paper-with-me

Papers

Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning

2024-07-18 · Ans Munir, Faisal Z. Qureshi, Muhammad Haris Khan, Mohsen Ali

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 Compositional Zero-Shot Learning (OW-CZSL) in this study, where our test space encompasses all potential combinations of attributes and objects. Our approach involves utilizing the self-attention mechanism between attributes and objects to achieve better generalization from seen to unseen compositions. Utilizing a self-attention mechanism facilitates the model's ability to identify relationships between attribute and objects. The similarity between the self-attended textual and visual features is subsequently calculated to generate predictions during the inference phase. The potential test space may encompass implausible object-attribute combinations arising from unrestricted attribute-object pairings. To mitigate this issue, we leverage external knowledge from ConceptNet to restrict the test space to realistic compositions. Our proposed model, Attention-based Simple Primitives (ASP), demonstrates competitive performance, achieving results comparable to the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2407.13715

Code (1)

ans92/ASP 공식 구현 pytorch

Tasks

AttributeCompositional Zero-Shot LearningObjectZero-Shot Learning

Similar Papers 제목 키워드 기반

Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning

2022-11-05 · Zhe Liu, Yun Li, Lina Yao, Xiaojun Chang 외

The task of Compositional Zero-Shot Learning (CZSL) is to recognize images of novel state-object compositions that are absent during the training stage. Previous methods of learning compositional embedding have shown eff…

Compositional Zero-Shot LearningDisentanglementZero-Shot Learning

ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning

2022-11-19 · Fushuo Huo, Wenchao Xu, Song Guo, Jingcai Guo 외

Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output spa…

Compositional Zero-Shot LearningObjectZero-Shot Learning

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

2022-05-13 · CVPR 2022 1 · Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata

The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions. In this …

Compositional Zero-Shot LearningMissing LabelsZero-Shot Learning

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning

2025-06-26 · Xiao Zhang, Yongqiang Ma, Haodong Jing, Nanning Zheng

Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives fe…

Compositional Zero-Shot LearningMixture-of-ExpertsZero-Shot Learning

Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

2026-08-18 · Fangling Jiang, Qi Li, Bing Liu, Weining Wang 외 arxiv

Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack types absent from training. Existing prom…

Domain GeneralizationFace Anti-Spoofing