Continual learning (CL) desires that the neural network sequentially perform learning tasks from a dynamic data stream without forgetting learned knowledge. To overcome forgetting, a line of work relies on gradient projection to minimize the influence between gradients during optimization. This article focuses on a challenging problem concerning CL: When, how, and where to implement gradient projection to promote CL. Tackling this problem can be divided into two perspectives, namely the gradient direction ( when and how ) and the area of gradient conflict ( where ). First, we propose a plug-and-play method UniGrad to tackle the inconsistency of conflicting and nonconflicting gradients during optimization in CL. Second, we explore the interaction mechanism of gradient projection and loss landscape in CL, and further propose a pluggable method UniGrad-FS to improve the CL performance. In short, this work expects to overcome forgetting through an efficient gradient projection at the area where the gradient conflicts are less intense. In essence, the proposed method is a general and pluggable method that can be used in any gradient-based optimizer. For evaluation, we plug UniGrad and UniGrad-FS into two top-performing baselines (WA and MEMO). Our method shows clear improvements, i.e., boosting WA and MEMO by +2.09% and 1.72% in the 20-step of the CIFAR100 benchmark. In addition, we observe performance enhancement on all settings of CIFAR100 and Tiny-ImageNet datasets. Extensive experiments demonstrate the simplicity and effectiveness of the proposed method.

As a main approach towards touch-free human-computer interaction, hand gesture recognition (HGR) has long been a research focus for both academia and industry. Meanwhile, visible light communication (VLC) has become increasingly popular with VLC-ready commercial products (e.g., Philips lamps) available on the market. These facts provoke us to ask: can we leverage a VLC-ready lamp to realize integrated sensing and communication (ISAC) by conducting both HGR and VLC simultaneously? To this end, we propose ReflexGest as our answer to this question. ReflexGest is implemented upon a table lamp for the sake of practicality; this VLC-ready lamp is equipped with a ring-shaped light-emitting diode (LED) array and a photodiode (PD, for light intensity sensing) originally aiming for up/down-link VLCs. Demanding hand gestures to be performed between the lamp and a table surface, ReflexGest exploits the variation of the reflection and their unique correlation with the corresponding hand gestures to achieve HGR. In particular, ReflexGest first handles the limited sensing ability of the PD by enhancing the LED lamp and thus diversifying the light emission patterns. Moreover, ReflexGest combats the reflection interference from varying table surfaces via an adversarial learning technique to distill only the features relevant to hand gestures. Our extensive evaluations demonstrate that ReflexGest is able to deliver accurate HGR under realistic VLC traffic.

With the help of traffic lights and street cameras, optical camera communication (OCC) can be adopted in Internet of Vehicles (IoV) applications to realize communication between vehicles and roadside units. However, the encoded light emitted by these OCC transmitters (LED infrastructures on the roadside and/or LED-based headlamps embedded in cars) will generate stripe patterns in image frames captured by existing license-plate recognition systems, which seriously degrades the accuracy of the recognition. To this end, we propose and experimentally demonstrate a method that can reduce the interference of OCC stripes in the image frames captured by the license-plate recognition system. We introduce an innovative pipeline with an end-to-end image reconstruction module. This module learns the distribution of images without OCC stripes and provides high-quality license-plate images for recognition in OCC conditions. In order to solve the problem of insufficient data, we model the OCC strips as multiplicative noise and propose a method to synthesize a pairwise dataset under OCC using the existing license-plate dataset. Moreover, we also build a prototype to simulate real scenes of the OCC-based vehicle networks and collect data in such scenes. Overall, the proposed method can achieve a recognition performance of $81.58$% and $79.35$% on the synthesized dataset and that captured from real scenes, respectively, which is improved by about $31.18$% and $24.26$%, respectively, compared with the conventional method.