相关论文: Coordinate-Aware Modulation for Neural Fields

We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-frequency signals. Lack of…

The Class Activation Map (CAM) lookup of a neural network tells us to which regions the neural network focuses when it makes a decision. In the past, the CAM search method was dependent upon a specific internal module of the network. It has…

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel…

This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map…

This paper introduces CoFie, a novel local geometry-aware neural surface representation. CoFie is motivated by the theoretical analysis of local SDFs with quadratic approximation. We find that local shapes are highly compressive in an…

Implicit neural representations (INR) has found successful applications across diverse domains. To employ INR in real-life, it is important to speed up training. In the field of INR for video applications, the state-of-the-art approach…

Parametric feature grid encodings have gained significant attention as an encoding approach for neural fields since they allow for much smaller MLPs, which significantly decreases the inference time of the models. In this work, we propose…

Recently, the explanation of neural network models has garnered considerable research attention. In computer vision, CAM (Class Activation Map)-based methods and LRP (Layer-wise Relevance Propagation) method are two common explanation…

In this work, we investigate the structure and representation capacity of sinusoidal MLPs - multilayer perceptron networks that use sine as the activation function. These neural networks (known as neural fields) have become fundamental in…

We present a novel differentiable grid-based representation for efficiently solving differential equations (DEs). Widely used architectures for neural solvers, such as sinusoidal neural networks, are coordinate-based MLPs that are both…

In deep learning, Multi-Layer Perceptrons (MLPs) have once again garnered attention from researchers. This paper introduces MC-MLP, a general MLP-like backbone for computer vision that is composed of a series of fully-connected (FC) layers.…

Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or…

Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance…

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However,…

Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining camera intrinsic and extrinsic parameters is challenging,…

Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid…

There are many challenges in the classification of hyper spectral images such as large dimensionality, scarcity of labeled data and spatial variability of spectral signatures. In this proposed method, we make a hybrid classifier (MLP-SVM)…

Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches align the representation spaces of images and brain…

As deep learning continues to advance, the transparency of neural network decision-making remains a critical challenge, limiting trust and applicability in high-stakes domains. Class Activation Mapping (CAM) techniques have emerged as a key…

Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has…