Papers with Code 아카이브
Unbiased Scene Graph Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 31
Unbiased Scene Graph Generation (Unbiased SGG) aims to predict more informative scene graphs composed of more "tail predicates" *(in contrast to "head predicates" in terms of class frequencies) by dealing with the skewed, long-tailed predicate class distribution. (Definition from Chiou et al. "Recovering the Unbiased Scene Graphs from the Biased Ones")
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Ensemble Predicate Decoding for Unbiased Scene Graph Generation
Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation
ALF: Adaptive Label Finetuning for Scene Graph Generation
FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing
Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation
Vision Relation Transformer for Unbiased Scene Graph Generation
Compositional Feature Augmentation for Unbiased Scene Graph Generation
Generalized Unbiased Scene Graph Generation
Unbiased Scene Graph Generation via Two-stage Causal Modeling
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
Unbiased Scene Graph Generation in Videos
Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation
Peer Learning for Unbiased Scene Graph Generation
Unbiased Scene Graph Generation using Predicate Similarities
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
Rethinking the Evaluation of Unbiased Scene Graph Generation
Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation
Learning Structured Representations of Visual Scenes
Fine-Grained Scene Graph Generation with Data Transfer
Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
Recovering the Unbiased Scene Graphs from the Biased Ones
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation
Unbiased Scene Graph Generation from Biased Training
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.