Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the state-of-the-art performance and latency trade-off on mobile devices by incorporating efficient architectural designs of ViTs into CNNs. Here, to achieve real-time segmenting anything on mobile devices, following MobileSAM, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model. Extensive experiments show that RepViT-SAM can enjoy significantly better zero-shot transfer capability than MobileSAM, along with nearly $10\times$ faster inference speed. The code and models are available at \url{https://github.com/THU-MIG/RepViT}.
Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the non-deterministic fact of speech-driven 3D face animation and employ the diffusion model for the task. However, personalizing facial animation and accelerating animation generation are still two major limitations of existing diffusion-based methods. To address the above limitations, we propose DiffusionTalker, a diffusion-based method that utilizes contrastive learning to personalize 3D facial animation and knowledge distillation to accelerate 3D animation generation. Specifically, to enable personalization, we introduce a learnable talking identity to aggregate knowledge in audio sequences. The proposed identity embeddings extract customized facial cues across different people in a contrastive learning manner. During inference, users can obtain personalized facial animation based on input audio, reflecting a specific talking style. With a trained diffusion model with hundreds of steps, we distill it into a lightweight model with 8 steps for acceleration. Extensive experiments are conducted to demonstrate that our method outperforms state-of-the-art methods. The code will be released.
Reconfigurable intelligent surfaces (RISs) are considered as an enabling technology for the upcoming sixth generation of wireless systems, exhibiting significant potential for radio localization and sensing. An RIS is usually treated as an anchor point with known position and orientation when deployed to offer user localization. However, it can also be attached to a user to enable its localization in a semi-passive manner. In this paper, we consider a static user equipped with an RIS and study the RIS localization problem (i.e., joint three-dimensional position and orientation estimation), when operating in a system comprising a single-antenna transmitter and multiple synchronized single-antenna receivers with known locations. We present a multi-stage estimator using time-of-arrival and spatial frequency measurements, and derive the Cram\'er-Rao lower bounds for the estimated parameters to validate the estimator's performance. Our simulation results demonstrate the efficiency of the proposed RIS state estimation approach under various system operation parameters.
Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonstrated the impressive performance of large generative language models on downstream tasks. However, existing generative language models generally neglect an inherent challenge in text corpus during training, i.e., the imbalance between frequent tokens and infrequent ones. It can lead a language model to be dominated by common and easy-to-learn tokens, thereby overlooking the infrequent and difficult-to-learn ones. To alleviate that, we propose an Information Entropy Loss (InfoEntropy Loss) function. During training, it can dynamically assess the learning difficulty of a to-be-learned token, according to the information entropy of the corresponding predicted probability distribution over the vocabulary. Then it scales the training loss adaptively, trying to lead the model to focus more on the difficult-to-learn tokens. On the Pile dataset, we train generative language models at different scales of 436M, 1.1B, and 6.7B parameters. Experiments reveal that models incorporating the proposed InfoEntropy Loss can gain consistent performance improvement on downstream benchmarks.
Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due to data scarcity. In this work, we explore the use of large language models (LLMs) to edit code based on user instructions, covering a broad range of implicit tasks such as comment insertion, code optimization, and code refactoring. To facilitate this, we introduce InstructCoder, the first dataset designed to adapt LLMs for general-purpose code editing, containing highdiversity code-editing tasks. It consists of over 114,000 instruction-input-output triplets and covers multiple distinct code editing scenarios. The dataset is systematically expanded through an iterative process that commences with code editing data sourced from GitHub commits as seed tasks. Seed and generated tasks are used subsequently to prompt ChatGPT for more task data. Our experiments demonstrate that open-source LLMs fine-tuned on InstructCoder can edit code correctly based on users' instructions most of the time, exhibiting unprecedented code-editing performance levels. Such results suggest that proficient instruction-finetuning can lead to significant amelioration in code editing abilities. The dataset and the source code are available at https://github.com/qishenghu/CodeInstruct.
Bayesian personalized federated learning (BPFL) addresses challenges in existing personalized FL (PFL). BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the statistical heterogeneity of client data. In PFL, some recent preliminary work proposes to decompose hidden neural representations into shared and local components and demonstrates interesting results. However, most of them do not address client uncertainty and heterogeneity in FL systems, while appropriately decoupling neural representations is challenging and often ad hoc. In this paper, we make the first attempt to introduce a general BPFL framework to decompose and jointly learn shared and personalized uncertainty representations on statistically heterogeneous client data over time. A Bayesian federated neural network BPFed instantiates BPFL by jointly learning cross-client shared uncertainty and client-specific personalized uncertainty over statistically heterogeneous and randomly participating clients. We further involve continual updating of prior distribution in BPFed to speed up the convergence and avoid catastrophic forgetting. Theoretical analysis and guarantees are provided in addition to the experimental evaluation of BPFed against the diversified baselines.
Unsupervised domain adaptation aims to transfer knowledge from a fully-labeled source domain to an unlabeled target domain. However, in real-world scenarios, providing abundant labeled data even in the source domain can be infeasible due to the difficulty and high expense of annotation. To address this issue, recent works consider the Few-shot Unsupervised Domain Adaptation (FUDA) where only a few source samples are labeled, and conduct knowledge transfer via self-supervised learning methods. Yet existing methods generally overlook that the sparse label setting hinders learning reliable source knowledge for transfer. Additionally, the learning difficulty difference in target samples is different but ignored, leaving hard target samples poorly classified. To tackle both deficiencies, in this paper, we propose a novel Confidence-based Visual Dispersal Transfer learning method (C-VisDiT) for FUDA. Specifically, C-VisDiT consists of a cross-domain visual dispersal strategy that transfers only high-confidence source knowledge for model adaptation and an intra-domain visual dispersal strategy that guides the learning of hard target samples with easy ones. We conduct extensive experiments on Office-31, Office-Home, VisDA-C, and DomainNet benchmark datasets and the results demonstrate that the proposed C-VisDiT significantly outperforms state-of-the-art FUDA methods. Our code is available at https://github.com/Bostoncake/C-VisDiT.
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. Consequently, researchers have dedicated themselves to compressing redundant information in ViTs for acceleration. However, they generally sparsely drop redundant image tokens by token pruning or brutally remove channels by channel pruning, leading to a sub-optimal balance between model performance and inference speed. They are also disadvantageous in transferring compressed models to downstream vision tasks that require the spatial structure of images, such as semantic segmentation. To tackle these issues, we propose a joint compression method for ViTs that offers both high accuracy and fast inference speed, while also maintaining favorable transferability to downstream tasks (CAIT). Specifically, we introduce an asymmetric token merging (ATME) strategy to effectively integrate neighboring tokens. It can successfully compress redundant token information while preserving the spatial structure of images. We further employ a consistent dynamic channel pruning (CDCP) strategy to dynamically prune unimportant channels in ViTs. Thanks to CDCP, insignificant channels in multi-head self-attention modules of ViTs can be pruned uniformly, greatly enhancing the model compression. Extensive experiments on benchmark datasets demonstrate that our proposed method can achieve state-of-the-art performance across various ViTs. For example, our pruned DeiT-Tiny and DeiT-Small achieve speedups of 1.7$\times$ and 1.9$\times$, respectively, without accuracy drops on ImageNet. On the ADE20k segmentation dataset, our method can enjoy up to 1.31$\times$ speedups with comparable mIoU. Our code will be publicly available.
Fusing multi-modal data can improve the performance of deep learning models. However, missing modalities are common for medical data due to patients' specificity, which is detrimental to the performance of multi-modal models in applications. Therefore, it is critical to adapt the models to missing modalities. This study aimed to develop an efficient multi-modal fusion architecture for medical data that was robust to missing modalities and further improved the performance on disease diagnosis.X-ray chest radiographs for the image modality, radiology reports for the text modality, and structured value data for the tabular data modality were fused in this study. Each modality pair was fused with a Transformer-based bi-modal fusion module, and the three bi-modal fusion modules were then combined into a tri-modal fusion framework. Additionally, multivariate loss functions were introduced into the training process to improve model's robustness to missing modalities in the inference process. Finally, we designed comparison and ablation experiments for validating the effectiveness of the fusion, the robustness to missing modalities and the enhancements from each key component. Experiments were conducted on MIMIC-IV, MIMIC-CXR with the 14-label disease diagnosis task. Areas under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC) were used to evaluate models' performance. The experimental results demonstrated that our proposed multi-modal fusion architecture effectively fused three modalities and showed strong robustness to missing modalities. This method is hopeful to be scaled to more modalities to enhance the clinical practicality of the model.