Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary

2021-07-21 · Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris

Generative models, such as Generative Adversarial Networks (GANs), have been used for unsupervised anomaly detection. While performance keeps improving, several limitations exist particularly attributed to difficulties at capturing multimodal supports and to the ability to approximate the underlying distribution closer to the tails, i.e. the boundary of the distribution's support. This paper proposes an approach that attempts to alleviate such shortcomings. We propose an invertible-residual-network-based model, the Boundary of Distribution Support Generator (BDSG). GANs generally do not guarantee the existence of a probability distribution and here, we use the recently developed Invertible Residual Network (IResNet) and Residual Flow (ResFlow), for density estimation. These models have not yet been used for anomaly detection. We leverage IResNet and ResFlow for Out-of-Distribution (OoD) sample detection and for sample generation on the boundary using a compound loss function that forces the samples to lie on the boundary. The BDSG addresses non-convex support, disjoint components, and multimodal distributions. Results on synthetic data and data from multimodal distributions, such as MNIST and CIFAR-10, demonstrate competitive performance compared to methods from the literature.

📄 PDF Abstract BibTeX arXiv:2107.09950

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection Density Estimation Unsupervised Anomaly Detection

Tail of Distribution GAN (TailGAN): Generative-Adversarial-Network-Based Boundary Formation

2021-07-24 · Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris

Generative Adversarial Networks (GAN) are a powerful methodology and can be used for unsupervised anomaly detection, where current techniques have limitations such as the accurate detection of anomalies near the tail of …

Anomaly Detection Generative Adversarial Network Unsupervised Anomaly Detection

LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection

2026-05-11 · Abhishek Moturu, Anna Goldenberg, Babak Taati arxiv

Synthetic data is useful only when the added samples fill missing parts of the training distribution that matter for the downstream task. We introduce LiBaGS, a lightweight, generator-agnostic method for targeted synthet…

GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection

2023-12-27 · Hefei Mei, Taijin Zhao, Shiyuan Tang, Heqian Qiu 외

Few-shot object detection (FSOD) aims to achieve object detection only using a few novel class training data. Most of the existing methods usually adopt a transfer-learning strategy to construct the novel class distribut…

Few-Shot Object Detection object-detection Object Detection Transfer Learning

NOVEL AND EFFECTIVE PARALLEL MIX-GENERATOR GENERATIVE ADVERSARIAL NETWORKS

2018-01-01 · ICLR 2018 1 · Xia Xiao, Sanguthevar Rajasekaran

In this paper, we propose a mix-generator generative adversarial networks (PGAN) model that works in parallel by mixing multiple disjoint generators to approximate a complex real distribution. In our model, we propose an…

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

2021-11-04 · NeurIPS 2021 12 · Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim 외

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original tra…

Data Free Quantization Disentanglement Diversity Quantization