相关论文: Mimetic Initialization of MLPs

Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately…

Neural reflectance models are capable of reproducing the spatially-varying appearance of many real-world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong…

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Implicit Neural Representations (INRs) have recently gained attention as a powerful approach for continuously representing signals such as images, videos, and 3D shapes using multilayer perceptrons (MLPs). However, MLPs are known to exhibit…

We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene. Recent approaches are computationally expensive, require per-scene optimization, or produce a memory-expensive…

Deep learning-based bilateral grid processing has emerged as a promising solution for image enhancement, inherently encoding spatial and intensity information while enabling efficient full-resolution processing through slicing operations.…

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Accurate prediction of surface energies and stabilities is essential for materials design, yet first-principles calculations remain computationally expensive and most existing interatomic potentials are trained only on bulk systems. Here,…

In this paper, we present an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method focuses on enhancing the efficiency and speed…

Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models directly, which…

Compared to convolutional layers, fully-connected (FC) layers are better at modeling the long-range dependencies but worse at capturing the local patterns, hence usually less favored for image recognition. In this paper, we propose a…

Feature-Imitating-Networks (FINs) are neural networks that are first trained to approximate closed-form statistical features (e.g. Entropy), and then embedded into other networks to enhance their performance. In this work, we perform the…

The development of machine learning models has led to an abundance of datasets containing quantum mechanical (QM) calculations for molecular and material systems. However, traditional training methods for machine learning models are unable…

Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is…

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…

Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training…

Combining information from different sources is a common way to improve classification accuracy in Brain-Computer Interfacing (BCI). For instance, in small sample settings it is useful to integrate data from other subjects or sessions in…

While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and…

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters…