A Realistic Radar Ray Tracing Simulator for Hand Pose Imaging

With the increasing popularity of human-computer interaction applications, there is also growing interest in generating sufficiently large and diverse data sets for automatic radar-based recognition of hand poses and gestures. Radar simulations are a vital approach to generating training data (e.g., for machine learning). Therefore, this work applies a ray tracing method to radar imaging of the hand. The performance of the proposed simulation approach is verified by a comparison of simulation and measurement data based on an imaging radar with a high lateral resolution. In addition, the surface material model incorporated into the ray tracer is highlighted in more detail and parameterized for radar hand imaging. Measurements and simulations show a very high similarity between synthetic and real radar image captures. The presented results demonstrate that it is possible to generate very realistic simulations of radar measurement data even for complex radar hand pose imaging systems.

Distributed Radar Imaging Based on Accelerated ADMM

The ability of widely distributed radar systems to capture diverse spatial scattering properties substantially improves radar imaging performance. Traditional imaging methods leverage regularized optimization techniques to reconstruct sparse images from local sensors and later combine them to create a global image. Alternatively, we proposed in an earlier work a joint reconstruction technique based on two problem formulations according to the optimization framework of the Alternating Direction Method of Multipliers (ADMM). The joint reconstruction of the global image offers faster convergence, flexible implementation, and a general distributed reconstruction framework. However, despite its benefits, ADMM framework still exhibits a slow convergence rate, making its employment in some contexts impractical. In this paper, we introduce a heuristic method to accelerate the convergence of the previously proposed ADMM formulations based on the gradual elimination of the already converged pixels in accordance with a predetermined criterion. In addition to reducing running time, the accelerated implementation offers reduced computational complexity and lower communication cost between the sensors during iterative updates.

From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement

Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. However, these methods have limited exploration in another major visibility damage, the glow effects in real night scenes. Glow effects are inevitable in the presence of artificial light sources and cause further diffused blurring when directly enhanced. To settle this issue, we innovatively consider the glow suppression task as learning physical glow generation via multiple scattering estimation according to the Atmospheric Point Spread Function (APSF). In response to the challenges posed by uneven glow intensity and varying source shapes, an APSF-based Nighttime Imaging Model with Near-field Light Sources (NIM-NLS) is specifically derived to design a scalable Light-aware Blind Deconvolution Network (LBDN). The glow-suppressed result is then brightened via a Retinex-based Enhancement Module (REM). Remarkably, the proposed glow suppression method is based on zero-shot learning and does not rely on any paired or unpaired training data. Empirical evaluations demonstrate the effectiveness of the proposed method in both glow suppression and low-light enhancement tasks.

Pre-training Vision Transformers with Very Limited Synthesized Images

Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks. These synthetic images are categorized according to the parameters in the mathematical formula that generate them. In the present work, we hypothesize that the process for generating different instances for the same category in FDSL, can be viewed as a form of data augmentation. We validate this hypothesis by replacing the instances with data augmentation, which means we only need a single image per category. Our experiments shows that this one-instance fractal database (OFDB) performs better than the original dataset where instances were explicitly generated. We further scale up OFDB to 21,000 categories and show that it matches, or even surpasses, the model pre-trained on ImageNet-21k in ImageNet-1k fine-tuning. The number of images in OFDB is 21k, whereas ImageNet-21k has 14M. This opens new possibilities for pre-training vision transformers with much smaller datasets.

MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis

Existing multimodal conditional image synthesis (MCIS) methods generate images conditioned on any combinations of various modalities that require all of them must be exactly conformed, hindering the synthesis controllability and leaving the potential of cross-modality under-exploited. To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i.e., composed multimodal conditional image synthesis (CMCIS). Specifically, we observe two challenging issues of the proposed CMCIS task, i.e., the modality coordination problem and the modality imbalance problem. To tackle these issues, we introduce a Mixture-of-Modality-Tokens Transformer (MMoT) that adaptively fuses fine-grained multimodal control signals, a multimodal balanced training loss to stabilize the optimization of each modality, and a multimodal sampling guidance to balance the strength of each modality control signal. Comprehensive experimental results demonstrate that MMoT achieves superior performance on both unimodal conditional image synthesis (UCIS) and MCIS tasks with high-quality and faithful image synthesis on complex multimodal conditions. The project website is available at https://jabir-zheng.github.io/MMoT.

A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models

Determining lymphoma subtypes is a crucial step for better patients treatment targeting to potentially increase their survival chances. In this context, the existing gold standard diagnosis method, which is based on gene expression technology, is highly expensive and time-consuming making difficult its accessibility. Although alternative diagnosis methods based on IHC (immunohistochemistry) technologies exist (recommended by the WHO), they still suffer from similar limitations and are less accurate. WSI (Whole Slide Image) analysis by deep learning models showed promising new directions for cancer diagnosis that would be cheaper and faster than existing alternative methods. In this work, we propose a vision transformer-based framework for distinguishing DLBCL (Diffuse Large B-Cell Lymphoma) cancer subtypes from high-resolution WSIs. To this end, we propose a multi-modal architecture to train a classifier model from various WSI modalities. We then exploit this model through a knowledge distillation mechanism for efficiently driving the learning of a mono-modal classifier. Our experimental study conducted on a dataset of 157 patients shows the promising performance of our mono-modal classification model, outperforming six recent methods from the state-of-the-art dedicated for cancer classification. Moreover, the power-law curve, estimated on our experimental data, shows that our classification model requires a reasonable number of additional patients for its training to potentially reach identical diagnosis accuracy as IHC technologies.

A Survey on Change Detection Techniques in Document Images

The problem of change detection in images finds application in different domains like diagnosis of diseases in the medical field, detecting growth patterns of cities through remote sensing, and finding changes in legal documents and contracts. However, this paper presents a survey on core techniques and rules to detect changes in different versions of a document image. Our discussions on change detection focus on two categories -- content-based and layout-based. The content-based techniques intelligently extract and analyze the image contents (text or non-text) to show the possible differences, whereas the layout-based techniques use structural information to predict document changes. We also summarize the existing datasets and evaluation metrics used in change detection experiments. The shortcomings and challenges the existing methods face are reported, along with some pointers for future research work.

Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes

3D human pose estimation in outdoor environments has garnered increasing attention recently. However, prevalent 3D human pose datasets pertaining to outdoor scenes lack diversity, as they predominantly utilize only one type of modality (RGB image or pointcloud), and often feature only one individual within each scene. This limited scope of dataset infrastructure considerably hinders the variability of available data. In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds. In order to obtain accurate human poses, we propose an algorithm based on multi-modal data input to generate ground truth annotation. This benefits from robust pointcloud detection and tracking, which solves the problem of inaccurate human localization and matching ambiguity that may exist in previous multi-view RGB videos in outdoor multi-person scenes, and generates reliable ground truth annotations. Evaluation of multiple different modalities algorithms has shown that this database is challenging and suitable for future research. Furthermore, we propose a 3D human pose estimation algorithm based on multi-modal data input, which demonstrates the advantages of multi-modal data input for 3D human pose estimation. Code and data will be released on https://github.com/soullessrobot/Human-M3-Dataset.

Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes

To gain a deeper understanding of the behavior and learning dynamics of (deep) artificial neural networks, it is valuable to employ mathematical abstractions and models. These tools provide a simplified perspective on network performance and facilitate systematic investigations through simulations. In this paper, we propose utilizing the framework of stochastic processes, which has been underutilized thus far. Our approach models activation patterns of thresholded nodes in (deep) artificial neural networks as stochastic processes. We focus solely on activation frequency, leveraging neuroscience techniques used for real neuron spike trains. During a classification task, we extract spiking activity and use an arrival process following the Poisson distribution. We examine observed data from various artificial neural networks in image recognition tasks, fitting the proposed model's assumptions. Through this, we derive parameters describing activation patterns in each network. Our analysis covers randomly initialized, generalizing, and memorizing networks, revealing consistent differences across architectures and training sets. Calculating Mean Firing Rate, Mean Fano Factor, and Variances, we find stable indicators of memorization during learning, providing valuable insights into network behavior. The proposed model shows promise in describing activation patterns and could serve as a general framework for future investigations. It has potential applications in theoretical simulations, pruning, and transfer learning.

NormKD: Normalized Logits for Knowledge Distillation

Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potential when we re-investigate the temperature, which is a crucial hyper-parameter to soften the logit outputs. For most of the previous works, it was set as a fixed value for the entire distillation procedure. However, as the logits from different samples are distributed quite variously, it is not feasible to soften all of them to an equal degree by just a single temperature, which may make the previous work transfer the knowledge of each sample inadequately. In this paper, we restudy the hyper-parameter temperature and figure out its incapability to distill the knowledge from each sample sufficiently when it is a single value. To address this issue, we propose Normalized Knowledge Distillation (NormKD), with the purpose of customizing the temperature for each sample according to the characteristic of the sample's logit distribution. Compared to the vanilla KD, NormKD barely has extra computation or storage cost but performs significantly better on CIRAR-100 and ImageNet for image classification. Furthermore, NormKD can be easily applied to the other logit based methods and achieve better performance which can be closer to or even better than the feature based method.