Lowering power consumption and increasing noise margin have become two central topics in every state of the art SRAM design. Due to parameter fluctuations in scaled technologies, stable operation is critical to obtain high yield low-voltage, low-power SRAM. Recent published works in literature have shown that the conventional 6T SRAM suffers a severe stability degradation due to access disturbances at low-power mode. Thus, several 8T and 10T cell designs have been reported, improving the cell stability. However, they either employ single-ended read port or require too large area. In this paper, we use a fully differential 8T SRAM that allows efficient bit-interleaving to achieve soft-error tolerance with conventional Error Correcting Code (ECC). It also consumes less power when compared to the conventional 6T design. A column-based dynamic supply voltage scheme is utilized to improve both the read noise margin and the write-ability. To verify the technique, a 128 64-bit of the proposed SRAM has been implemented in a standard 65 nm/1 V CMOS process. Simulation results reaffirmed that the proposed design has 2 higher noise margin and consumes 54% less power when compared to the conventional 6T design.Index Terms-Low power SRAM, low voltage SRAM, multiple port SRAM, static-noise-margin-free.

Object detection on very-high-resolution (VHR) remote sensing imagery has attracted a lot of attention in the field of image automatic interpretation. Region-based convolutional neural networks (CNNs) have been vastly promoted in this domain, which first generate candidate regions and then accurately classify and locate the objects existing in these regions. However, the overlarge images, the complex image backgrounds and the uneven size and quantity distribution of training samples make the detection tasks more challenging, especially for small and dense objects. To solve these problems, an effective region-based VHR remote sensing imagery object detection framework named Double Multi-scale Feature Pyramid Network (DM-FPN) was proposed in this paper, which utilizes inherent multi-scale pyramidal features and combines the strong-semantic, low-resolution features and the weak-semantic, high-resolution features simultaneously. DM-FPN consists of a multi-scale region proposal network and a multi-scale object detection network, these two modules share convolutional layers and can be trained end-to-end. We proposed several multi-scale training strategies to increase the diversity of training data and overcome the size restrictions of the input images. We also proposed multi-scale inference and adaptive categorical non-maximum suppression (ACNMS) strategies to promote detection performance, especially for small and dense objects. Extensive experiments and comprehensive evaluations on large-scale DOTA dataset demonstrate the effectiveness of the proposed framework, which achieves mean average precision (mAP) value of 0.7927 on validation dataset and the best mAP value of 0.793 on testing dataset.

Scene classification, aiming to identify the land-cover categories of remotely sensed image patches, is now a fundamental task in the remote sensing image analysis field. Deep-learning-model-based algorithms are widely applied in scene classification and achieve remarkable performance, but these high-level methods are computationally expensive and time-consuming. Consequently in this paper, we introduce a knowledge distillation framework, currently a mainstream model compression method, into remote sensing scene classification to improve the performance of smaller and shallower network models. Our knowledge distillation training method makes the high-temperature softmax output of a small and shallow student model match the large and deep teacher model. In our experiments, we evaluate knowledge distillation training method for remote sensing scene classification on four public datasets: AID dataset, UCMerced dataset, NWPU-RESISC dataset, and EuroSAT dataset. Results show that our proposed training method was effective and increased overall accuracy (3% in AID experiments, 5% in UCMerced experiments, 1% in NWPU-RESISC and EuroSAT experiments) for small and shallow models. We further explored the performance of the student model on small and unbalanced datasets. Our findings indicate that knowledge distillation can improve the performance of small network models on datasets with lower spatial resolution images, numerous categories, as well as fewer training samples.