arXiv subjects

Yabin Wang

Publications and source records attributed to Yabin Wang.

21 records · Page 2Linked to original sources

arXiv2022

A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials

There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem. We evaluate existing methods, including their adapted ones, on the proposed CDDB. Within the proposed benchmark, we explore some commonly known essentials of standard continual learning. Our study provides new insights on these essentials in the context of continual deepfake detection. The suggested CDDB is clearly more challenging than the existing benchmarks, which thus offers a suitable evaluation avenue to the future research. Both data and code are available at https://github.com/Coral79/CDDB.

cs.CV↗

arXiv2022

Search for sterile neutrinos by shower events at a future neutrino telescope

It is pointed out that searching for sterile neutrinos at high energy regions at a future IceCube-like facility has advantages compared with that of reactor or short baseline accelerator neutrino experiments, in which the size of the detector and energy resolution make it difficult to gain good sensitivity for a large mass-squared difference. In this study we show that it is possible to improve constraints on sterile neutrino mixing $θ_{14}$ for 1 eV$^2~\lesssim Δm_{41}^2\lesssim$ 100 eV$^2$ by looking for a dip in the shower events at an IceCube-like neutrino telescope whose volume is at least 10 times as large as that of IceCube and duration is 10 years. We also give an analytic expression for the oscillation probabilities in two cases where the condition of one mass scale dominance is satisfied.

hep-ph↗

arXiv2021

Object Counting: You Only Need to Look at One

This paper aims to tackle the challenging task of one-shot object counting. Given an image containing novel, previously unseen category objects, the goal of the task is to count all instances in the desired category with only one supporting bounding box example. To this end, we propose a counting model by which you only need to Look At One instance (LaoNet). First, a feature correlation module combines the Self-Attention and Correlative-Attention modules to learn both inner-relations and inter-relations. It enables the network to be robust to the inconsistency of rotations and sizes among different instances. Second, a Scale Aggregation mechanism is designed to help extract features with different scale information. Compared with existing few-shot counting methods, LaoNet achieves state-of-the-art results while learning with a high convergence speed. The code will be available soon.

cs.CV↗