No abstract

No abstract

Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored. In this paper, we propose a multiple expert brainstorming network (MEB-Net) for domain adaptive person re-ID, opening up a promising direction about model ensemble problem under unsupervised conditions. MEB-Net adopts a mutual learning strategy, where multiple networks with different architectures are pre-trained within a source domain as expert models equipped with specific features and knowledge, while the adaptation is then accomplished through brainstorming (mutual learning) among expert models. MEB-Net accommodates the heterogeneity of experts learned with different architectures and enhances discrimination capability of the adapted re-ID model, by introducing a regularization scheme about authority of experts. Extensive experiments on large-scale datasets (Market-1501 and DukeMTMC-reID) demonstrate the superior performance of MEB-Net over the state-of-the-arts. Code is available at https://github.com/YunpengZhai/MEB-Net.

Occluded person re-identification (re-ID) is a challenging task as different human parts may become invisible in cluttered scenes, making it hard to match person images of different identities. Most existing methods address this challenge by aligning spatial features of body parts according to semantic information (e.g. human poses) or feature similarities but this approach is complicated and sensitive to noises. This paper presents Matching on Sets (MoS), a novel method that positions occluded person re-ID as a set matching task without requiring spatial alignment. MoS encodes a person image by a pattern set as represented by a `global vector’ with each element capturing one specific visual pattern, and it introduces Jaccard distance as a metric to compute the distance between pattern sets and measure image similarity. To enable Jaccard distance over continuous real numbers, we employ minimization and maximization to approximate the operations of intersection and union, respectively. In addition, we design a Jaccard triplet loss that enhances the pattern discrimination and allows to embed set matching into deep neural networks for end-to-end training. In the inference stage, we introduce a conflict penalty mechanism that detects mutually exclusive patterns in the pattern union of image pairs and decreases their similarities accordingly. Extensive experiments over three widely used datasets (Market1501, DukeMTMC and Occluded-DukeMTMC) show that MoS achieves superior re-ID performance. Additionally, it is tolerant of occlusions and outperforms the state-of-the-art by large margins for Occluded-DukeMTMC.

RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities. Existing methods address this challenge typically by aligning feature distributions or image styles across modalities, whereas the very useful similarities among gallery samples of the same modality (i.e. intra-modality sample similarities) are largely neglected. This paper presents a novel similarity inference metric (SIM) that exploits the intra-modality sample similarities to circumvent the cross-modality discrepancy targeting optimal cross-modality image matching. SIM works by successive similarity graph reasoning and mutual nearest-neighbor reasoning that mine cross-modality sample similarities by leveraging intra-modality sample similarities from two different perspectives. Extensive experiments over two cross-modality re-ID datasets (SYSU-MM01 and RegDB) show that SIM achieves significant accuracy improvement but with little extra training as compared with the state-of-the-art.

No abstract

No abstract

ObjectiveThe present study aimed to evaluate the safety and feasibility of modified thoracoscopic wedge resection of limited peripheral lesions in the posterior basal segment (S10) in children with congenital pulmonary airway malformation (CPAM).Materials and methodsWe retrospectively analyzed the clinical data of children with CPAM who underwent thoracoscopic modified wedge resection at our institution from November 2020 to February 2022. The surgical method was as follows: we marked the external boundary of the lesion with an electric hook, dissected and retained the segmental vein between the lesion and normal lung tissue as the internal boundary, cut the arteries, veins, and bronchus entering the lesion, and cut and sealed the lung tissue between the internal and external boundaries with LigaSure™ to complete the modified wedge resection.ResultsA total of 16 patients were included, aged 3.8−70.0 months and weighing 6.5−21.0 kg. The intraoperative course was uneventful in all patients. The median operation time and intraoperative bleeding volume were 74 min (50−110 min) and 5 mL (5−15 mL), respectively. The median postoperative drainage tube indwelling time was 3 days (2−4 days), and the median postoperative hospital stay was 6 days (4−8 days). Pathological diagnosis included two cases of type 1, 10 cases of type 2, and four cases of type 3 CPAM. There were no cases of intraoperative conversion, surgical mortality, or major complications. However, subcutaneous emphysema occurred in two children, which spontaneously resolved without pneumothorax orbronchopleural fistula development. All patients were followed up for a median period of 10 months (3–18 months), and there were no cases of hemoptysis or residual lesions on chest computed tomography.ConclusionModified thoracoscopic wedge resection via the inferior pulmonary ligament approach is safe and feasible for children with CPAM with limited peripheral lesions in S10.