Search Results for author:
Found 14 papers, 5 papers with code
CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors
Prohibited item detection based on X-ray images is one of the most effective security inspection methods.
CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain.
Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
To address these challenges, we propose \textbf{TFPS}, a novel architecture that leverages pattern-specific experts for more accurate and adaptable time series forecasting.
DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model.
Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP
To address aforementioned challenges, in this paper, we introduce distillation-based open-vocabulary object detection (OVOD) task into X-ray security inspection domain by extending CLIP to learn visual representations in our specific X-ray domain, aiming to detect novel prohibited item categories beyond base categories on which the detector is trained.
Fine-Grained Domain Generalization with Feature Structuralization
Likewise, we propose a Feature Structuralized Domain Generalization (FSDG) model, wherein features experience structuralization into common, specific, and confounding segments, harmoniously aligned with their relevant semantic concepts, to elevate performance in FGDG.
MMCL: Boosting Deformable DETR-Based Detectors with Multi-Class Min-Margin Contrastive Learning for Superior Prohibited Item Detection
Prohibited Item detection in X-ray images is one of the most effective security inspection methods. However, differing from natural light images, the unique overlapping phenomena in X-ray images lead to the coupling of foreground and background features, thereby lowering the accuracy of general object detectors. Therefore, we propose a Multi-Class Min-Margin Contrastive Learning (MMCL) method that, by clarifying the category semantic information of content queries under the deformable DETR architecture, aids the model in extracting specific category foreground information from coupled features. Specifically, after grouping content queries by the number of categories, we employ the Multi-Class Inter-Class Exclusion (MIE) loss to push apart content queries from different groups.
Hierarchical Classification Auxiliary Network for Time Series Forecasting
In this work, we introduce a novel approach by tokenizing time series values to train forecasting models via cross-entropy loss, while considering the continuous nature of time series data.
AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection
Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an Anti-Overlapping DETR (AO-DETR) based on one of the state-of-the-art general object detectors, DINO.
Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion
Depth completion is a critical task for handling depth images with missing pixels, which can negatively impact further applications.
Prior Knowledge Guided Network for Video Anomaly Detection
Video Anomaly Detection (VAD) involves detecting anomalous events in videos, presenting a significant and intricate task within intelligent video surveillance.
AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completion
In the encoding stage, an Attention Guided Gated-Convolution (AG-GConv) module is proposed to realize the fusion of depth and color features at different scales, which can effectively reduce the negative impacts of invalid depth data on the reconstruction.
Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification
Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks.
Learning Deep Representations by Mutual Information for Person Re-identification
Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods.
