Paper Reading AI Learner

Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation

2024-05-20 03:31:43
Runou Yang, Tian Tian, Jinwen Tian


Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant accuracy improvements. However, existing methods often overlook class differences, treating all classes equally, resulting in suboptimal results. Furthermore, the integration of instance-level alignment with a one-stage detector, essential due to the absence of a Region Proposal Network (RPN), remains unexplored in this framework. In response to these shortcomings, we introduce a novel teacher-student model named Versatile Teacher (VT). VT differs from previous works by considering class-specific detection difficulty and employing a two-step pseudo-label selection mechanism, referred to as Class-aware Pseudo-label Adaptive Selection (CAPS), to generate more reliable pseudo labels. These labels are leveraged as saliency matrices to guide the discriminator for targeted instance-level alignment. Our method demonstrates promising results on three benchmark datasets, and extends the alignment methods for widely-used one-stage detectors, presenting significant potential for practical applications. Code is available at this https URL.

Abstract (translated)

在保持模型性能的同时解决数据集之间的领域转换挑战是非常重要的。在跨领域目标检测的背景下,教师-学生框架,一种广泛使用的半监督模型,已经显示出显著的准确性提高。然而,现有的方法通常忽视了类之间的差异,将所有类别都平等对待,导致 suboptimal 的结果。此外,在這個框架中,将实例级对齐与一阶段检测器的集成(由于缺少区域提议网络(RPN))仍然是未探索的。为了应对这些不足,我们引入了一个名为 Versatile Teacher(VT)的新教师-学生模型。VT 与以前的工作不同,考虑了类别特定的检测难度,并采用了一种称为类感知伪标签选择机制(CAPS)来生成更可靠的伪标签。这些标签被用作引导分类器的针对性实例级别对齐的 saliency 矩阵。我们的方法在三个基准数据集上的表现表明,它为广泛使用的一阶段检测器的对齐方法扩展了可能性,具有显著的实用性。代码可以从這個網址获取:



3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot