Related papers: Locality-Sensitive Hashing-Based Efficient Point T…

The recently introduced coder based on region-adaptive hierarchical transform (RAHT) for the compression of point clouds attributes, was shown to have a performance competitive with the state-of-the-art, while being much less complex. In…

Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical…

The increasing scale of deep learning models in high-energy physics (HEP) has posed challenges to their deployment on low-power, latency-sensitive platforms, such as FPGAs and ASICs used in trigger systems, as well as in offline data…

Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-world applications. This work proposes Transfer Entropy…

Graph-based transforms have been shown to be powerful tools in terms of image energy compaction. However, when the support increases to best capture signal dependencies, the computation of the basis functions becomes rapidly untractable.…

Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud…

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Point-based 3D point cloud models employ computation and memory intensive mapping functions alongside NN layers for classification/segmentation, and are executed on server-grade GPUs. The sparse, and unstructured nature of 3D point cloud…

Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transformer family of networks has shown a more powerful learning…

We investigate the training of sparse layers that use different parameters for different inputs based on hashing in large Transformer models. Specifically, we modify the feedforward layer to hash to different sets of weights depending on…

HEP-Frame is a new C++ package designed to efficiently perform analyses of data sets from a very large number of events, like those available at the Large Hadron Collider (LHC) at CERN, Geneva. It mainly targets high performance servers and…

Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great…

Currently, prominent Transformer architectures applied on graphs and meshes for shape analysis tasks employ traditional attention layers that heavily utilize spectral features requiring costly eigenvalue decomposition-based methods. To…

Spatial computing architectures promise a major stride in performance and energy efficiency over the traditional load/store devices currently employed in large scale computing systems. The adoption of high-level synthesis (HLS) from…

Exploiting fine-grained semantic features on point cloud is still challenging due to its irregular and sparse structure in a non-Euclidean space. Among existing studies, PointNet provides an efficient and promising approach to learn shape…

The Transformer architecture revolutionized the field of natural language processing (NLP). Transformers-based models (e.g., BERT) power many important Web services, such as search, translation, question-answering, etc. While enormous…

Tensor network methods provide a scalable solution to represent high-dimensional data. However, their efficacy is often limited by static, expert-defined structures that fail to adapt to evolving data correlations. We address this…

Machine-learning models in high-energy physics are often trained on simulated data, where fully simulated samples are computationally expensive while fast simulation provides large statistics at reduced realism. In this work, we…

Pansharpening is a crucial remote sensing technique that fuses low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) imagery. Although deep learning…

Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in…