Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can perform randomized smoothing on any classifier via a simple "denoise-and-classify" pipeline, so-called denoised smoothing, given that an accurate denoiser is available - such as diffusion model. In this paper, we present scalable methods to address the current trade-off between certified robustness and accuracy in denoised smoothing. Our key idea is to "selectively" apply smoothing among multiple noise scales, coined multi-scale smoothing, which can be efficiently implemented with a single diffusion model. This approach also suggests a new objective to compare the collective robustness of multi-scale smoothed classifiers, and questions which representation of diffusion model would maximize the objective. To address this, we propose to further fine-tune diffusion model (a) to perform consistent denoising whenever the original image is recoverable, but (b) to generate rather diverse outputs otherwise. Our experiments show that the proposed multi-scale smoothing scheme combined with diffusion fine-tuning enables strong certified robustness available with high noise level while maintaining its accuracy closer to non-smoothed classifiers.
While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically, due to the low information density of speech data, the transformed discrete speech unit sequence is much longer than the corresponding text transcription, posing significant challenges to existing auto-regressive models. Furthermore, it is not optimal to brutally apply discrete diffusion on the speech unit sequence while disregarding the continuous space structure, which will degrade the generation performance significantly. In this paper, we propose a novel diffusion model by applying the diffusion forward process in the \textit{continuous} speech representation space, while employing the diffusion backward process in the \textit{discrete} speech unit space. In this way, we preserve the semantic structure of the continuous speech representation space in the diffusion process and integrate the continuous and discrete diffusion models. We conduct extensive experiments on the textless direct speech-to-speech translation task, where the proposed method achieves comparable results to the computationally intensive auto-regressive baselines (500 steps on average) with significantly fewer decoding steps (50 steps).
Automatic sign language recognition (SLR) is an important topic within the areas of human-computer interaction and machine learning. On the one hand, it poses a complex challenge that requires the intervention of various knowledge areas, such as video processing, image processing, intelligent systems and linguistics. On the other hand, robust recognition of sign language could assist in the translation process and the integration of hearing-impaired people, as well as the teaching of sign language for the hearing population. SLR systems usually employ Hidden Markov Models, Dynamic Time Warping or similar models to recognize signs. Such techniques exploit the sequential ordering of frames to reduce the number of hypothesis. This paper presents a general probabilistic model for sign classification that combines sub-classifiers based on different types of features such as position, movement and handshape. The model employs a bag-of-words approach in all classification steps, to explore the hypothesis that ordering is not essential for recognition. The proposed model achieved an accuracy rate of 97% on an Argentinian Sign Language dataset containing 64 classes of signs and 3200 samples, providing some evidence that indeed recognition without ordering is possible.
The rising importance of 3D representation learning, pivotal in computer vision, autonomous driving, and robotics, is evident. However, a prevailing trend, which straightforwardly resorted to transferring 2D alignment strategies to the 3D domain, encounters three distinct challenges: (1) Information Degradation: This arises from the alignment of 3D data with mere single-view 2D images and generic texts, neglecting the need for multi-view images and detailed subcategory texts. (2) Insufficient Synergy: These strategies align 3D representations to image and text features individually, hampering the overall optimization for 3D models. (3) Underutilization: The fine-grained information inherent in the learned representations is often not fully exploited, indicating a potential loss in detail. To address these issues, we introduce JM3D, a comprehensive approach integrating point cloud, text, and image. Key contributions include the Structured Multimodal Organizer (SMO), enriching vision-language representation with multiple views and hierarchical text, and the Joint Multi-modal Alignment (JMA), combining language understanding with visual representation. Our advanced model, JM3D-LLM, marries 3D representation with large language models via efficient fine-tuning. Evaluations on ModelNet40 and ScanObjectNN establish JM3D's superiority. The superior performance of JM3D-LLM further underscores the effectiveness of our representation transfer approach. Our code and models are available at https://github.com/Mr-Neko/JM3D.
Detecting misleading patterns in automated diagnostic assistance systems, such as those powered by Artificial Intelligence, is critical to ensuring their reliability, particularly in healthcare. Current techniques for evaluating deep learning models cannot visualize confounding factors at a diagnostic level. Here, we propose a self-conditioned diffusion model termed DiffChest and train it on a dataset of 515,704 chest radiographs from 194,956 patients from multiple healthcare centers in the United States and Europe. DiffChest explains classifications on a patient-specific level and visualizes the confounding factors that may mislead the model. We found high inter-reader agreement when evaluating DiffChest's capability to identify treatment-related confounders, with Fleiss' Kappa values of 0.8 or higher across most imaging findings. Confounders were accurately captured with 11.1% to 100% prevalence rates. Furthermore, our pretraining process optimized the model to capture the most relevant information from the input radiographs. DiffChest achieved excellent diagnostic accuracy when diagnosing 11 chest conditions, such as pleural effusion and cardiac insufficiency, and at least sufficient diagnostic accuracy for the remaining conditions. Our findings highlight the potential of pretraining based on diffusion models in medical image classification, specifically in providing insights into confounding factors and model robustness.
Joint source and channel coding (JSCC) has attracted increasing attention due to its robustness and high efficiency. However, JSCC is vulnerable to privacy leakage due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-protective JSCC (DIB-PPJSCC) for image transmission, which aims at protecting private information as well as achieving superior communication performance at the legitimate receiver. In particular, we propose a DIB objective to disentangle private and public information. The goal is to compress the private information in the public subcodewords, preserve the private information in the private subcodewords and improve the reconstruction quality simultaneously. In order to optimize JSCC neural networks using the DIB objective, we derive a differentiable estimation of the DIB objective based on the variational approximation and the density-ratio trick. Additionally, we design a password-based privacy-protective (PP) algorithm which can be jointly optimized with JSCC neural networks to encrypt the private subcodewords. Specifically, we employ a private information encryptor to encrypt the private subcodewords before transmission, and a corresponding decryptor to recover the private information at the legitimate receiver. A loss function for jointly training the encryptor, decryptor and JSCC decoder is derived based on the maximum entropy principle, which aims at maximizing the eavesdropping uncertainty as well as improving the reconstruction quality. Experimental results show that DIB-PPJSCC can reduce the eavesdropping accuracy on private information up to $15\%$ and reduce $10\%$ inference time compared to existing privacy-protective JSCC and traditional separate methods.
Multi-modal image registration is a crucial pre-processing step in many medical applications. However, it is a challenging task due to the complex intensity relationships between different imaging modalities, which can result in large discrepancy in image appearance. The success of multi-modal image registration, whether it is conventional or learning based, is predicated upon the choice of an appropriate distance (or similarity) measure. Particularly, deep learning registration algorithms lack in accuracy or even fail completely when attempting to register data from an "unseen" modality. In this work, we present Modality Agnostic Distance (MAD), a deep image distance}] measure that utilises random convolutions to learn the inherent geometry of the images while being robust to large appearance changes. Random convolutions are geometry-preserving modules which we use to simulate an infinite number of synthetic modalities alleviating the need for aligned paired data during training. We can therefore train MAD on a mono-modal dataset and successfully apply it to a multi-modal dataset. We demonstrate that not only can MAD affinely register multi-modal images successfully, but it has also a larger capture range than traditional measures such as Mutual Information and Normalised Gradient Fields.
We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V. As illustrated in Fig. 1 (right), we employ off-the-shelf interactive segmentation models, such as SAM, to partition an image into regions at different levels of granularity, and overlay these regions with a set of marks e.g., alphanumerics, masks, boxes. Using the marked image as input, GPT-4V can answer the questions that require visual grounding. We perform a comprehensive empirical study to validate the effectiveness of SoM on a wide range of fine-grained vision and multimodal tasks. For example, our experiments show that GPT-4V with SoM outperforms the state-of-the-art fully-finetuned referring segmentation model on RefCOCOg in a zero-shot setting.
Our paper presents a robust framework for UWB-based static gesture recognition, leveraging proprietary UWB radar sensor technology. Extensive data collection efforts were undertaken to compile datasets containing five commonly used gestures. Our approach involves a comprehensive data pre-processing pipeline that encompasses outlier handling, aspect ratio-preserving resizing, and false-color image transformation. Both CNN and MobileNet models were trained on the processed images. Remarkably, our best-performing model achieved an accuracy of 96.78%. Additionally, we developed a user-friendly GUI framework to assess the model's system resource usage and processing times, which revealed low memory utilization and real-time task completion in under one second. This research marks a significant step towards enhancing static gesture recognition using UWB technology, promising practical applications in various domains.
We introduce Hyper-Skin, a hyperspectral dataset covering wide range of wavelengths from visible (VIS) spectrum (400nm - 700nm) to near-infrared (NIR) spectrum (700nm - 1000nm), uniquely designed to facilitate research on facial skin-spectra reconstruction. By reconstructing skin spectra from RGB images, our dataset enables the study of hyperspectral skin analysis, such as melanin and hemoglobin concentrations, directly on the consumer device. Overcoming limitations of existing datasets, Hyper-Skin consists of diverse facial skin data collected with a pushbroom hyperspectral camera. With 330 hyperspectral cubes from 51 subjects, the dataset covers the facial skin from different angles and facial poses. Each hyperspectral cube has dimensions of 1024$\times$1024$\times$448, resulting in millions of spectra vectors per image. The dataset, carefully curated in adherence to ethical guidelines, includes paired hyperspectral images and synthetic RGB images generated using real camera responses. We demonstrate the efficacy of our dataset by showcasing skin spectra reconstruction using state-of-the-art models on 31 bands of hyperspectral data resampled in the VIS and NIR spectrum. This Hyper-Skin dataset would be a valuable resource to NeurIPS community, encouraging the development of novel algorithms for skin spectral reconstruction while fostering interdisciplinary collaboration in hyperspectral skin analysis related to cosmetology and skin's well-being. Instructions to request the data and the related benchmarking codes are publicly available at: \url{https://github.com/hyperspectral-skin/Hyper-Skin-2023}.