The development of robust, generalized models in human activity recognition (HAR) has been hindered by the scarcity of large-scale, labeled data sets. Recent work has shown that virtual IMU data extracted from videos using computer vision techniques can lead to substantial performance improvements when training HAR models combined with small portions of real IMU data. Inspired by recent advances in motion synthesis from textual descriptions and connecting Large Language Models (LLMs) to various AI models, we introduce an automated pipeline that first uses ChatGPT to generate diverse textual descriptions of activities. These textual descriptions are then used to generate 3D human motion sequences via a motion synthesis model, T2M-GPT, and later converted to streams of virtual IMU data. We benchmarked our approach on three HAR datasets (RealWorld, PAMAP2, and USC-HAD) and demonstrate that the use of virtual IMU training data generated using our new approach leads to significantly improved HAR model performance compared to only using real IMU data. Our approach contributes to the growing field of cross-modality transfer methods and illustrate how HAR models can be improved through the generation of virtual training data that do not require any manual effort.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Learning
·
模式崩潰
·
梯度消失
·
值域
·
We propose {\it HumanDiffusion,} a diffusion model trained from humans' perceptual gradients to learn an acceptable range of data for humans (i.e., human-acceptable distribution). Conventional HumanGAN aims to model the human-acceptable distribution wider than the real-data distribution by training a neural network-based generator with human-based discriminators. However, HumanGAN training tends to converge in a meaningless distribution due to the gradient vanishing or mode collapse and requires careful heuristics. In contrast, our HumanDiffusion learns the human-acceptable distribution through Langevin dynamics based on gradients of human perceptual evaluations. Our training iterates a process to diffuse real data to cover a wider human-acceptable distribution and can avoid the issues in the HumanGAN training. The evaluation results demonstrate that our HumanDiffusion can successfully represent the human-acceptable distribution without any heuristics for the training.
Ground-based solar image restoration is a computationally expensive procedure that involves nonlinear optimization techniques. The presence of atmospheric turbulence produces perturbations in individual images that make it necessary to apply blind deconvolution techniques. These techniques rely on the observation of many short exposure frames that are used to simultaneously infer the instantaneous state of the atmosphere and the unperturbed object. We have recently explored the use of machine learning to accelerate this process, with promising results. We build upon this previous work to propose several interesting improvements that lead to better models. As well, we propose a new method to accelerate the restoration based on algorithm unrolling. In this method, the image restoration problem is solved with a gradient descent method that is unrolled and accelerated aided by a few small neural networks. The role of the neural networks is to correct the estimation of the solution at each iterative step. The model is trained to perform the optimization in a small fixed number of steps with a curated dataset. Our findings demonstrate that both methods significantly reduce the restoration time compared to the standard optimization procedure. Furthermore, we showcase that these models can be trained in an unsupervised manner using observed images from three different instruments. Remarkably, they also exhibit robust generalization capabilities when applied to new datasets. To foster further research and collaboration, we openly provide the trained models, along with the corresponding training and evaluation code, as well as the training dataset, to the scientific community.
Motivated by recent advancements in text-to-image diffusion, we study erasure of specific concepts from the model's weights. While Stable Diffusion has shown promise in producing explicit or realistic artwork, it has raised concerns regarding its potential for misuse. We propose a fine-tuning method that can erase a visual concept from a pre-trained diffusion model, given only the name of the style and using negative guidance as a teacher. We benchmark our method against previous approaches that remove sexually explicit content and demonstrate its effectiveness, performing on par with Safe Latent Diffusion and censored training. To evaluate artistic style removal, we conduct experiments erasing five modern artists from the network and conduct a user study to assess the human perception of the removed styles. Unlike previous methods, our approach can remove concepts from a diffusion model permanently rather than modifying the output at the inference time, so it cannot be circumvented even if a user has access to model weights. Our code, data, and results are available at //erasing.baulab.info/
State-of-The-Art (SoTA) image captioning models often rely on the Microsoft COCO (MS-COCO) dataset for training. This dataset contains annotations provided by human annotators, who typically produce captions averaging around ten tokens. However, this constraint presents a challenge in effectively capturing complex scenes and conveying detailed information. Furthermore, captioning models tend to exhibit bias towards the ``average'' caption, which captures only the more general aspects. What would happen if we were able to automatically generate longer captions, thereby making them more detailed? Would these captions, evaluated by humans, be more or less representative of the image content compared to the original MS-COCO captions? In this paper, we present a novel approach to address previous challenges by showcasing how captions generated from different SoTA models can be effectively fused, resulting in richer captions. Our proposed method leverages existing models from the literature, eliminating the need for additional training. Instead, it utilizes an image-text based metric to rank the captions generated by SoTA models for a given image. Subsequently, the top two captions are fused using a Large Language Model (LLM). Experimental results demonstrate the effectiveness of our approach, as the captions generated by our model exhibit higher consistency with human judgment when evaluated on the MS-COCO test set. By combining the strengths of various SoTA models, our method enhances the quality and appeal of image captions, bridging the gap between automated systems and the rich, informative nature of human-generated descriptions. This advance opens up new possibilities for generating captions that are more suitable for the training of both vision-language and captioning models.
The integration of deep learning and neuroscience has been advancing rapidly, which has led to improvements in the analysis of brain activity and the understanding of deep learning models from a neuroscientific perspective. The reconstruction of visual experience from human brain activity is an area that has particularly benefited: the use of deep learning models trained on large amounts of natural images has greatly improved its quality, and approaches that combine the diverse information contained in visual experiences have proliferated rapidly in recent years. In this technical paper, by taking advantage of the simple and generic framework that we proposed (Takagi and Nishimoto, CVPR 2023), we examine the extent to which various additional decoding techniques affect the performance of visual experience reconstruction. Specifically, we combined our earlier work with the following three techniques: using decoded text from brain activity, nonlinear optimization for structural image reconstruction, and using decoded depth information from brain activity. We confirmed that these techniques contributed to improving accuracy over the baseline. We also discuss what researchers should consider when performing visual reconstruction using deep generative models trained on large datasets. Please check our webpage at //sites.google.com/view/stablediffusion-with-brain/. Code is also available at //github.com/yu-takagi/StableDiffusionReconstruction.
Humankind is entering a novel creative era in which anybody can synthesize digital information using generative artificial intelligence (AI). Text-to-image generation, in particular, has become vastly popular and millions of practitioners produce AI-generated images and AI art online. This chapter first gives an overview of the key developments that enabled a healthy co-creative online ecosystem around text-to-image generation to rapidly emerge, followed by a high-level description of key elements in this ecosystem. A particular focus is placed on prompt engineering, a creative practice that has been embraced by the AI art community. It is then argued that the emerging co-creative ecosystem constitutes an intelligent system on its own - a system that both supports human creativity, but also potentially entraps future generations and limits future development efforts in AI. The chapter discusses the potential risks and dangers of cultivating this co-creative ecosystem, such as the bias inherent in today's training data, potential quality degradation in future image generation systems due to synthetic data becoming common place, and the potential long-term effects of text-to-image generation on people's imagination, ambitions, and development.
Voice assistants have sharply risen in popularity in recent years, but their use has been limited mostly to simple applications like music, hands-free search, or control of internet-of-things devices. What would it take for voice assistants to guide people through more complex tasks? In our work, we study the limitations of the dominant approach voice assistants take to complex task guidance: reading aloud written instructions. Using recipes as an example, we observe twelve participants cook at home with a state-of-the-art voice assistant. We learn that the current approach leads to nine challenges, including obscuring the bigger picture, overwhelming users with too much information, and failing to communicate affordances. Instructions delivered by a voice assistant are especially difficult because they cannot be skimmed as easily as written instructions. Alexa in particular did not surface crucial details to the user or answer questions well. We draw on our observations to propose eight ways in which voice assistants can ``rewrite the script'' -- summarizing, signposting, splitting, elaborating, volunteering, reordering, redistributing, and visualizing -- to transform written sources into forms that are readily communicated through spoken conversation. We conclude with a vision of how modern advancements in natural language processing can be leveraged for intelligent agents to guide users effectively through complex tasks.
Automated audio captioning (AAC) is an important cross-modality translation task, aiming at generating descriptions for audio clips. However, captions generated by previous AAC models have faced ``false-repetition'' errors due to the training objective. In such scenarios, we propose a new task of AAC error correction and hope to reduce such errors by post-processing AAC outputs. To tackle this problem, we use observation-based rules to corrupt captions without errors, for pseudo grammatically-erroneous sentence generation. One pair of corrupted and clean sentences can thus be used for training. We train a neural network-based model on the synthetic error dataset and apply the model to correct real errors in AAC outputs. Results on two benchmark datasets indicate that our approach significantly improves fluency while maintaining semantic information.
Despite the notable accomplishments of deep object detection models, a major challenge that persists is the requirement for extensive amounts of training data. The process of procuring such real-world data is a laborious undertaking, which has prompted researchers to explore new avenues of research, such as synthetic data generation techniques. This study presents a framework for the generation of synthetic datasets by fine-tuning pretrained stable diffusion models. The synthetic datasets are then manually annotated and employed for training various object detection models. These detectors are evaluated on a real-world test set of 331 images and compared against a baseline model that was trained on real-world images. The results of this study reveal that the object detection models trained on synthetic data perform similarly to the baseline model. In the context of apple detection in orchards, the average precision deviation with the baseline ranges from 0.09 to 0.12. This study illustrates the potential of synthetic data generation techniques as a viable alternative to the collection of extensive training data for the training of deep models.
Exercise-based rehabilitation programs have been shown to enhance quality of life and reduce mortality and rehospitalizations. AI-driven virtual rehabilitation programs enable patients to complete exercises independently at home while AI algorithms can analyze exercise data to provide feedback to patients and report their progress to clinicians. This paper introduces a novel approach to assessing the quality of rehabilitation exercises using RGB video. Sequences of skeletal body joints are extracted from consecutive RGB video frames and analyzed by many-to-one sequential neural networks to evaluate exercise quality. Existing datasets for exercise rehabilitation lack adequate samples for training deep sequential neural networks to generalize effectively. A cross-modal data augmentation approach is proposed to resolve this problem. Visual augmentation techniques are applied to video data, and body joints extracted from the resulting augmented videos are used for training sequential neural networks. Extensive experiments conducted on the KInematic assessment of MOvement and clinical scores for remote monitoring of physical REhabilitation (KIMORE) dataset, demonstrate the superiority of the proposed method over previous baseline approaches. The ablation study highlights a significant enhancement in exercise quality assessment following cross-modal augmentation.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191