Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.

Skin biopsy histopathological analysis is one of the primary methods used for pathologists to assess the presence and deterioration of melanoma in clinical. A comprehensive and reliable pathological analysis is the result of correctly segmented melanoma and its interaction with benign tissues, and therefore providing accurate therapy. In this study, we applied the deep convolution network on the hyperspectral pathology images to perform the segmentation of melanoma. To make the best use of spectral properties of three dimensional hyperspectral data, we proposed a 3D fully convolutional network named Hyper-net to segment melanoma from hyperspectral pathology images. In order to enhance the sensitivity of the model, we made a specific modification to the loss function with caution of false negative in diagnosis. The performance of Hyper-net surpassed the 2D model with the accuracy over 92%. The false negative rate decreased by nearly 66% using Hyper-net with the modified loss function. These findings demonstrated the ability of the Hyper-net for assisting pathologists in diagnosis of melanoma based on hyperspectral pathology images.

As being radiation-free, portable, and capable of repetitive use, ultrasonography is playing an important role in diagnosing and evaluating the COVID-19 Pneumonia (PN) in this epidemic. By virtue of lung ultrasound scores (LUSS), lung ultrasound (LUS) was used to estimate the excessive lung fluid that is an important clinical manifestation of COVID-19 PN, with high sensitivity and specificity. However, as a qualitative method, LUSS suffered from large interobserver variations and requirement for experienced clinicians. Considering this limitation, we developed a quantitative and automatic lung ultrasound scoring system for evaluating the COVID-19 PN. A total of 1527 ultrasound images prospectively collected from 31 COVID-19 PN patients with different clinical conditions were evaluated and scored with LUSS by experienced clinicians. All images were processed via a series of computer-aided analysis, including curve-to-linear conversion, pleural line detection, region-of-interest (ROI) selection, and feature extraction. A collection of 28 features extracted from the ROI was specifically defined for mimicking the LUSS. Multilayer fully connected neural networks, support vector machines, and decision trees were developed for scoring LUS images using the fivefold cross validation. The model with $128\times256$ two fully connected layers gave the best accuracy of 87%. It is concluded that the proposed method could assess the ultrasound images by assigning LUSS automatically with high accuracy, potentially applicable to the clinics.

This paper presents a novel star pattern recognition algorithm based on a discrete hidden Markov model (HMM) for autonomous spacecraft attitude determination in the lost-in-space mode. A two-layer structure is proposed to build an HMM-based star pattern for every guide star. The hidden layer describes the unique geometric distributions of stars in the field of view via the transitions among hidden states, and the observation layer uses discrete and rounded feature sequences consisting of the angular distances of star pairs as outputs. An HMM-based star pattern with maximum probabilities in generating the sequences obtained in the recognition process is uniquely matched. Experiments of synthesized and real star images are tested for the HMM algorithm. Results show that the proposed algorithm has a fast average identification time and is highly robust toward star positions, magnitude noise, and false stars. In the simulation, the HMM algorithm exhibits 99.65% identification rate with 0.4 pixel standard deviations of positional noises, 0.323-Mv magnitude noises, and 1.5-ms average identification time. Moreover, the identification rate is 99.11% and the average identification time is 1.2 ms when testing real star images.

Existing unsupervised person re-identification (Re-ID) methods have achieved remarkable performance by adopting an alternate clustering-training manner. However, they still suffer from camera variation, which results in an inconsistent feature space and unreliable pseudo labels that severely degrade the performance. In this paper, we propose a cross-camera self-distillation (CCSD) framework for unsupervised person Re-ID to alleviate the effect of camera variation. Specifically, in the clustering phase, we propose a camera-aware cluster refinement mechanism, which first splits each cluster into multiple clusters according to the camera views, and then refines them into more compact clusters. In the training phase, we first obtain the similarity between the samples and the refined clusters from the same and different cameras, and then transfer the knowledge of similarity distribution from intra-camera to cross-camera. Since the intra-camera similarity is free from camera variation, our knowledge distillation approach is able to learn a more consistent feature space across cameras. Extensive experiments demonstrate the superiority of our proposed CCSD against the state-of-the-art approaches on unsupervised person Re-ID.