L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality object attention mining. We observe that classification models can discover object regions with more details when replacing the input image with its local patches. Taking this into account, we first leverage a local classification network to extract attentions from multiple local patches randomly cropped from the input image. Then, we utilize a global network to learn complementary attention knowledge across multiple local attention maps online. Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks. Experiments show that our method attains 72.1% and 44.2% mIoU scores on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively, setting new state-of-the-art records. Code is available at https://github.com/PengtaoJiang/L2G.
Code (1)
Tasks
ObjectSemantic SegmentationTransfer LearningWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
Distilling Global and Local Logits With Densely Connected Relations
In prevalent knowledge distillation, logits in most image recognition models are computed by global average pooling, then used to learn to encode the high-level and task-relevant knowledge. In this work, we solve the…
image-classificationImage ClassificationKnowledge Distillationobject-detection+2Enhancing Cross-Problem Vehicle Routing via Federated Learning
Vehicle routing problems (VRPs) constitute a core optimization challenge in modern logistics and supply chain management. The recent neural combinatorial optimization (NCO) has demonstrated superior efficiency over some …
Federated LearningFedPCL-CDR: A Federated Prototype-based Contrastive Learning Framework for Privacy-Preserving Cross-domain Recommendation
Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR approaches often assume that user-item interaction data …
Contrastive LearningFederated LearningPrivacy PreservingTransfer LearningPatch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment
With the rapid advancement of image generation technologies, perceptual quality assessment of AI-generated images has emerged as a crucial research direction in computer vision. The core challenge of this task lies in ac…
Image Quality AssessmentComputational EfficiencyKnowledge DistillationImage GenerationCDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning
In a practical setting towards better generalization abilities of client models for realizing robust personalized Federated Learning (FL) systems, efficient model aggregation methods have been considered as a critical re…
Federated LearningKnowledge DistillationPersonalized Federated LearningTransfer Learning