Search

Under Display Camera (UDC) is an advanced imaging system that places a digital camera lens underneath a display panel, effectively concealing the camera. However, the display panel significantly degrades captured images or videos, introducing low transmittance, blur, noise, and flare issues. Tackling such issues is challenging because of the complex degradation of UDCs, including diverse flare patterns. Despite extensive research on UDC images and their restoration models, studies on videos have yet to be significantly explored. While two UDC video datasets exist, they primarily focus on unrealistic or synthetic UDC degradation rather than real-world UDC degradation. In this paper, we propose a real-world UDC video dataset called UDC-VIT. Unlike existing datasets, only UDC-VIT exclusively includes human motions that target facial recognition. We propose a video-capturing system to simultaneously acquire non-degraded and UDC-degraded videos of the same scene. Then, we align a pair of captured videos frame by frame, using discrete Fourier transform (DFT). We compare UDC-VIT with six representative UDC still image datasets and two existing UDC video datasets. Using six deep-learning models, we compare UDC-VIT and an existing synthetic UDC video dataset. The results indicate the ineffectiveness of models trained on earlier synthetic UDC video datasets, as they do not reflect the actual characteristics of UDC-degraded videos. We also demonstrate the importance of effective UDC restoration by evaluating face recognition accuracy concerning PSNR, SSIM, and LPIPS scores. UDC-VIT enables further exploration in the UDC video restoration and offers better insights into the challenge. UDC-VIT is available at our project site., Comment: Main body (10 pages, 9 Figures, 3 Tables), References (4 pages), Appendix (15 pages, 11 Figures, 6 Tables)

Under-Display Camera (UDC) houses a digital camera lens under a display panel. However, UDC introduces complex degradations such as noise, blur, decrease in transmittance, and flare. Despite the remarkable progress, previous research on UDC mainly focuses on eliminating diffraction in the spatial domain and rarely explores its potential in the frequency domain. It is essential to consider both the spatial and frequency domains effectively. For example, degradations, such as noise and blur, can be addressed by local information (e.g., CNN kernels in the spatial domain). At the same time, tackling flares may require leveraging global information (e.g., the frequency domain). In this paper, we revisit the UDC degradations in the Fourier space and figure out intrinsic frequency priors that imply the presence of the flares. Based on this observation, we propose a novel multi-level DNN architecture called SFIM. It efficiently restores UDC-distorted images by integrating local and global (the collective contribution of all points in the image) information. The architecture exploits CNNs to capture local information and FFT-based models to capture global information. SFIM comprises a spatial domain block (SDB), a Frequency Domain Block (FDB), and an Attention-based Multi-level Integration Block (AMIB). Specifically, SDB focuses more on detailed textures such as noise and blur, FDB emphasizes irregular texture loss in extensive areas such as flare, and AMIB enables effective cross-domain interaction. SFIM's superior performance over state-of-the-art approaches is demonstrated through rigorous quantitative and qualitative assessments across three UDC benchmarks., Comment: Main body (10 pages, 9 Figures, 5 Tables), References (3 pages), Appendix (8 pages, 6 Figures, 6 Tables)

Young planetary nebulae (PNe) are characterized by their hot central stars and the presence of abundant neutral and molecular components, which result from significant mass loss during the asymptotic giant branch (AGB) phase of stellar evolution. Far-UV \ion{He}{2}$\lambda$1025 line photons produced near the central star can undergo Raman scattering by hydrogen atoms, creating a broad emission feature centered at $\sim$ 6545~\AA. We conducted high-resolution spectroscopy of 12 young PNe from April 2019 to March 2020 using the Bohyunsan Observatory Echelle Spectrograph ({\it BOES}). Building on the study by Choi and Lee, who identified Raman-scattered \ion{He}{2} at 6545~\AA\ in NGC~6881 and NGC~6886, we report new detections of this feature in NGC~6741 and NGC~6884. Profile fitting reveals that the velocity of the \ion{H}{1} component relative to the \ion{He}{2} emission region ranges from $26-33~{\rm km~s^{-1}}$ in these PNe. Using photoionization modeling, we estimate the line flux of \ion{He}{2}$\lambda$1025 and derive Raman conversion efficiencies of 0.39, 0.21, 0.24, and 0.07 for NGC~6881, NGC~6741, NGC~6886, and NGC~6884, respectively. These results, combined with radiative transfer modeling, suggest the presence of \ion{H}{1} components with masses around $10^{-2}~M_\odot$, moving outward from the central \ion{He}{2} emission region at speeds characteristic of the slow stellar wind from a mass-losing giant star., Comment: 15 pages, 10 figures, accepted for publication in ApJ

Dataset deduplication plays a crucial role in enhancing data quality, ultimately improving training performance and efficiency of LLMs. A commonly used method for data deduplication is the MinHash LSH algorithm. Recently, NVIDIA introduced a GPU-based MinHash LSH deduplication method, but it remains suboptimal, leaving room for further improvement in processing efficiency. This paper proposes a GPU-accelerated deduplication framework \sys that optimizes MinHash LSH for GPU clusters and leverages computationally efficient and partially reusable non-cryptographic hash functions. \sys significantly outperforms the CPU-based deduplication tool included in SlimPajama by up to 58.3 times and the GPU-based deduplication tool included in NVIDIA NeMo Curator by up to 8.6 times when processing 1 million documents with a node of four GPUs. Deduplication of 1.2 trillion tokens is completed in just 5.1 hours in a four-node, 16-GPU environment. The related code is publicly available on GitHub (https://github.com/mcrl/FED)., Comment: 12 pages, 3 figures

Code generation with large language models has shown significant promise, especially when employing retrieval-augmented generation (RAG) with few-shot examples. However, selecting effective examples that enhance generation quality remains a challenging task, particularly when the target programming language (PL) is underrepresented. In this study, we present two key findings: (1) retrieving examples whose presented algorithmic plans can be referenced for generating the desired behavior significantly improves generation accuracy, and (2) converting code into pseudocode effectively captures such algorithmic plans, enhancing retrieval quality even when the source and the target PLs are different. Based on these findings, we propose Plan-as-query Example Retrieval for few-shot prompting in Code generation (PERC), a novel framework that utilizes algorithmic plans to identify and retrieve effective examples. We validate the effectiveness of PERC through extensive experiments on the CodeContests, HumanEval and MultiPL-E benchmarks: PERC consistently outperforms the state-of-the-art RAG methods in code generation, both when the source and target programming languages match or differ, highlighting its adaptability and robustness in diverse coding environments., Comment: Accepted by COLING 2025 main conference

Purpose: To develop and evaluate a new pulse sequence for highly accelerated distortion-free diffusion MRI (dMRI) by inserting an additional echo without prolonging TR, when generalized slice dithered enhanced resolution (gSlider) radiofrequency encoding is used for volumetric acquisition. Methods: A phase-reversed interleaved multi-echo acquisition (PRIME) was developed for rapid, high-resolution, and distortion-free dMRI, which includes two echoes where the first echo is for target diffusion-weighted imaging (DWI) acquisition with high-resolution and the second echo is acquired with either 1) lower-resolution for high-fidelity field map estimation, or 2) matching resolution to enable efficient diffusion relaxometry acquisitions. The sequence was evaluated on in vivo data acquired from healthy volunteers on clinical and Connectome 2.0 scanners. Results: In vivo experiments demonstrated that 1) high in-plane acceleration (Rin-plane of 5-fold with 2D partial Fourier) was achieved using the high-fidelity field maps estimated from the second echo, which was made at a lower resolution/acceleration to increase its SNR while matching the effective echo spacing of the first readout, 2) high-resolution diffusion relaxometry parameters were estimated from dual-echo PRIME data using a white matter model of multi-TE spherical mean technique (MTE-SMT), and 3) high-fidelity mesoscale DWI at 550 um isotropic resolution could be obtained in vivo by capitalizing on the high-performance gradients of the Connectome 2.0 scanner. Conclusion: The proposed PRIME sequence enabled highly accelerated, high-resolution, and distortion-free dMRI using an additional echo without prolonging scan time when gSlider encoding is utilized., Comment: 12 figures, 1 table

This paper aims to extend the code generation capability of large language models (LLMs) to automatically manage comprehensive software requirements from given textual descriptions. Such requirements include both functional (i.e. achieving expected behavior for inputs) and non-functional (e.g., time/space performance, robustness, maintainability) requirements. However, textual descriptions can either express requirements verbosely or may even omit some of them. We introduce ARCHCODE, a novel framework that leverages in-context learning to organize requirements observed in descriptions and to extrapolate unexpressed requirements from them. ARCHCODE generates requirements from given descriptions, conditioning them to produce code snippets and test cases. Each test case is tailored to one of the requirements, allowing for the ranking of code snippets based on the compliance of their execution results with the requirements. Public benchmarks show that ARCHCODE enhances to satisfy functional requirements, significantly improving Pass@k scores. Furthermore, we introduce HumanEval-NFR, the first evaluation of LLMs' non-functional requirements in code generation, demonstrating ARCHCODE's superiority over baseline methods. The implementation of ARCHCODE and the HumanEval-NFR benchmark are both publicly accessible., Comment: Accepted by ACL 2024 main conference

We present HyperSum, an extractive summarization framework that captures both the efficiency of traditional lexical summarization and the accuracy of contemporary neural approaches. HyperSum exploits the pseudo-orthogonality that emerges when randomly initializing vectors at extremely high dimensions ("blessing of dimensionality") to construct representative and efficient sentence embeddings. Simply clustering the obtained embeddings and extracting their medoids yields competitive summaries. HyperSum often outperforms state-of-the-art summarizers -- in terms of both summary accuracy and faithfulness -- while being 10 to 100 times faster. We open-source HyperSum as a strong baseline for unsupervised extractive summarization., Comment: ICASSP 2024

Changing-look (CL) Active Galactic Nuclei (AGNs), characterized by appearance/disappearance of broad emission lines in the span of a few years, present a challenge for the AGN unified model, whereby the Type 1 vs. Type 2 dichotomy results from orientation effects alone. We present a systematic study of a large sample of spectroscopically classified AGNs, using optical variability data from the Zwicky Transient Facility (ZTF) as well as follow-up spectroscopy data. We demonstrate that Type 1 vs. 2 AGN can be neatly separated on the basis of the variability metric $\sigma_{\rm QSO}$, which quantifies the resemblance of a light curve to a damp random walk model. For a small sub-sample, however, the ZTF light curves are inconsistent with their previous classification, suggesting the occurrence of a CL event. Specifically, we identify 35 (12) turn-on (turn-off) CL AGN candidates at $z < 0.35$. Based on follow-up spectroscopy, we confirm 17 (4) turn-on (turn-off) CL AGNs out of 21 (5) candidates, presenting a high success rate of our method. Our results suggest that the occurrence rate of CL AGNs is $\sim$0.3% over timescales of 5 to 20 years, and confirm that the CL transition typically occurs at the Eddington ratio of $\leq 0.01$., Comment: 23 pages, 12 figures. Accepted by ApJ

Conventional spoofing detection systems have heavily relied on the use of handcrafted features derived from speech data. However, a notable shift has recently emerged towards the direct utilization of raw speech waveforms, as demonstrated by methods like SincNet filters. This shift underscores the demand for more sophisticated audio sample features. Moreover, the success of deep learning models, particularly those utilizing large pretrained wav2vec 2.0 as a featurization front-end, highlights the importance of refined feature encoders. In response, this research assessed the representational capability of wav2vec 2.0 as an audio feature extractor, modifying the size of its pretrained Transformer layers through two key adjustments: (1) selecting a subset of layers starting from the leftmost one and (2) fine-tuning a portion of the selected layers from the rightmost one. We complemented this analysis with five spoofing detection back-end models, with a primary focus on AASIST, enabling us to pinpoint the optimal configuration for the selection and fine-tuning process. In contrast to conventional handcrafted features, our investigation identified several spoofing detection systems that achieve state-of-the-art performance in the ASVspoof 2019 LA dataset. This comprehensive exploration offers valuable insights into feature selection strategies, advancing the field of spoofing detection., Comment: 5 pages

Job shop scheduling problems represent a significant and complex facet of combinatorial optimization problems, which have traditionally been addressed through either exact or approximate solution methodologies. However, the practical application of these solutions is often challenged due to the complexity of real-world problems. Even when utilizing an approximate solution approach, the time required to identify a near-optimal solution can be prohibitively extensive, and the solutions derived are generally not applicable to new problems. This study proposes an innovative attention-based reinforcement learning method specifically designed for the category of job shop scheduling problems. This method integrates a policy gradient reinforcement learning approach with a modified transformer architecture. A key finding of this research is the ability of our trained learners within the proposed method to be repurposed for larger-scale problems that were not part of the initial training set. Furthermore, empirical evidence demonstrates that our approach surpasses the results of recent studies and outperforms commonly implemented heuristic rules. This suggests that our method offers a promising avenue for future research and practical application in the field of job shop scheduling problems.

Typical quantitative MRI (qMRI) methods estimate parameter maps after image reconstructing, which is prone to biases and error propagation. We propose a Nonlinear Conjugate Gradient (NLCG) optimizer for model-based T2/T1 estimation, which incorporates U-Net regularization trained in a scan-specific manner. This end-to-end method directly estimates qMRI maps from undersampled k-space data using mono-exponential signal modeling with zero-shot scan-specific neural network regularization to enable high fidelity T1 and T2 mapping. T2 and T1 mapping results demonstrate the ability of the proposed NLCG-Net to improve estimation quality compared to subspace reconstruction at high accelerations., Comment: 8 pages, 5 figures, submitted to International Society for Magnetic Resonance in Medicine 2024

This study aimed to analyze brain activity during various STEM activities, exploring the feasibility of classifying between different tasks. EEG brain data from twenty subjects engaged in five cognitive tasks were collected and segmented into 4-second clips. Power spectral densities of brain frequency waves were then analyzed. Testing different k-intervals with XGBoost, Random Forest, and Bagging Classifier revealed that Random Forest performed best, achieving a testing accuracy of 91.07% at an interval size of two. When utilizing all four EEG channels, cognitive flexibility was most recognizable. Task-specific classification accuracy showed the right frontal lobe excelled in mathematical processing and planning, the left frontal lobe in cognitive flexibility and mental flexibility, and the left temporoparietal lobe in connections. Notably, numerous connections between frontal and temporoparietal lobes were observed during STEM activities. This study contributes to a deeper understanding of implementing machine learning in analyzing brain activity and sheds light on the brain's mechanisms., Comment: 20 pages, 7 figures

This study investigated the use of forearm EMG data for distinguishing eight hand gestures, employing the Neural Network and Random Forest algorithms on data from ten participants. The Neural Network achieved 97 percent accuracy with 1000-millisecond windows, while the Random Forest achieved 85 percent accuracy with 200-millisecond windows. Larger window sizes improved gesture classification due to increased temporal resolution. The Random Forest exhibited faster processing at 92 milliseconds, compared to the Neural Network's 124 milliseconds. In conclusion, the study identified a Neural Network with a 1000-millisecond stream as the most accurate (97 percent), and a Random Forest with a 200-millisecond stream as the most efficient (85 percent). Future research should focus on increasing sample size, incorporating more hand gestures, and exploring different feature extraction methods and modeling algorithms to enhance system accuracy and efficiency., Comment: 21 pages, 7 figures

Purpose: We implemented the blip-up, blip-down circular echo planar imaging (BUDA-cEPI) sequence with readout and phase partial Fourier to reduced off-resonance effect and T2* blurring. BUDA-cEPI reconstruction with S-based low-rank modeling of local k-space neighborhoods (S-LORAKS) is shown to be effective at reconstructing the highly under-sampled BUDA-cEPI data, but it is computationally intensive. Thus, we developed an ML-based reconstruction technique termed "BUDA-cEPI RUN-UP" to enable fast reconstruction. Methods: BUDA-cEPI RUN-UP - a model-based framework that incorporates off-resonance and eddy current effects was unrolled through an artificial neural network with only six gradient updates. The unrolled network alternates between data consistency (i.e., forward BUDA-cEPI and its adjoint) and regularization steps where U-Net plays a role as the regularizer. To handle the partial Fourier effect, the virtual coil concept was also incorporated into the reconstruction to effectively take advantage of the smooth phase prior, and trained to predict the ground-truth images obtained by BUDA-cEPI with S-LORAKS. Results: BUDA-cEPI with S-LORAKS reconstruction enabled the management of off-resonance, partial Fourier, and residual aliasing artifacts. However, the reconstruction time is approximately 225 seconds per slice, which may not be practical in a clinical setting. In contrast, the proposed BUDA-cEPI RUN-UP yielded similar results to BUDA-cEPI with S-LORAKS, with less than a 5% normalized root mean square error detected, while the reconstruction time is approximately 3 seconds. Conclusion: BUDA-cEPI RUN-UP was shown to reduce the reconstruction time by ~88x when compared to the state-of-the-art technique, while preserving imaging details as demonstrated through DTI application., Comment: Number: Figures: 8 Tables: 3 References: 71

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then be used for a diverse set of tasks in a zero-shot way, similar to ``Contrastive Language-Image Pre-training (CLIP)'' and ``Locked-image Tuning (LiT)'' that have recently gained considerable attention. Most existing works for cross-modal representation alignment (including CLIP and LiT) use the standard contrastive training objective, which employs sets of positive and negative examples to align similar and repel dissimilar training data samples. However, similarity amongst training examples has a more continuous nature, thus calling for a more `non-binary' treatment. To address this, we propose a novel loss function called Continuously Weighted Contrastive Loss (CWCL) that employs a continuous measure of similarity. With CWCL, we seek to align the embedding space of one modality with another. Owing to the continuous nature of similarity in the proposed loss function, these models outperform existing methods for 0-shot transfer across multiple models, datasets and modalities. Particularly, we consider the modality pairs of image-text and speech-text and our models achieve 5-8% (absolute) improvement over previous state-of-the-art methods in 0-shot image classification and 20-30% (absolute) improvement in 0-shot speech-to-intent classification and keyword classification., Comment: Accepted to Neural Information Processing Systems (NeurIPS) 2023 conference

Diffusion MRI is commonly performed using echo-planar imaging (EPI) due to its rapid acquisition time. However, the resolution of diffusion-weighted images is often limited by magnetic field inhomogeneity-related artifacts and blurring induced by T2- and T2*-relaxation effects. To address these limitations, multi-shot EPI (msEPI) combined with parallel imaging techniques is frequently employed. Nevertheless, reconstructing msEPI can be challenging due to phase variation between multiple shots. In this study, we introduce a novel msEPI reconstruction approach called zero-MIRID (zero-shot self-supervised learning of Multi-shot Image Reconstruction for Improved Diffusion MRI). This method jointly reconstructs msEPI data by incorporating deep learning-based image regularization techniques. The network incorporates CNN denoisers in both k- and image-spaces, while leveraging virtual coils to enhance image reconstruction conditioning. By employing a self-supervised learning technique and dividing sampled data into three groups, the proposed approach achieves superior results compared to the state-of-the-art parallel imaging method, as demonstrated in an in-vivo experiment., Comment: 10 pages, 4 figures

Purpose: To develop and evaluate methods for 1) reconstructing 3D-quantification using an interleaved Look-Locker acquisition sequence with T2 preparation pulse (3D-QALAS) time-series images using a low-rank subspace method, which enables accurate and rapid T1 and T2 mapping, and 2) improving the fidelity of subspace QALAS by combining scan-specific deep-learning-based reconstruction and subspace modeling. Methods: A low-rank subspace method for 3D-QALAS (i.e., subspace QALAS) and zero-shot deep-learning subspace method (i.e., Zero-DeepSub) were proposed for rapid and high fidelity T1 and T2 mapping and time-resolved imaging using 3D-QALAS. Using an ISMRM/NIST system phantom, the accuracy and reproducibility of the T1 and T2 maps estimated using the proposed methods were evaluated by comparing them with reference techniques. The reconstruction performance of the proposed subspace QALAS using Zero-DeepSub was evaluated in vivo and compared with conventional QALAS at high reduction factors of up to 9-fold. Results: Phantom experiments showed that subspace QALAS had good linearity with respect to the reference methods while reducing biases and improving precision compared to conventional QALAS, especially for T2 maps. Moreover, in vivo results demonstrated that subspace QALAS had better g-factor maps and could reduce voxel blurring, noise, and artifacts compared to conventional QALAS and showed robust performance at up to 9-fold acceleration with Zero-DeepSub, which enabled whole-brain T1, T2, and PD mapping at 1 mm isotropic resolution within 2 min of scan time. Conclusion: The proposed subspace QALAS along with Zero-DeepSub enabled high fidelity and rapid whole-brain multiparametric quantification and time-resolved imaging., Comment: 24 figures, 4 tables

The broad line region (BLR) size-luminosity relation has paramount importance for estimating the mass of black holes in active galactic nuclei (AGNs). Traditionally, the size of the H$\beta$ BLR is often estimated from the optical continuum luminosity at 5100\angstrom{} , while the size of the H$\alpha$ BLR and its correlation with the luminosity is much less constrained. As a part of the Seoul National University AGN Monitoring Project (SAMP) which provides six-year photometric and spectroscopic monitoring data, we present our measurements of the H$\alpha$ lags of 6 high-luminosity AGNs. Combined with the measurements for 42 AGNs from the literature, we derive the size-luminosity relations of H$\alpha$ BLR against broad H$\alpha$ and 5100\angstrom{} continuum luminosities. We find the slope of the relations to be $0.61\pm0.04$ and $0.59\pm0.04$, respectively, which are consistent with the \hb{} size-luminosity relation. Moreover, we find a linear relation between the 5100\angstrom{} continuum luminosity and the broad H$\alpha$ luminosity across 7 orders of magnitude. Using these results, we propose a new virial mass estimator based on the H$\alpha$ broad emission line, finding that the previous mass estimates based on the scaling relations in the literature are overestimated by up to 0.7 dex at masses lower than $10^7$~M$_{\odot}$., Comment: Accepted for publication in ApJ (Jun. 25th, 2023). 21 pages, 12 figures

Purpose: To develop and evaluate a method for rapid estimation of multiparametric T1, T2, proton density (PD), and inversion efficiency (IE) maps from 3D-quantification using an interleaved Look-Locker acquisition sequence with T2 preparation pulse (3D-QALAS) measurements using self-supervised learning (SSL) without the need for an external dictionary. Methods: A SSL-based QALAS mapping method (SSL-QALAS) was developed for rapid and dictionary-free estimation of multiparametric maps from 3D-QALAS measurements. The accuracy of the reconstructed quantitative maps using dictionary matching and SSL-QALAS was evaluated by comparing the estimated T1 and T2 values with those obtained from the reference methods on an ISMRM/NIST phantom. The SSL-QALAS and the dictionary matching methods were also compared in vivo, and generalizability was evaluated by comparing the scan-specific, pre-trained, and transfer learning models. Results: Phantom experiments showed that both the dictionary matching and SSL-QALAS methods produced T1 and T2 estimates that had a strong linear agreement with the reference values in the ISMRM/NIST phantom. Further, SSL-QALAS showed similar performance with dictionary matching in reconstructing the T1, T2, PD, and IE maps on in vivo data. Rapid reconstruction of multiparametric maps was enabled by inferring the data using a pre-trained SSL-QALAS model within 10 s. Fast scan-specific tuning was also demonstrated by fine-tuning the pre-trained model with the target subject's data within 15 min. Conclusion: The proposed SSL-QALAS method enabled rapid reconstruction of multiparametric maps from 3D-QALAS measurements without an external dictionary or labeled ground-truth training data., Comment: 18 figures, 4 tables

Purpose: This work aims to develop a novel distortion-free 3D-EPI acquisition and image reconstruction technique for fast and robust, high-resolution, whole-brain imaging as well as quantitative T2* mapping. Methods: 3D-Blip-Up and -Down Acquisition (3D-BUDA) sequence is designed for both single- and multi-echo 3D GRE-EPI imaging using multiple shots with blip-up and -down readouts to encode B0 field map information. Complementary k-space coverage is achieved using controlled aliasing in parallel imaging (CAIPI) sampling across the shots. For image reconstruction, an iterative hard-thresholding algorithm is employed to minimize the cost function that combines field map information informed parallel imaging with the structured low-rank constraint for multi-shot 3D-BUDA data. Extending 3D-BUDA to multi-echo imaging permits T2* mapping. For this, we propose constructing a joint Hankel matrix along both echo and shot dimensions to improve the reconstruction. Results: Experimental results on in vivo multi-echo data demonstrate that, by performing joint reconstruction along with both echo and shot dimensions, reconstruction accuracy is improved compared to standard 3D-BUDA reconstruction. CAIPI sampling is further shown to enhance the image quality. For T2* mapping, T2* values from 3D-Joint-CAIPI-BUDA and reference multi-echo GRE are within limits of agreement as quantified by Bland-Altman analysis. Conclusions: The proposed technique enables rapid 3D distortion-free high-resolution imaging and T2* mapping. Specifically, 3D-BUDA enables 1-mm isotropic whole-brain imaging in 22 s at 3 T and 9 s on a 7 T scanner. The combination of multi-echo 3D-BUDA with CAIPI acquisition and joint reconstruction enables distortion-free whole-brain T2* mapping in 47 s at 1.1x1.1x1.0 mm3 resolution.

Purpose: Volumetric, high-resolution, quantitative mapping of brain tissue relaxation properties is hindered by long acquisition times and signal-to-noise (SNR) challenges. This study, for the first time, combines the time-efficient wave-CAIPI readouts into the 3D-quantification using an interleaved Look-Locker acquisition sequence with a T2 preparation pulse (3D-QALAS) acquisition scheme, enabling full brain quantitative T1, T2 and proton density (PD) maps at 1.15 mm3 isotropic voxels in only 3 minutes. Methods: Wave-CAIPI readouts were embedded in the standard 3D-QALAS encoding scheme, enabling full brain quantitative parameter maps (T1, T2, and PD) at acceleration factors of R=3x2 with minimum SNR loss due to g-factor penalties. The quantitative parameter maps were estimated using a dictionary-based mapping algorithm incorporating inversion efficiency and B1 field inhomogeneity. The quantitative maps using the accelerated protocol were quantitatively compared against those obtained from conventional 3D-QALAS sequence using GRAPPA acceleration of R=2 in the ISMRM NIST phantom, and ten healthy volunteers. Results: When tested in both the ISMRM/NIST phantom and ten healthy volunteers, the quantitative maps using the accelerated protocol showed excellent agreement against those obtained from conventional 3D-QALAS at RGRAPPA=2. Conclusion: 3D-QALAS enhanced with wave-CAIPI readouts enables time-efficient, full brain quantitative T1, T2, and PD mapping at 1.15 mm3 in 3 minutes at R=3x2 acceleration. When tested on the NIST phantom and ten healthy volunteers, the quantitative maps obtained from the accelerated wave-CAIPI 3D-QALAS protocol showed very similar values to those obtained from the standard 3D-QALAS (R=2) protocol, alluding to the robustness and reliability of the proposed methods.

In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech applications that require discriminative representation of consistent attributes within an utterance: speaker, language, emotion, and age. Existing frame-level self-supervised speech representation, e.g., wav2vec, can be used as utterance-level representation with pooling, but the models are usually large. There are also SSL techniques to learn utterance-level representation. One of the most successful is a contrastive method, which requires negative sampling: selecting alternative samples to contrast with the current sample (anchor). However, this does not ensure that all the negative samples belong to classes different from the anchor class without labels. This paper applies a non-contrastive self-supervised method to learn utterance-level embeddings. We adapted DIstillation with NO labels (DINO) from computer vision to speech. Unlike contrastive methods, DINO does not require negative sampling. We compared DINO to x-vector trained in a supervised manner. When transferred to down-stream tasks (speaker verification, speech emotion recognition (SER), and Alzheimer's disease detection), DINO outperformed x-vector. We studied the influence of several aspects during transfer learning such as dividing the fine-tuning process into steps, chunk lengths, or augmentation. During fine-tuning, tuning the last affine layers first and then the whole network surpassed fine-tuning all at once. Using shorter chunk lengths, although they generate more diverse inputs, did not necessarily improve performance, implying speech segments at least with a specific length are required for better performance per application. Augmentation was helpful in SER., Comment: EARLY ACCESS of IEEE JSTSP Special Issue on Self-Supervised Learning for Speech and Audio Processing

Considering the abundance of unlabeled speech data and the high labeling costs, unsupervised learning methods can be essential for better system development. One of the most successful methods is contrastive self-supervised methods, which require negative sampling: sampling alternative samples to contrast with the current sample (anchor). However, it is hard to ensure if all the negative samples belong to classes different from the anchor class without labels. This paper applies a non-contrastive self-supervised learning method on an unlabeled speech corpus to learn utterance-level embeddings. We used DIstillation with NO labels (DINO), proposed in computer vision, and adapted it to the speech domain. Unlike the contrastive methods, DINO does not require negative sampling. These embeddings were evaluated on speaker verification and emotion recognition. In speaker verification, the unsupervised DINO embedding with cosine scoring provided 4.38% EER on the VoxCeleb1 test trial. This outperforms the best contrastive self-supervised method by 40% relative in EER. An iterative pseudo-labeling training pipeline, not requiring speaker labels, further improved the EER to 1.89%. In emotion recognition, the DINO embedding performed 60.87, 79.21, and 56.98% in micro-f1 score on IEMOCAP, Crema-D, and MSP-Podcast, respectively. The results imply the generality of the DINO embedding to different speech applications., Comment: Accepted at Interspeech 2022