU-Net proposes the salient regions (binary mask) that the deeper models can use as the input. Experiments show that QU-Net helped achieve a computational reduction of 25% on the Microsoft Common Objects in Context (MS COCO) dataset and 57% on the Cityscapes dataset. Moreover, QU-Net is a generalizable model that outperforms other similar works, such as Dynamic Convolutions.
ContributorsSanthosh Kumar Varma, Rahul (Author) / Yang, Yezhou (Thesis advisor) / Fan, Deliang (Committee member) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021
Description
Retinotopic map, the map between visual inputs on the retina and neuronal activation in brain visual areas, is one of the central topics in visual neuroscience. For human observers, the map is typically obtained by analyzing functional magnetic resonance imaging (fMRI) signals of cortical responses to slowly moving visual stimuli on the retina. Biological evidences show the retinotopic mapping is topology-preserving/topological (i.e. keep the neighboring relationship after human brain process) within each visual region.
Unfortunately, due to limited spatial resolution and the signal-noise ratio of fMRI, state of art retinotopic map is not topological.
The topic was to model the topology-preserving condition mathematically, fix non-topological retinotopic map with numerical methods, and improve the quality of retinotopic maps.
The impose of topological condition, benefits several applications.
With the topological retinotopic maps, one may have a better insight on human retinotopic maps, including better cortical magnification factor quantification, more precise description of retinotopic maps, and potentially better exam ways of in Ophthalmology clinic.
ContributorsTu, Yanshuai (Author) / Wang, Yalin (Thesis advisor) / Lu, Zhong-Lin (Committee member) / Crook, Sharon (Committee member) / Yang, Yezhou (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2022
Description
It is not merely an aggregation of static entities that a video clip carries, but alsoa variety of interactions and relations among these entities. Challenges still remain
for a video captioning system to generate natural language descriptions focusing on
the prominent interest and aligning with the latent aspects beyond observations. This
work presents a Commonsense knowledge Anchored Video cAptioNing (dubbed as
CAVAN) approach. CAVAN exploits inferential commonsense knowledge to assist the
training of video captioning model with a novel paradigm for sentence-level semantic
alignment. Specifically, commonsense knowledge is queried to complement per training
caption by querying a generic knowledge atlas ATOMIC, and form the commonsense-
caption entailment corpus. A BERT based language entailment model trained from
this corpus then serves as a commonsense discriminator for the training of video
captioning model, and penalizes the model from generating semantically misaligned
captions. With extensive empirical evaluations on MSR-VTT, V2C and VATEX
datasets, CAVAN consistently improves the quality of generations and shows higher
keyword hit rate. Experimental results with ablations validate the effectiveness of
CAVAN and reveals that the use of commonsense knowledge contributes to the video
caption generation.
ContributorsShao, Huiliang (Author) / Yang, Yezhou (Thesis advisor) / Jayasuriya, Suren (Committee member) / Xiao, Chaowei (Committee member) / Arizona State University (Publisher)
Created2022
Description
Multimodal reasoning is one of the most interesting research fields because of the ability to interact with systems and the explainability of the models' behavior. Traditional multimodal research problems do not focus on complex commonsense reasoning (such as physical interactions). Although real-world objects have physical properties associated with them, many of these properties (such as mass and coefficient of friction) are not captured directly by the imaging pipeline. Videos often capture objects, their motion, and the interactions between different objects. However, these properties can be estimated by utilizing cues from relative object motion and the dynamics introduced by collisions. This thesis introduces a new video question-answering task for reasoning about the implicit physical properties of objects in a scene, from videos. For this task, I introduce a dataset -- CRIPP-VQA (Counterfactual Reasoning about Implicit Physical Properties - Video Question Answering), which contains videos of objects in motion, annotated with hypothetical/counterfactual questions about the effect of actions (such as removing, adding, or replacing objects), questions about planning (choosing actions to perform to reach a particular goal), as well as descriptive questions about the visible properties of objects. Further, I benchmark the performance of existing video question-answering models on two test settings of CRIPP-VQA: i.i.d. and an out-of-distribution setting which contains objects with values of mass, coefficient of friction, and initial velocities that are not seen in the training distribution. Experiments reveal a surprising and significant performance gap in terms of answering questions about implicit properties (the focus of this thesis) and explicit properties (the focus of prior work) of objects.
ContributorsPatel, Maitreya Jitendra (Author) / Yang, Yezhou (Thesis advisor) / Baral, Chitta (Committee member) / Lee, Kookjin (Committee member) / Arizona State University (Publisher)
Created2022
Description
The increasing availability of data and advances in computation have spurred the development of data-driven approaches for modeling complex dynamical systems. These approaches are based on the idea that the underlying structure of a complex system can be discovered from data using mathematical and computational techniques. They also show promise for addressing the challenges of modeling high-dimensional, nonlinear systems with limited data. In this research expository, the state of the art in data-driven approaches for modeling complex dynamical systems is surveyed in a systemic way. First the general formulation of data-driven modeling of dynamical systems is discussed. Then several representative methods in feature engineering and system identification/prediction are reviewed, including recent advances and key challenges.
ContributorsShi, Wenlong (Author) / Ren, Yi (Thesis advisor) / Hong, Qijun (Committee member) / Jiao, Yang (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2022