Papers Unsupervised Part Discovery
“Unsupervised Part Discovery” 태그가 달린 논문 7편 · 필터 해제
Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints
Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminate the reliance on labels, most of them c…
Image RestorationUnsupervised Part DiscoveryBeyond Patches: Mining Interpretable Part-Prototypes for Explainable AI
Deep learning has provided considerable advancements for multimedia systems, yet the interpretability of deep models remains a challenge. State-of-the-art post-hoc explainability methods, such as GradCAM, provide visual …
Unsupervised Part DiscoveryUnsupervised Part Discovery via Dual Representation Alignment
Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has establi…
Representation LearningUnsupervised Part DiscoveryPDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers
Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery driven by a fine-grained classification t…
Fine-Grained Image ClassificationImage ClassificationUnsupervised Part DiscoveryUnsupervised Part Discovery from Contrastive Reconstruction
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learni…
Representation LearningUnsupervised Keypoint EstimationUnsupervised Part DiscoveryUnsupervised Part Discovery via Feature Alignment
Understanding objects in terms of their individual parts is important, because it enables a precise understanding of the objects' geometrical structure, and enhances object recognition when the object is seen in a novel …
ObjectObject RecognitionUnsupervised Part DiscoveryUnsupervised Part Discovery by Unsupervised Disentanglement
We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pi…
DisentanglementSegmentationUnsupervised Part Discovery