• 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...

Modern autonomous vehicles rely heavily on mechanical LiDARs for perception. Current perception methods generally require $360^\circ$ point clouds, collected sequentially as the LiDAR scans azimuth and acquires consecutive wedge-shaped ...

Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the network. Depth map approaches yield more accurate to objects than other methods thanks trained on large-scale dataset. However, can be limited by accuracy map, and sequentially using two separated networks for significantly increases computation cost inference time. In this w...

Modern object detectors are ill-equipped to incrementally learn new emerging classes over time due the well-known phenomenon of catastrophic forgetting. Due data privacy or limited storage, few no images old can be stored for replay. In this paper, we design a novel One-Shot Replay (OSR) method incremental detection, which is an augmentation-based method. Rather than storing original images, on...