Paper Reading AI Learner

Match me if you can: Semantic Correspondence Learning with Unpaired Images

2023-11-30 13:22:15
Jiwon Kim, Byeongho Heo, Sangdoo Yun, Seungryong Kim, Dongyoon Han

Abstract

Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points. Despite their performance improvements, they remain constrained by the limited training pairs due to costly point-level annotations. This paper proposes a simple yet effective method that performs training with unlabeled pairs to complement both limited image pairs and sparse point pairs, requiring neither extra labeled keypoints nor trainable modules. We fundamentally extend the data quantity and variety by augmenting new unannotated pairs not primitively provided as training pairs in benchmarks. Using a simple teacher-student framework, we offer reliable pseudo correspondences to the student network via machine supervision. Finally, the performance of our network is steadily improved by the proposed iterative training, putting back the student as a teacher to generate refined labels and train a new student repeatedly. Our models outperform the milestone baselines, including state-of-the-art methods on semantic correspondence benchmarks.

Abstract (translated)

近年来,针对语义匹配的方法主要关注使用复杂网络获取高质量匹配,并通过精炼模糊或嘈杂的匹配点来优化。尽管它们的性能有所提高,但它们仍然受到由于昂贵点级注释而有限训练对对的限制。本文提出了一种简单而有效的方法,通过未标记的对进行训练来补充有限图像对和稀疏点对,无需额外的标记关键点或可训练模块。我们通过扩展基准中未提供作为训练对的数据量和多样性来扩展数据量。通过简单的老师和学生框架,我们通过机器监督向学生网络提供可靠的伪对应。最后,通过提出的迭代训练,我们的网络性能得到了持续的提高,让学生重新成为老师,生成更精确的标签,并重复训练一个新的学生。我们的模型在语义匹配基准中优于里程碑基准,包括在语义匹配基准上最先进的方法。

URL

https://arxiv.org/abs/2311.18540

PDF

https://arxiv.org/pdf/2311.18540.pdf


Tags
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 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 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