A Multi-Level Approach to Waste Object Segmentation.

We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation. The results of the above steps are further integrated into a densely connected conditional random field that learns to respect the appearance, depth, and spatial affinities with pixel-level accuracy. In addition, we create a new RGBD waste object segmentation dataset, MJU-Waste, that is made public to facilitate future research in this area. The efficacy of our method is validated on both MJU-Waste and the Trash Annotation in Context (TACO) dataset.

Custom-printed microfluidic chips using simultaneous ratiometric fluorescence with "Green" carbon dots for detection of multiple antibiotic residues in pork and water samples.

In the evolving field of food safety, rapid and precise detection of antibiotic residues is crucial. This study aimed to tackle this challenge by integrating advanced inkjet printing technology with sophisticated microfluidic paper-based analytical devices (µPADs). The µPAD design utilized "green" quantum dots synthesized via an eco-friendly hydrothermal method using green white mulberry leaves as the carbon source, serving as the key fluorescent detection material. The action mechanism involved a photoinduced electron transfer system using red carbon dots (CDs) as electron donors and blue CDs combined with two-dimensional layered molybdenum disulfide (MoS2) nanosheets as electron acceptors. This system could quickly detect antibiotics within 10 min in pork and water samples, demonstrating high sensitivity and recovery rates: 6.5 pmol/L at 99.75%-110% for sulfadimethoxine, 3.3 pmol/L at 99%-105% for sulfamethoxazole, and 8.5 pmol/L at 98.5%-105% for tetracycline. It achieved a relative standard deviation under 5%, ensuring reliability and reproducibility. The fabricated sensor offered a promising application for the rapid and efficient on-site detection of antibiotic residues in food.

StainGAN: Learning a structural preserving translation for white blood cell images.

Analysis of white blood cells in blood smear images plays a vital role in computer-aided diagnosis for the analysis and treatment of many diseases. However, different techniques for blood smear preparation result in images with large appearance variations, which limits the performance of large-scale machine learning algorithms. In this paper, we propose StainGAN, an image translation framework to transform the conventional Wright-stained white blood cell images into their rapidly-stained counterpart. Moreover, we designed a cluster-based learning strategy that does not require manual annotations and a multi-scale discriminator that incorporates a richer hierarchy of the spatial context to generate sharper images with better semantic consistency. Experimental results on multiple real-world datasets prove the effectiveness of our proposed framework. Moreover, we show that the transformed images from StainGAN can be used to boost the downstream segmentation performance under the label-limiting scenario.

Semi-Supervised Medical Image Segmentation with Co-Distribution Alignment.

Medical image segmentation has made significant progress when a large amount of labeled data are available. However, annotating medical image segmentation datasets is expensive due to the requirement of professional skills. Additionally, classes are often unevenly distributed in medical images, which severely affects the classification performance on minority classes. To address these problems, this paper proposes Co-Distribution Alignment (Co-DA) for semi-supervised medical image segmentation. Specifically, Co-DA aligns marginal predictions on unlabeled data to marginal predictions on labeled data in a class-wise manner with two differently initialized models before using the pseudo-labels generated by one model to supervise the other. Besides, we design an over-expectation cross-entropy loss for filtering the unlabeled pixels to reduce noise in their pseudo-labels. Quantitative and qualitative experiments on three public datasets demonstrate that the proposed approach outperforms existing state-of-the-art semi-supervised medical image segmentation methods on both the 2D CaDIS dataset and the 3D LGE-MRI and ACDC datasets, achieving an mIoU of 0.8515 with only 24% labeled data on CaDIS, and a Dice score of 0.8824 and 0.8773 with only 20% data on LGE-MRI and ACDC, respectively.