Computed Tomography (CT) is a medical imaging modality that can generate more informative 3D images than 2D X-rays. However, this advantage comes at the expense of more radiation exposure, higher costs, and longer acquisition time. Hence, the reconstruction of 3D CT images using a limited number of 2D X-rays has gained significant importance as an economical alternative. Nevertheless, existing methods primarily prioritize minimizing pixel/voxel-level intensity discrepancies, often neglecting the preservation of textural details in the synthesized images. This oversight directly impacts the quality of the reconstructed images and thus affects the clinical diagnosis. To address the deficits, this paper presents a new self-driven generative adversarial network model (SdCT-GAN), which is motivated to pay more attention to image details by introducing a novel auto-encoder structure in the discriminator. In addition, a Sobel Gradient Guider (SGG) idea is applied throughout the model, where the edge information from the 2D X-ray image at the input can be integrated. Moreover, LPIPS (Learned Perceptual Image Patch Similarity) evaluation metric is adopted that can quantitatively evaluate the fine contours and textures of reconstructed images better than the existing ones. Finally, the qualitative and quantitative results of the empirical studies justify the power of the proposed model compared to mainstream state-of-the-art baselines.
Rhetorical Structure Theory based Discourse Parsing (RST-DP) explores how clauses, sentences, and large text spans compose a whole discourse and presents the rhetorical structure as a hierarchical tree. Existing RST parsing pipelines construct rhetorical structures without the knowledge of document-level content structures, which causes relatively low performance when predicting the discourse relations for large text spans. Recognizing the value of high-level content-related information in facilitating discourse relation recognition, we propose a novel pipeline for RST-DP that incorporates structure-aware news content sentence representations derived from the task of News Discourse Profiling. By incorporating only a few additional layers, this enhanced pipeline exhibits promising performance across various RST parsing metrics.
In the realm of Large Language Models, the balance between instruction data quality and quantity has become a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from vast open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal tool to identify discrepancies between a model's expected responses and its autonomous generation prowess. Through the adept application of IFD, cherry samples are pinpointed, leading to a marked uptick in model training efficiency. Empirical validations on renowned datasets like Alpaca and WizardLM underpin our findings; with a mere 10% of conventional data input, our strategy showcases improved results. This synthesis of self-guided cherry-picking and the IFD metric signifies a transformative leap in the optimization of LLMs, promising both efficiency and resource-conscious advancements.
Data is the cornerstone of deep learning. This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection. Existing methods for scaling up detection-oriented data often require manual collection or generative models to obtain target images, followed by data augmentation and labeling to produce training pairs, which are costly, complex, or lacking diversity. To address these issues, we presentDiffusionEngine (DE), a data scaling-up engine that provides high-quality detection-oriented training pairs in a single stage. DE consists of a pre-trained diffusion model and an effective Detection-Adapter, contributing to generating scalable, diverse and generalizable detection data in a plug-and-play manner. Detection-Adapter is learned to align the implicit semantic and location knowledge in off-the-shelf diffusion models with detection-aware signals to make better bounding-box predictions. Additionally, we contribute two datasets, i.e., COCO-DE and VOC-DE, to scale up existing detection benchmarks for facilitating follow-up research. Extensive experiments demonstrate that data scaling-up via DE can achieve significant improvements in diverse scenarios, such as various detection algorithms, self-supervised pre-training, data-sparse, label-scarce, cross-domain, and semi-supervised learning. For example, when using DE with a DINO-based adapter to scale up data, mAP is improved by 3.1% on COCO, 7.6% on VOC, and 11.5% on Clipart.
This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals. We introduce three strategies: (1) Transfer learning to initialize the speaker embedding network, improving generalization and reducing overfitting. (2) Knowledge distillation to train a more flexible speaker verification model, incorporating frame-level ASR loss as an auxiliary task. (3) A lightweight speaker adaptor for efficient feature conversion without altering the original ASR Conformer, allowing parallel ASR and speaker verification. Experiments on VoxCeleb show significant improvements: transfer learning yields a 0.48% EER, knowledge distillation results in a 0.43% EER, and the speaker adaptor approach, with just an added 4.92M parameters to a 130.94M-parameter model, achieves a 0.57% EER. Overall, our methods effectively transfer ASR capabilities to speaker verification tasks.
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model compression. However, existing knowledge distillation techniques lack an in-depth investigation and analysis of VLP, and practical guidelines for VLP-oriented distillation are still not yet explored. In this paper, we present DLIP, a simple yet efficient Distilling Language-Image Pre-training framework, through which we investigate how to distill a light VLP model. Specifically, we dissect the model distillation from multiple dimensions, such as the architecture characteristics of different modules and the information transfer of different modalities. We conduct comprehensive experiments and provide insights on distilling a light but performant VLP model. Experimental results reveal that DLIP can achieve a state-of-the-art accuracy/efficiency trade-off across diverse cross-modal tasks, e.g., image-text retrieval, image captioning and visual question answering. For example, DLIP compresses BLIP by 1.9x, from 213M to 108M parameters, while achieving comparable or better performance. Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22.4% parameters and 24.8% FLOPs compared to the teacher model and accelerates inference speed by 2.7x.
In this paper, we contribute a novel and extensive dataset for speaker verification, which contains noisy 38k identities/1.45M utterances (VoxBlink) and relatively cleaned 18k identities/1.02M (VoxBlink-Clean) utterances for training. Firstly, we accumulate a 60K+ users' list with their avatars and download their short videos on YouTube. We then established an automatic and scalable pipeline to extract relevant speech and video segments from these videos. To our knowledge, the VoxBlink dataset is one of the largest speaker recognition datasets available. Secondly, we conduct a series of experiments based on different backbones trained on a mix of the VoxCeleb2 and the VoxBlink-Clean. Our findings highlight a notable performance improvement, ranging from 13% to 30%, across different backbone architectures upon integrating our dataset for training. The dataset will be made publicly available shortly.
This paper introduces our system designed for Track 2, which focuses on locating manipulated regions, in the second Audio Deepfake Detection Challenge (ADD 2023). Our approach involves the utilization of multiple detection systems to identify splicing regions and determine their authenticity. Specifically, we train and integrate two frame-level systems: one for boundary detection and the other for deepfake detection. Additionally, we employ a third VAE model trained exclusively on genuine data to determine the authenticity of a given audio clip. Through the fusion of these three systems, our top-performing solution for the ADD challenge achieves an impressive 82.23% sentence accuracy and an F1 score of 60.66%. This results in a final ADD score of 0.6713, securing the first rank in Track 2 of ADD 2023.
This paper is the system description of the DKU-MSXF System for the track1, track2 and track3 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). For Track 1, we utilize a network structure based on ResNet for training. By constructing a cross-age QMF training set, we achieve a substantial improvement in system performance. For Track 2, we inherite the pre-trained model from Track 1 and conducte mixed training by incorporating the VoxBlink-clean dataset. In comparison to Track 1, the models incorporating VoxBlink-clean data exhibit a performance improvement by more than 10% relatively. For Track3, the semi-supervised domain adaptation task, a novel pseudo-labeling method based on triple thresholds and sub-center purification is adopted to make domain adaptation. The final submission achieves mDCF of 0.1243 in task1, mDCF of 0.1165 in Track 2 and EER of 4.952% in Track 3.