Towards Robust Point Cloud Recognition With Sample-Adaptive Auto-Augmentation.

Robust 3D perception amidst corruption is a crucial task in the realm of 3D vision. Conventional data augmentation methods aimed at enhancing corruption robustness typically apply random transformations to all point cloud samples offline, neglecting sample structure, which often leads to over- or under-enhancement. In this study, we propose an alternative approach to address this issue by employing sample-adaptive transformations based on sample structure, through an auto-augmentation framework named AdaptPoint++.

Multi-angle and full-Stokes polarization multispectral images using quarter-wave plate and tunable filter.

Polarization multispectral imaging has advanced significantly due to its robust information representation capability. Imaging application requires rigorous simulation evaluation and experimental validation using standardized datasets. However, the current full-Stokes polarization multispectral images (FSPMI) dataset, while providing simulation data, is limited by image drift and spectral bands.

Miniature spectrometer based on graded bandgap perovskite filter.

Miniature spectrometer is powerful tool for scientific research and industrial inspection. Here, we report the fabrication of graded perovskite filters with tunable bandgap and their application in constructing miniature spectrometer. The graded perovskite filters were fabricated using a Finkelstein reaction between formed halogen ion with a preformed MAPbX film.

Opto-intelligence spectrometer using diffractive neural networks.

Spectral reconstruction, critical for understanding sample composition, is extensively applied in fields like remote sensing, geology, and medical imaging. However, existing spectral reconstruction methods require bulky equipment or complex electronic reconstruction algorithms, which limit the system's performance and applications. This paper presents a novel flexible all-optical opto-intelligence spectrometer, termed OIS, using a diffractive neural network for high-precision spectral reconstruction, featuring low energy consumption and light-speed processing.

Transformed pupil-function misalignment calibration strategy for Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) is an enabling quantitative phase imaging technique with both high-resolution (HR) and wide field-of-view (FOV), which can surpass the diffraction limit of the objective lens by employing an LED array to provide angular-varying illumination. The precise illumination angles are critical to ensure exact reconstruction, while it's difficult to separate actual positional parameters in conventional algorithmic self-calibration approaches due to the mixing of multiple systematic error sources. In this paper, we report a pupil-function-based strategy for independently calibrating the position of LED array.

Factorization Vision Transformer: Modeling Long-Range Dependency With Local Window Cost.

Transformers have astounding representational power but typically consume considerable computation which is quadratic with image resolution. The prevailing Swin transformer reduces computational costs through a local window strategy. However, this strategy inevitably causes two drawbacks: 1) the local window-based self-attention (WSA) hinders global dependency modeling capability and 2) recent studies point out that local windows impair robustness.

MsSVT++: Mixed-Scale Sparse Voxel Transformer With Center Voting for 3D Object Detection.

Accurate 3D object detection in large-scale outdoor scenes, characterized by considerable variations in object scales, necessitates features rich in both long-range and fine-grained information. While recent detectors have utilized window-based transformers to model long-range dependencies, they tend to overlook fine-grained details. To bridge this gap, we propose MsSVT++, an innovative Mixed-scale Sparse Voxel Transformer that simultaneously captures both types of information through a divide-and-conquer approach.

Anti-UAV410: A Thermal Infrared Benchmark and Customized Scheme for Tracking Drones in the Wild.

The perception of drones, also known as Unmanned Aerial Vehicles (UAVs), particularly in infrared videos, is crucial for effective anti-UAV tasks. However, existing datasets for UAV tracking have limitations in terms of target size and attribute distribution characteristics, which do not fully represent complex realistic scenes. To address this issue, we introduce a generalized infrared UAV tracking benchmark called Anti-UAV410.

Expert-Guided Knowledge Distillation for Semi-Supervised Vessel Segmentation.

In medical image analysis, blood vessel segmentation is of considerable clinical value for diagnosis and surgery. The predicaments of complex vascular structures obstruct the development of the field. Despite many algorithms have emerged to get off the tight corners, they rely excessively on careful annotations for tubular vessel extraction.

Dynamic Loss for Robust Learning.

Label noise and class imbalance are common challenges encountered in real-world datasets. Existing approaches for robust learning often focus on addressing either label noise or class imbalance individually, resulting in suboptimal performance when both biases are present. To bridge this gap, this work introduces a novel meta-learning-based dynamic loss that adapts the objective functions during the training process to effectively learn a classifier from long-tailed noisy data.

Full-Stokes polarization multispectral images of various stereoscopic objects.

Polarization multispectral imaging (PMI) has been applied widely with the ability of characterizing physicochemical properties of objects. However, traditional PMI relies on scanning each domain, which is time-consuming and occupies vast storage resources. Therefore, it is imperative to develop advanced PMI methods to facilitate real-time and cost-effective applications.

MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation.

Noisy labels, inevitably existing in pseudo-segmentation labels generated from weak object-level annotations, severely hamper model optimization for semantic segmentation. Previous works often rely on massive handcrafted losses and carefully tuned hyperparameters to resist noise, suffering poor generalization capability and high model complexity. Inspired by recent advances in meta-learning, we argue that rather than struggling to tolerate noise hidden behind clean labels passively, a more feasible solution would be to find out the noisy regions actively, so as to simply ignore them during model optimization.

Deep Learning in Medical Hyperspectral Images: A Review.

With the continuous progress of development, deep learning has made good progress in the analysis and recognition of images, which has also triggered some researchers to explore the area of combining deep learning with hyperspectral medical images and achieve some progress. This paper introduces the principles and techniques of hyperspectral imaging systems, summarizes the common medical hyperspectral imaging systems, and summarizes the progress of some emerging spectral imaging systems through analyzing the literature. In particular, this article introduces the more frequently used medical hyperspectral images and the pre-processing techniques of the spectra, and in other sections, it discusses the main developments of medical hyperspectral combined with deep learning for disease diagnosis.

Comparative Analysis on the Effect of Surface Reflectance for Laser 3D Scanner Calibrator.

The calibrator is one of the most important factors in the calibration of various laser 3D scanning instruments. The requirements for the diffuse reflection surface are emphasized in many national standards. In this study, spherical calibrator and plane calibrator comparative measurement experiments were carried out.

Polarimetry-inspired feature fusion spectroscopy (PIFFS) for ammonia sensing in water.

The sustainable use of water resources is inseparable from water pollution detection. The sensing of toxic ammonia nitrogen in water currently requires auxiliary reagents, which may cause secondary pollution. Benefiting from the ability of substances to change light characteristics, this work proposes polarimetry-inspired feature fusion spectroscopy (PIFFS) to detect ammonia.

Integration of Fourier ptychography with machine learning: an alternative scheme.

As the core task of the reconstruction in conventional ptychography (CP) and Fourier ptychographic microscopy (FPM), the meticulous design of ptychographical iterative engine (PIE) largely affects the performance of reconstruction algorithms. Compared to traditional PIE algorithms, the paradigm of combining with machine learning to cross a local optimum has recently achieved significant progress. Nevertheless, existing designed engines still suffer drawbacks such as excessive hyper-parameters, heavy tuning work and lack of compatibility, which greatly limit their practical applications.

SCANet: A Unified Semi-Supervised Learning Framework for Vessel Segmentation.

Automatic subcutaneous vessel imaging with near-infrared (NIR) optical apparatus can promote the accuracy of locating blood vessels, thus significantly contributing to clinical venipuncture research. Though deep learning models have achieved remarkable success in medical image segmentation, they still struggle in the subfield of subcutaneous vessel segmentation due to the scarcity and low-quality of annotated data. To relieve it, this work presents a novel semi-supervised learning framework, SCANet, that achieves accurate vessel segmentation through an alternate training strategy.

Research on Small Sample Dynamic Human Ear Recognition Based on Deep Learning.

Due to the problem of insufficient dynamic human ear data, the Changchun University dynamic human ear (CCU-DE) database, which is a small sample human ear database, was developed in this study. The database fully considers the various complex situations and posture changes of human ear images, such as translation angle, rotation angle, illumination change, occlusion and interference, etc., making the research of dynamic human ear recognition closer to complex real-life situations, and increasing the applicability of human ear dynamic recognition.

Multiscale Joint Optimization Strategy for Retinal Vascular Segmentation.

The accurate segmentation of retinal vascular is of great significance for the diagnosis of diseases such as diabetes, hypertension, microaneurysms and arteriosclerosis. In order to segment more deep and small blood vessels and provide more information to doctors, a multi-scale joint optimization strategy for retinal vascular segmentation is presented in this paper. Firstly, the Multi-Scale Retinex (MSR) algorithm is used to improve the uneven illumination of fundus images.

Deep Multi-Feature Transfer Network for Fourier Ptychographic Microscopy Imaging Reconstruction.

Fourier ptychographic microscopy (FPM) is a potential imaging technique, which is used to achieve wide field-of-view (FOV), high-resolution and quantitative phase information. The LED array is used to irradiate the samples from different angles to obtain the corresponding low-resolution intensity images. However, the performance of reconstruction still suffers from noise and image data redundancy, which needs to be considered.

RTNet: Relation Transformer Network for Diabetic Retinopathy Multi-Lesion Segmentation.

Automatic diabetic retinopathy (DR) lesions segmentation makes great sense of assisting ophthalmologists in diagnosis. Although many researches have been conducted on this task, most prior works paid too much attention to the designs of networks instead of considering the pathological association for lesions. Through investigating the pathogenic causes of DR lesions in advance, we found that certain lesions are closed to specific vessels and present relative patterns to each other.

Learning Context Restrained Correlation Tracking Filters via Adversarial Negative Instance Generation.

The tracking performance of discriminative correlation filters (DCFs) is often subject to unwanted boundary effects. Many attempts have already been made to address the above issue by enlarging searching regions over the last years. However, introducing excessive background information makes the discriminative filter prone to learn from the surrounding context rather than the target.

Combining Regional Energy and Intuitionistic Fuzzy Sets for Infrared and Visible Image Fusion.

To get more obvious target information and more texture features, a new fusion method for the infrared (IR) and visible (VIS) images combining regional energy (RE) and intuitionistic fuzzy sets (IFS) is proposed, and this method can be described by several steps as follows. Firstly, the IR and VIS images are decomposed into low- and high-frequency sub-bands by non-subsampled shearlet transform (NSST). Secondly, RE-based fusion rule is used to obtain the low-frequency pre-fusion image, which allows the important target information preserved in the resulting image.

Physics-based learning with channel attention for Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) is a computational imaging technology for large field-of-view, high resolution and quantitative phase imaging. In FPM, low-resolution intensity images captured with angle-varying illumination are synthesized in Fourier space with phase retrieval approaches. However, system errors such as pupil aberration and light-emitting diode (LED) intensity error seriously affect the reconstruction performance.