No abstract

No abstract

No abstract

No abstract

Learning to recognize novel visual categories from a few examples is a challenging task for machines in realworld applications. In contrast, humans have the ability to discriminate even similar objects with little supervision. This paper attempts to address the few-shot fine-grained recognition problem. We propose a feature fusion model to explore the largest discriminative features by focusing on key regions. The model utilizes focus-area location to discover the perceptually similar regions among objects. High-order integration is employed to capture the interaction information among intra-parts. We also design a Center Neighbor Loss to form robust embedding space distribution for generating discriminative features. Furthermore, we build a typical fine-grained and few-shot learning dataset miniPPlankton from the real-world application in the area of marine ecological environment. Extensive experiments are carried out to validate the performance of our model. First the model is evaluated with two challenging experiments based on the miniDogsNet and Caltech-UCSD public datasets. The results demonstrate that our model achieves competitive performance compared with state-of-the-art models. Then, we implement our model for the real-world phytoplankton recognition task. The experimental results show the superiority of the proposed model compared with others on the miniPPlankton dataset.

Polygalae Radix is an important medicinal plant that is widely used in most of Africa. 3,4,5-Trimethoxycinnamic acid (TMCA) is one of the constituents of Polygalae Radix. Until now, the mechanisms involved in the anti-seizure property of TMCA are still unclear. We examined the anti-seizure effect of TMCA. TMCA administered at doses of 5, 10 and 20 mg/kg and evaluated anti-seizure effects by maximal electroshock (MES) and pentylenetetrazol (PTZ) models in mice. TMCA administered at doses of 10 and 20 mg/kg significantly reduced the incidence of MES-induced tonic hindlimb extension (THE). TMCA significantly delayed the onset of myoclonic jerks (MJ), and decreased the seizure severity and mortality compared with the vehicle-treated animals in PTZ seizure model. TMCA 10 and 20 mg/kg treated groups also did not determined generalized clonic seizures (GCS). Pretreatment with a GABAA/benzodiazepine (BZ) receptor antagonist flumazenil blocked the anti-seizure effects of TMCA. These data support the further investigation of TMCA as a GABAA/BZ receptor agonist for anti-seizure therapy.

No abstract

Real-time semantic segmentation is in intense demand for the application of autonomous driving. Most of the semantic segmentation models tend to use large feature maps and complex structures to enhance the representation power for high accuracy. However, these inefficient designs increase the amount of computational costs, which hinders the model to be applied on autonomous driving. In this paper, we propose a lightweight realtime segmentation model, named Parallel Complement Network (PCNet), to address the challenging task with fewer parameters. A Parallel Complement layer is introduced to generate complementary features with a large receptive field. It provides the ability to overcome the problem of similar feature encoding among different classes, and further produces discriminative representations. With the inverted residual structure, we design a Parallel Complement block to construct the proposed PCNet. Extensive experiments are carried out on challenging road scene datasets, i.e., CityScapes and CamVid, to make comparison against several state-of-the-art real-time segmentation models. The results show that our model has promising performance. Specifically, PCNet* achieves 72.9% Mean IoU on CityScapes using only 1.5M parameters and reaches 79.1 FPS with 1024×2048 resolution images on GTX 2080Ti. Moreover, our proposed system achieves the best accuracy when being trained from scratch.