Search

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data. Nevertheless, most active learning methods are not inherently designed to handle domain gap between data distribution, on the other hand, some active domain adaptation methods (ADA) usually requires complicated query functions, which is vulnerable to overfitting. In this work, we propose a concise but effective ADA method called Select-by-Distinctive-Margin (SDM), which consists of a maximum margin loss and a margin sampling algorithm for data selection. We provide theoretical analysis to show that SDM works like a Support Vector Machine, storing hard examples around decision boundaries and exploiting them to find informative and transferable data. In addition, we propose two variants of our method, one is designed to adaptively adjust the gradient from margin loss, the other boosts the selectivity of margin sampling by taking the gradient direction into account. We benchmark SDM with standard active learning setting, demonstrating our algorithm achieves competitive results with good data scalability. Code is available at https://github.com/TencentYoutuResearch/ActiveLearning-SDM, Comment: To appear in CVPR 2022

Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes. In this paper, we raise the problem of weak connection between the training targets and the evaluation metrics caused by NMS and propose a novel NMS-Loss making the NMS procedure can be trained end-to-end without any additional network parameters. Our NMS-Loss punishes two cases when FP is not suppressed and FN is wrongly eliminated by NMS. Specifically, we propose a pull loss to pull predictions with the same target close to each other, and a push loss to push predictions with different targets away from each other. Experimental results show that with the help of NMS-Loss, our detector, namely NMS-Ped, achieves impressive results with Miss Rate of 5.92% on Caltech dataset and 10.08% on CityPersons dataset, which are both better than state-of-the-art competitors., Comment: ICMR2021 camera ready version

Constructing a hollow structured Ce-based catalyst is an effective way to result in an efficient catalytic system for the selective catalytic reduction of NOx using NH3 (NH3-SCR). A WO3@CeO2 catalyst with hollow structure was successfully developed using carbon sphere as hard template, and tested for the NH3-SCR of NOx reaction. The obtained WO3@CeO2 catalyst with hollow structure exhibit higher NOx conversion (88%) than traditional WO3-CeO2 catalyst (40%) at 200 °C, and superior SO2 and H2O tolerance at 300 °C, given its high specific surface area, reducible W species, increased specific amount of chemisorbed oxygen species and acid sites.

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (ie, without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission., CVPR 2021. Project page at https://fudan-zvg.github.io/SETR/

Xuefu Zhuyu Decoction (XFZYD), the classical recipe for promoting blood circulation by removing blood stasis, has been used in China for a long history clinically. XFZYD has been found to improve cardiac function through reducing inflammation. However, the effect of XFZYD on myocardial apoptosis remains unclear. Herein, we investigated the mechanism of XFZYD preconditioning on myocardial injury in sepsis rats. The rats were treated with XFZYD one week, followed with intraperitoneal injection of lipopolysaccharide (LPS: 10 mg/kg) to induce sepsis. Pretreatment with XFZYD could reverse the effects of LPS-induced decreased mean arterial pressure (MAP) and increased heart rate (HR). XFZYD decreased the levels of malondialdehyde (MDA), superoxide dismutase (SOD), tumor necrosis factor-α (TNF-α), interleukin-1β (IL-1β), and interleukin-6 (IL-6) in serum or in heart. TUNEL staining revealed that the apoptotic index of XFZYD was significantly lower compared with the LPS group (P