相关论文: Patch-aware Vector Quantized Codebook Learning for…

In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training…

Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE),…

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality,…

Vector Quantization (VQ) underpins many modern generative frameworks such as VQ-VAE, VQ-GAN, and latent diffusion models. Yet, it suffers from the persistent problem of codebook collapse, where a large fraction of code vectors remains…

Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper,…

Unsupervised transfer learning-based change detection methods exploit the feature extraction capability of pre-trained networks to distinguish changed pixels from the unchanged ones. However, their performance may vary significantly…

Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the…

Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available. Most state-of-the-art methods fall into two categories:…

We present a novel approach to enhance the capabilities of VQ-VAE models through the integration of a Residual Encoder and a Residual Pixel Attention layer, named Attentive Residual Encoder (AREN). The objective of our research is to…

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…

Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…

Vector Quantisation (VQ) is experiencing a comeback in machine learning, where it is increasingly used in representation learning. However, optimizing the codevectors in existing VQ-VAE is not entirely trivial. A problem is codebook…

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding…

In this paper, I present VQ-DRAW, an algorithm for learning compact discrete representations of data. VQ-DRAW leverages a vector quantization effect to adapt the sequential generation scheme of DRAW to discrete latent variables. I show that…

Visual anomaly detection targets to detect images that notably differ from normal pattern, and it has found extensive application in identifying defective parts within the manufacturing industry. These anomaly detection paradigms…

Reliable fault detection is an essential requirement for safe and efficient operation of complex mechanical systems in various industrial applications. Despite the abundance of existing approaches and the maturity of the fault detection…

Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated…

Automatic image anomaly detection is important for quality inspection in the manufacturing industry. The usual unsupervised anomaly detection approach is to train a model for each object class using a dataset of normal samples. However, a…

The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete…