Deep convolutional networks are prominently used in object detection tasks due to their notable performances. These typically have pooling layers following the convolution, which effectively subsamples convolution output, potentially introducing aliasing. An aliased signal emerging earlier inevitably propagates throughout network and such distortion prevents getting best performance out of a ne...

The application of RPCA model in moving object detection can accurately extract the foreground, but effect is not ideal under complex dynamic background conditions. Based on this, this paper proposes an improved based rank–1 regulation and 3D-TV. uses term to describe low rank video background, 3D-TV constrain spatiotemporal continuity objects, F-norm eliminate interference background. experime...

Mainstream object detectors are commonly constituted of two sub-tasks, including classification and regression tasks, implemented by parallel heads. This classic design paradigm inevitably leads to inconsistent spatial distributions between score localization quality (IOU). Therefore, this paper alleviates misalignment in the view knowledge distillation. First, we observe that massive teacher a...

• A matching imbalance in current object detection pipelines is pointed out. It can lead to poor performance of detecting objects with different scales. An innovative loss function called scale-balanced proposed alleviate the imbalance. Experiments demonstrate effectiveness loss, especially small improved significantly. Object an important field computer vision. Nevertheless, a research area th...

The existing fusion based RGB-D salient object detection methods usually adopt the bi-stream structure to strike trade-off between RGB and depth (D). D quality varies from scene scene, while SOTA approaches are unaware, which easily result in substantial difficulties achieving complementary status D, leading poor results facing of low-quality D. Thus, this paper attempts integrate a novel aware...

Deep learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by leveraging large amounts of data. However, they could fail when retrieved information is not enough fit vast number parameters, frequently resulting overfitting and therefore poor generalizability. Few-Shot Learning aims at designing models that can effectively operate a...