Related papers: Intensity-only Mode Decomposition on Multimode Fib…
Space-division multiplexing (SDM) is one of the key enabling technologies to increase the capacity of fiber communication systems. However, implementing SDM-based systems using multimode fiber has been challenging with the need for compact,…
Decomposition is a proven way to shrink deep networks without changing input-output dimensionality or interface semantics. We bring this idea to hyperdimensional computing (HDC), where footprint cuts usually shrink the feature axis and…
One-dimensional signal decomposition is a well-established and widely used technique across various scientific fields. It serves as a highly valuable pre-processing step for data analysis. While traditional decomposition techniques often…
Significant effort in optical-fiber research has been put in recent years into realizing mode-division multiplexing (MDM) in conjunction with wavelength-division multiplexing (WDM) to enable further scaling of the communication bandwidth…
After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…
We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be…
Fiber imaging bundles are widely used as thin, passive image conduits for miniaturised and endoscopic microscopy, particularly for confocal fluorescence imaging. Holographic microscopy through fiber bundles is more challenging; phase…
Light transport in a highly multimode fiber exhibits complex behavior in space, time, frequency and polarization, especially in the presence of mode coupling. The newly developed techniques of spatial wavefront shaping turn out to be highly…
We report on a method to obtain confocal imaging through multimode fibers using optical correlation. First, we measure the fiber's transmission matrix in a calibration step. This allows us to create focused spots at one end of the fiber by…
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on designing a connectivity structure for the decoder. To achieve…
Bi-temporal change detection is highly sensitive to acquisition discrepancies, including illumination, season, and atmosphere, which often cause false alarms. We observe that genuine changes exhibit higher patch-wise singular-value entropy…
The integration density of photonic integrated circuits has been limited by light coupling between waveguides. Traditional approaches to layout the waveguide with high density are based on refractive index engineering to suppress the light…
Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as…
The popularity and diffusion of wearable devices provides new opportunities for sensor-based human activity recognition that leverages deep learning-based algorithms. Although impressive advances have been made, two major challenges remain.…
Coherent beam combination of multiple fibres can be used to overcome limitations such as the power handling capability of single fibre configurations. In such a scheme, the focal intensity profile is critically dependent upon the relative…
The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks…
Molecular communication is a novel approach for data transmission between miniaturized devices, especially in contexts where electrical signals are to be avoided. The communication is based on sending molecules (or other particles) at nano…
Controlling a complex network is of great importance in many applications. The network can be controlled by inputting external control signals through some selected nodes, which are called input nodes. Previous works found that the majority…
Most approaches for video frame interpolation require accurate dense correspondences to synthesize an in-between frame. Therefore, they do not perform well in challenging scenarios with e.g. lighting changes or motion blur. Recent deep…
We propose a deep-learning approach for the joint MIMO detection and channel decoding problem. Conventional MIMO receivers adopt a model-based approach for MIMO detection and channel decoding in linear or iterative manners. However, due to…