Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally le...
详细信息
This paper proposes the use of an event camera as a component of a vision system that enables counting of fast-moving objects – in this case, falling corn grains. These type of cameras transmit information about the ...
详细信息
3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolu...
详细信息
Transformers have achieved remarkable success in several domains, ranging from natural language processing to computervision. Nevertheless, it has been recently shown that stacking self-attention layers — the distin...
ISBN:
(纸本)9781713871088
Transformers have achieved remarkable success in several domains, ranging from natural language processing to computervision. Nevertheless, it has been recently shown that stacking self-attention layers — the distinctive architectural component of Transformers — can result in rank collapse of the tokens' representations at initialization. The question of if and how rank collapse affects training is still largely unanswered, and its investigation is necessary for a more comprehensive understanding of this architecture. In this work, we shed new light on the causes and the effects of this phenomenon. First, we show that rank collapse of the tokens' representations hinders training by causing the gradients of the queries and keys to vanish at initialization. Furthermore, we provide a thorough description of the origin of rank collapse and discuss how to prevent it via an appropriate depth-dependent scaling of the residual branches. Finally, our analysis unveils that specific architectural hyperparameters affect the gradients of queries and values differently, leading to disproportionate gradient norms. This suggests an explanation for the widespread use of adaptive methods for Transformers' optimization.
This paper proposes the use of an event camera as a component of a vision system that enables counting of fast-moving objects – in this case, falling corn grains. These type of cameras transmit information about the ...
详细信息
3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolu...
详细信息
In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most ex...
详细信息
In recent years, event cameras (DVS – Dynamic vision Sensors) have been used in vision systems as an alternative or supplement to traditional cameras. They are characterised by high dynamic range, high temporal resol...
详细信息
In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for...
详细信息
In this paper we present a vision based hardware-software control system enabling the autonomous landing of a multirotor unmanned aerial vehicle (UAV). It allows for the detection of a marked landing pa...
详细信息
暂无评论