arXiv subjects

Guojun Dai

Publications and source records attributed to Guojun Dai.

3 recordsLinked to original sources

arXiv2024

EEG-Driven 3D Object Reconstruction with Style Consistency and Diffusion Prior

Electroencephalography (EEG)-based visual perception reconstruction has become an important area of research. Neuroscientific studies indicate that humans can decode imagined 3D objects by perceiving or imagining various visual information, such as color, shape, and rotation. Existing EEG-based visual decoding methods typically focus only on the reconstruction of 2D visual stimulus images and face various challenges in generation quality, including inconsistencies in texture, shape, and color between the visual stimuli and the reconstructed images. This paper proposes an EEG-based 3D object reconstruction method with style consistency and diffusion priors. The method consists of an EEG-driven multi-task joint learning stage and an EEG-to-3D diffusion stage. The first stage uses a neural EEG encoder based on regional semantic learning, employing a multi-task joint learning scheme that includes a masked EEG signal recovery task and an EEG based visual classification task. The second stage introduces a latent diffusion model (LDM) fine-tuning strategy with style-conditioned constraints and a neural radiance field (NeRF) optimization strategy. This strategy explicitly embeds semantic- and location-aware latent EEG codes and combines them with visual stimulus maps to fine-tune the LDM. The fine-tuned LDM serves as a diffusion prior, which, combined with the style loss of visual stimuli, is used to optimize NeRF for generating 3D objects. Finally, through experimental validation, we demonstrate that this method can effectively use EEG data to reconstruct 3D objects with style consistency.

cs.CV↗

arXiv2019

HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization

Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing methods deal with such problem by either treating each candidate label equally or identifying the ground-truth label iteratively. In this paper, we propose a novel PLL approach called HERA, which simultaneously incorporates the HeterogEneous Loss and the SpaRse and Low-rAnk procedure to estimate the labeling confidence for each instance while training the model. Specifically, the heterogeneous loss integrates the strengths of both the pairwise ranking loss and the pointwise reconstruction loss to provide informative label ranking and reconstruction information for label identification, while the embedded sparse and low-rank scheme constrains the sparsity of ground-truth label matrix and the low rank of noise label matrix to explore the global label relevance among the whole training data for improving the learning model. Extensive experiments on both artificial and real-world data sets demonstrate that our method can achieve superior or comparable performance against the state-of-the-art methods.

cs.LG↗

arXiv2015

Quorum-based Localized Scheme for Duty Cycling in Asynchronous Sensor Networks

Many TDMA- and CSMA-based protocols try to obtain fair channel access and to increase channel utilization. It is still challenging and crucial in Wireless Sensor Networks (WSNs), especially when the time synchronization cannot be well guaranteed and consumes much extra energy. This paper presents a localized and ondemand scheme ADC to adaptively adjust duty cycle based on quorum systems. ADC takes advantages of TDMA and CSMA and guarantees that (1) each node can fairly access channel based on its demand, (2) channel utilization can be increased by reducing competition for channel access among neighboring nodes, (3) every node has at least one rendezvous active time slot with each of its neighboring nodes even under asynchronization. The latency bound of data aggregation is analyzed under ADC to show that ADC can bound the latency under both synchronization and asynchronization. We conduct extensive experiments in TinyOS on a real test-bed with TelosB nodes to evaluate the performance of ADC. Comparing with B-MAC, ADC substantially reduces the contention for channel access and energy consumption, and improves network throughput.

cs.NI↗