Taijin Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Taijin Zhao has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
- Heqian Qiu
University of Electronic Science and Technology of China
7 shared publications - Hongliang Li
University of Electronic Science and Technology of China
6 shared publications - Fanman Meng
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Lanxiao Wang
University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Qingbo Wu
University of Electronic Science and Technology of China
3 shared publications - Yu Dai
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications
Latest Publications
- 18 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (6) , 1382-1397
Continual Egocentric Activity Recognition by Multi-level Multimodal Feature Calibration and Temporal Aggregation
- 18 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (6) , 1382-1397
Continual Egocentric Activity Recognition by Multi-level Multimodal Feature Calibration and Temporal Aggregation
- Open Access
Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness recognition and foreground classification within shared feature spaces. This paradigm inherently establishes class-specific objectness criteria and suffers from unrepresentative novel class samples. To resolve this limitation, we propose a Uniform Orthogonal Feature Space (UOFS) optimization framework. First, UOFS decouples the feature space into two orthogonal components, where magnitude encodes objectness and angle encodes classification. This decoupling enables transferring class-agnostic objectness knowledge from base classes to novel classes. Moreover, implementing the disentanglement requires careful attention to two challenges: (1) Base set images contain unlabeled foreground instances, causing confusion between potential novel class instances and backgrounds. (2) Angular optimization depends exclusively on base class foreground instances, inducing overfitting of angular distributions to base classes. To address these challenges, we propose a Hybrid Background Optimization (HBO) strategy: (1) Constructing a pure background base set by removing unlabeled instances in original images to provide unbiased magnitude-based objectness supervision. (2) Incorporating unlabeled foreground instances in the original base set into angular optimization to enhance distribution uniformity. Additionally, we propose a Spatial-wise Attention Disentanglement and Association (SADA) module to address task conflicts between class-agnostic and class-specific tasks. Experiments demonstrate that our method significantly outperforms existing approaches based on entangled feature spaces.
Open AccessAttention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness recognition and foreground classification within shared feature spaces. This paradigm inherently establishes class-specific objectness criteria and suffers from unrepresentative novel class samples. To resolve this limitation, we propose a Uniform Orthogonal Feature Space (UOFS) optimization framework. First, UOFS decouples the feature space into two orthogonal components, where magnitude encodes objectness and angle encodes classification. This decoupling enables transferring class-agnostic objectness knowledge from base classes to novel classes. Moreover, implementing the disentanglement requires careful attention to two challenges: (1) Base set images contain unlabeled foreground instances, causing confusion between potential novel class instances and backgrounds. (2) Angular optimization depends exclusively on base class foreground instances, inducing overfitting of angular distributions to base classes. To address these challenges, we propose a Hybrid Background Optimization (HBO) strategy: (1) Constructing a pure background base set by removing unlabeled instances in original images to provide unbiased magnitude-based objectness supervision. (2) Incorporating unlabeled foreground instances in the original base set into angular optimization to enhance distribution uniformity. Additionally, we propose a Spatial-wise Attention Disentanglement and Association (SADA) module to address task conflicts between class-agnostic and class-specific tasks. Experiments demonstrate that our method significantly outperforms existing approaches based on entangled feature spaces.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer
Considering the arbitrary orientation of remote sensing objects, accurate angle prediction plays a crucial role in achieving precise oriented object detection (OOD) of aerial scenes. Existing transformer-based methods typically adopt an iterative refinement mechanism to update the angle prediction and perform bipartite graph matching based on the combined matching costs. However, these methods may suffer from the angle error accumulation across decoder layers and inconsistency between the L1 cost and the rotated IoU cost, thus resulting in inaccurate angle prediction. To address these problems, this paper proposes a novel transformer-based OOD method named Oriented-DINO, which comprises three important components: Error-mitigating Angle Decoupling Prediction (EADP) module, Nonlinear Angle-conversion Consistency Optimizer (NACO), and Query-driven Diversity (QD) loss. To mitigate the angle error, the EADP module decouples the angle prediction from the iterative box refinement process and employs independent branches to directly predict the angle. To address the issue of inconsistent matching, the NACO module employs a nonlinear function for angle conversion in matching cost calculation. This approach effectively alleviates the matching cost discrepancy in angle boundary case, while preserving the consistency in other instances. To avoid highly overlapped predictions triggered by similar queries, we introduce the QD loss to encourage the generation of diverse object queries, thus avoiding redundant predictions and enhancing prediction accuracy. Extensive experimental results demonstrate that our method achieves superior performance on OOD task.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer
Considering the arbitrary orientation of remote sensing objects, accurate angle prediction plays a crucial role in achieving precise oriented object detection (OOD) of aerial scenes. Existing transformer-based methods typically adopt an iterative refinement mechanism to update the angle prediction and perform bipartite graph matching based on the combined matching costs. However, these methods may suffer from the angle error accumulation across decoder layers and inconsistency between the L1 cost and the rotated IoU cost, thus resulting in inaccurate angle prediction. To address these problems, this paper proposes a novel transformer-based OOD method named Oriented-DINO, which comprises three important components: Error-mitigating Angle Decoupling Prediction (EADP) module, Nonlinear Angle-conversion Consistency Optimizer (NACO), and Query-driven Diversity (QD) loss. To mitigate the angle error, the EADP module decouples the angle prediction from the iterative box refinement process and employs independent branches to directly predict the angle. To address the issue of inconsistent matching, the NACO module employs a nonlinear function for angle conversion in matching cost calculation. This approach effectively alleviates the matching cost discrepancy in angle boundary case, while preserving the consistency in other instances. To avoid highly overlapped predictions triggered by similar queries, we introduce the QD loss to encourage the generation of diverse object queries, thus avoiding redundant predictions and enhancing prediction accuracy. Extensive experimental results demonstrate that our method achieves superior performance on OOD task.
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
VLM-guided Explicit-Implicit Complementary novel class semantic learning for few-shot object detection
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
VLM-guided Explicit-Implicit Complementary novel class semantic learning for few-shot object detection
- 27 November 2023
- Published by Springer Nature
- p. 400-412
Novel-Registrable Weights and Region-Level Contrastive Learning for Incremental Few-shot Object Detection
- 27 November 2023
- Published by Springer Nature
- p. 400-412
Novel-Registrable Weights and Region-Level Contrastive Learning for Incremental Few-shot Object Detection
- 1 January 2020
- Published by Springer Nature
- p. 692-712
VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results
- 1 January 2020
- Published by Springer Nature
- p. 692-712
VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results