Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 2
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

Acquiring labels in anomaly detection tasks is expensive and challenging. Therefore, as an effective way to improve efficiency, pretraining is widely used in anomaly detection models, which enriches the model's representation capabilities, thereby enhancing both performance and efficiency in anomaly detection. In most pretraining methods, the decoder is typically randomly initialized. Drawing inspiration from the diffusion model, this paper proposed to use denoising as a task to pretrain the decoder in anomaly detection, which is trained to reconstruct the original noise-free input. Denoising requires the model to learn the structure, patterns, and related features of the data, particularly when training samples are limited. This paper explored two approaches on anomaly detection: simultaneous denoising pretraining for encoder and decoder, denoising pretraining for only decoder. Experimental results demonstrate the effectiveness of this method on improving model’s performance. Particularly, when the number of samples is limited, the improvement is more pronounced.
Go to article

Authors and Affiliations

Xianlei Ge
1 2
ORCID: ORCID
Xiaoyan Li
3
ORCID: ORCID
Zhipeng Zhang
1

  1. School of Electronic Engineering, Huainan Normal University, China
  2. College of Computing and Information Technologies, National University, Philippines
  3. School of Computer, Huainan Normal University, China
Download PDF Download RIS Download Bibtex

Abstract

Forecasting future trajectories of intelligent agents presents a formidable challenge, necessitating the analysis of intricate scenarios and uncertainties arising from agent interactions. Consequently, it is judicious to contemplate the establishment of inter-agent relationships and the assimilation of contextual semantic information. In this manuscript, we introduce HTTNet, a comprehensive framework that spans three dimensions of information modeling: (1) the temporal dimension, where HTTNet employs a time encoder to articulate time sequences, comprehending the influences of past and future trajectories; (2) the social dimension, where the trajectory encoder facilitates the input of trajectories from multiple agents, thereby streamlining the modeling of interaction information among intelligent agents; (3) the contextual dimension, where the TF-map encoder integrates semantic scene input, amplifying HTTNet cognitive grasp of scene information. Furthermore, HTTNet integrates a hybrid modeling paradigm featuring CNN and transformer, transmuting map scenes into feature information for the transformer. Qualitative and quantitative analyses on the nuScenes and interaction datasets highlight the exceptional performance of HTTNet, achieving 1.03 minADE10 and a 0.31 miss rate on nuScenes, underscoring its effectiveness in multi-agent trajectory prediction in complex scenarios.
Go to article

Authors and Affiliations

Xianlei Ge
1 2
ORCID: ORCID
Xiaobo Sen
1 3
Xuanxin Zhou
1
ORCID: ORCID
Xiaoyan Li
4 2
ORCID: ORCID

  1. School of Electronic Engineering, Huainan Normal University, China
  2. College of Computing and Information Technologies, National University, Philippines
  3. College of Industrial Education, Technological University of the Philippines, Philippines
  4. School of Computer, Huainan Normal University, China

This page uses 'cookies'. Learn more