Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 30 for “"cycle-consistency"”.

  1. Skeleton-Based Human Activity Recognition using Temporal Cycle-Consistency Learning

    … use of temporal alignment, specifically temporal cycle-consistency learning, for constructing sample-similarity based classifiers and few-shot classifiers. These models aim to inherit the advantages of existing few-shot methods while taking advantage of the characteristics of skeleton data and the …

    queens Repository record for Skeleton-Based Human Activity Recognition using Temporal Cycle-Consistency Learning (opens in a new tab)

  2. Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech

    … the problem of limited paired data, the idea of cycle-consistency losses has been proposed recently in areas such as machine translation and computer vision. In ASR, cycle-consistency training is achieved by building a reverse system, e.g., a text-to-speech system, and designing a loss based on …

    uiuc Repository record for Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech (opens in a new tab)

  3. Probabilistic Temporal Correspondence Learning for Self-Supervised Video Alignment

    … Self-supervised methods based on temporal cycle-consistency make fine-grained alignment possible without frame-level annotations, but they rest on assumptions that break down in realistic settings: they presume a single one-to-one correspondence for every frame, they assume that every frame …

    unt Repository record for Probabilistic Temporal Correspondence Learning for Self-Supervised Video Alignment (opens in a new tab)

  4. Revealing The Three-Dimensional Magnetic Texture with Machine Learning Models

    … potential that EH cannot probe. Integrating the cycle consistency and a forward model from magnetization to EH phasemap, we build a cycle consistency generative adversarial network (cycleGAN) based generative model that gives impressive reconstruction results of magnetization. This cycle …

    cuny-grad Repository record for Revealing The Three-Dimensional Magnetic Texture with Machine Learning Models (opens in a new tab)

  5. Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation

    … have ground-truth translations across domains. Cycle-consistent GANs solve this problem by using unpaired data. Such methods work well for translations that involve color and texture changes but fail when shape changes are required. This research analyzes the trade-offs between the …

    rit Repository record for Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation (opens in a new tab)

  6. Robust Group Synchronization via Quadratic Programming

    … problem. Our objective function exploits the cycle consistency of the group and we thus refer to our method as detection and estimation of structural consistency (DESC). This general framework can be extended to other algebraic and geometric structures. Our formulation has the following …

    umn Repository record for Robust Group Synchronization via Quadratic Programming (opens in a new tab)

  7. Attention-enhanced Cross-View Transformer for monocular BEV perception

    … to refine encoder features, followed by Cycled View Projection (CVP) and a Cross-View Transformer (CVT) for view transformation. CVP enforces geometric coherence through cycle-consistency constraints, while CVT explicitly models feature correspondence across views. We evaluate our …

    uoit Repository record for Attention-enhanced Cross-View Transformer for monocular BEV perception (opens in a new tab)

  8. AI-Driven 4D Lung SBRT Treatment Planning: An End-to-End Approach

    … deformation realism. The registration model uses cycle consistency to improve bi-directional registration consistency, a generator-discriminator pair to force realistic deformations, and weak supervision to improve registration quality. Additionally, segmentation models were created and compared …

    gatech Repository record for AI-Driven 4D Lung SBRT Treatment Planning: An End-to-End Approach (opens in a new tab)

  9. SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY

    … framework that disentangles pose and shape using cycle consistency, enabling cross-character transfer without extensive paired data. (2) Diffusion-Guided Generalizable Human Reconstruction employing a coarse-to-fine strategy that combines feedforward mesh reconstruction with SMPL priors and 2D …

    nus Repository record for SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY (opens in a new tab) Download file for SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY (opens in a new tab)

  10. Learning Representations For Matching

    … of these matching problems, using multi-image cycle consistency and geometric consistency losses to learn robust representations. We propose a framework for handling outlier rejection in training the deep neural networks using primal-dual optimization. We will apply these techniques to …

    penn Repository record for Learning Representations For Matching (opens in a new tab)

  11. Scalable learning for expanding robot vision

    … data generation. We propose an improvement to cycle-consistency GANs, and a very simple method for collecting images affected by adherent droplets complete with a clear ground-truth. Scene synthesis and randomization techniques are used for improved semantic segmentation models, finishing with …

    oxford Repository record for Scalable learning for expanding robot vision (opens in a new tab)

  12. Generative modeling of the tumor microenvironment : deconvolution, completion, and integration

    … by learning shared latent representations under cycle-consistency, spatial, and cell-type constraints. These methods demonstrate that structured generative modeling can infer biologically meaningful signals under acquisition constraints, without requiring paired supervision or complete …

    texas Repository record for Generative modeling of the tumor microenvironment : deconvolution, completion, and integration (opens in a new tab)

  13. Generative Prior for Unsupervised Image Restoration

    … restoring it. We propose using a combination of cycle consistency losses and self-attention to enhance face images by first learning the degradation and then using this information to train a style-based neural network. We also aim to use the latent representation to achieve a high level of …

    wvu Repository record for Generative Prior for Unsupervised Image Restoration (opens in a new tab)

  14. Label-Efficient Visual Understanding with Consistency Constraints

    … as follows. In Part I, we propose to use the consistency over different geometric formulations and a cycle consistency over time to tackle the low-level scene geometry perception tasks in a self-supervised learning setting. In Part II, we tackle the high-level semantic understanding tasks in a …

    vt Repository record for Label-Efficient Visual Understanding with Consistency Constraints (opens in a new tab)

  15. 4D VISION: REPRESENT, RECONSTRUCT AND GENERATE THE DYNAMIC 3D WORLD

    … via bijective canonical mappings that guarantee cycle consistency and topology preservation. CaDeX++ improves efficiency with local feature grids and foundation models, significantly speeding up dense tracking. This thesis demonstrates that geometric inductive biases such as piecewise rigidity, …

    penn Repository record for 4D VISION: REPRESENT, RECONSTRUCT AND GENERATE THE DYNAMIC 3D WORLD (opens in a new tab)

  16. Scalable Deep Learning-Based Quantitative Ultrasound Tomography for Medical Imaging

    … speed maps. Central to the PNFWI approach is the cycle-consistency loss, which enables the network to train while solving the physics of wave propagation. This significantly mitigates the risk of cycle skipping and ensures stable convergence even under conditions of added data noise. Therefore, …

    alabama Repository record for Scalable Deep Learning-Based Quantitative Ultrasound Tomography for Medical Imaging (opens in a new tab)

  17. UNSUPERVISED DOMAIN ADAPTATION FOR SPEAKER VERIFICATION IN THE WILD

    … using an auxiliary network, and minimize a cycle-consistency loss between the original and reconstructed target features. Our unsupervised adaptation approach complements its supervised counterpart, where adaptation is done using labeled data from both domains. We focus on three domain …

    jhu Repository record for UNSUPERVISED DOMAIN ADAPTATION FOR SPEAKER VERIFICATION IN THE WILD (opens in a new tab)

  18. Computation-efficient and Scalable Robotic Motion Planning Techniques To Address Dynamic Environmental Constraints

    … algorithm via bidirectional subspace alignment, cycle consistency and human behavior transformer inspired by robotic learning from expert demonstration to address the scarcity of paired cross-embodiment datasets and the impediment of designing intricate controllers. We develop an innovative …

    ucf Repository record for Computation-efficient and Scalable Robotic Motion Planning Techniques To Address Dynamic Environmental Constraints (opens in a new tab)

  19. On Disentangled Analysis-by-Synthesis Shape Representations

    … codes. The mappings, trained via AbS-based cycle-consistency constraints and distribution-matching priors, implement single-image 3D reconstruction (SI3DR) in one direction and 3D-aware generative image modelling in the other. Unlike prior methods, our Cyclic Generative Renderer (CGR) only …

    toronto-retro Repository record for On Disentangled Analysis-by-Synthesis Shape Representations (opens in a new tab)

  20. Advances in deep learning with applications to computer vision and astronomy

    … employs an adversarial inference model and a cycle-consistency loss function to empower the framework to obtain more accurate predictions. In addition, a conformal mapping network structure is incorporated into VPGAN to enable action control for generating desirable future frames. In this way, …

    njit Repository record for Advances in deep learning with applications to computer vision and astronomy (opens in a new tab)

Page 1 of 2