Papers Compositional Zero-Shot Learning
“Compositional Zero-Shot Learning” 태그가 달린 논문 81편 · 필터 해제
Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptio…
AttributeClusteringCompositional Zero-Shot LearningContrastive Learning+1Learning Primitive Relations for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to identify unseen state-object compositions by leveraging knowledge learned from seen compositions. Existing approaches often independently predict states and objects, overlo…
Compositional Zero-Shot LearningZero-Shot LearningDual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of attributes and objects by leveraging knowledge learned from seen compositions. Recent approaches have explored the use of Vision-Language Mo…
Compositional Zero-Shot LearningPrompt EngineeringZero-Shot LearningSeparated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize subtle differences in meaning or the combination of states and objects through the use of known and unknown concepts during training. Existing methods either focu…
AttributeCompositional Zero-Shot LearningLanguage ModelingLanguage Modelling+3Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
Conditional dependency present one of the trickiest problems in Compositional Zero-Shot Learning, leading to significant property variations of the same state (object) across different objects (states). To address this p…
Compositional Zero-Shot LearningRepresentation LearningZero-Shot LearningDuplex: Dual Prototype Learning for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to enable models to recognize novel compositions of visual states and objects that were absent during training. Existing methods predominantly focus on learning semantic repre…
Compositional Zero-Shot LearningGraph Neural NetworkLearning Semantic RepresentationsPrompt Engineering+2LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning the primitive concepts (*i.e.*, attribute and object) from the training set. While recent works achieve impre…
AttributeCompositional Zero-Shot LearningZero-Shot LearningBeyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning
Human reasoning naturally combines concepts to identify unseen compositions, a capability that Compositional Zero-Shot Learning (CZSL) aims to replicate in machine learning models. However, we observe that focusing s…
Action RecognitionAttributeCompositional Zero-Shot Learningimage-classification+2Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects. Current CLIP-based methods in CZSL, despite their advancements, often fail to effectively understand and link …
AttributeCompositional Zero-Shot LearningContrastive LearningZero-Shot LearningUnified Framework for Open-World Compositional Zero-shot Learning
Open-World Compositional Zero-Shot Learning (OW-CZSL) addresses the challenge of recognizing novel compositions of known primitives and entities. Even though prior works utilize language knowledge for recognition, such a…
Compositional Zero-Shot LearningZero-Shot LearningLeveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attribute and object by extracting shared and exclusive pa…
AttributeCompositional Zero-Shot LearningDisentanglementLanguage Modeling+7Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, …
AttributeCompositional Zero-Shot LearningDiversityZero-Shot LearningCross-composition Feature Disentanglement for Compositional Zero-shot Learning
Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the feature divergence of an attribute (resp. obje…
AttributeCompositional Zero-Shot LearningDisentanglementLanguage Modeling+2TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components. Despite considerable progress, effectively calibrating the bias …
Compositional Zero-Shot LearningZero-Shot LearningAttention Based Simple Primitives for Open World Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compos…
AttributeCompositional Zero-Shot LearningObjectZero-Shot LearningAnticipating Future Object Compositions without Forgetting
Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focu…
AttributeCompositional Zero-Shot Learningimage-classificationImage Classification+4Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known attribute-object pairs. The primary challenge in CZSL tasks lies in the significant discrepancies introduced by the complex interactio…
AttributeCompositional Zero-Shot LearningCross-Domain Few-Shotcross-domain few-shot learning+3MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attribu…
AttributeCompositional Zero-Shot LearningZero-Shot LearningCSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods…
AttributeCompositional Zero-Shot LearningDisentanglementObject+2Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object pairs based on a limited set of observed examples. Current CZSL methodologies, despite their advancements, tend to neglect the distinct sp…
AttributeCompositional Zero-Shot LearningDiversitySpecificity+1