Papers with Code 아카이브
Compositional Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 6
Compositional Zero-Shot Learning (CZSL) is a computer vision task in which the goal is to recognize unseen compositions fromed from seen state and object during training. The key challenge in CZSL is the inherent entanglement between the state and object within the context of an image. Some example benchmarks for this task are MIT-states, UT-Zappos, and C-GQA. Models are usually evaluated with the Accuracy for both seen and unseen compositions, as well as their Harmonic Mean(HM).
<span style="color:grey; opacity: 0.6">( Image credit: Heosuab )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ExplainableML/co-cge
공식 코드Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
https://github.com/ExplainableML/czsl
공식 코드https://github.com/FrankRuis/ProtoProp
공식 코드Independent Prototype Propagation for Zero-Shot Compositionality
https://github.com/Tushar-N/attributes-as-operators
공식 코드Attributes as Operators: Factorizing Unseen Attribute-Object Compositions
https://github.com/ans92/ASP
공식 코드Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning
https://github.com/batsresearch/csp
공식 코드Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
https://github.com/bighuang624/rl-czsl
공식 코드https://github.com/bighuang624/troika
공식 코드Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
https://github.com/cogito2012/plid
공식 코드Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
https://github.com/daoyuan98/relation-czsl
공식 코드Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
https://github.com/explainableml/kg-sp
공식 코드KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
https://github.com/forest-art/dfsp
공식 코드Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
https://github.com/hanjaekim98/cot
공식 코드Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
https://github.com/haoosz/ade-czsl
공식 코드Learning Attention as Disentangler for Compositional Zero-shot Learning
https://github.com/hirunima/OWCZSL
공식 코드Unified Framework for Open-World Compositional Zero-shot Learning
https://github.com/hlr/gipcol
공식 코드GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning
https://github.com/lisuyi/pbadv_czsl
공식 코드Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
https://github.com/ltpwy/msci
공식 코드MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning
https://github.com/nirat1606/oadis
공식 코드https://github.com/nv-research-israel/causal_comp
공식 코드https://github.com/pris-cv/ivr
공식 코드Learning Invariant Visual Representations for Compositional Zero-Shot Learning
https://github.com/quhongyu/cluspro
공식 코드Learning Clustering-based Prototypes for Compositional Zero-shot Learning
https://github.com/wjpoom/spec
공식 코드Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
https://github.com/wqshmzh/canet-czsl
공식 코드Learning Conditional Attributes for Compositional Zero-Shot Learning
https://github.com/xduxyli/scen-master
공식 코드Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
https://github.com/xud-yan/Trident
공식 코드Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
https://github.com/zhaohengz/caila
공식 코드CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
https://github.com/zhihou7/batchformer
공식 코드BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
https://github.com/zhaohengz/llamp
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.