Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints
원문 초록
Cross-modal embeddings, between textual and visual modalities, aim to organise multimodal instances by their semantic correlations. State-of-the-art approaches use maximum-margin methods, based on the hinge-loss, to enforce a constant margin m, to separate projections of multimodal instances from different categories. In this paper, we propose a novel scheduled adaptive maximum-margin (SAM) formulation that infers triplet-specific constraints during training, therefore organising instances by adaptively enforcing inter-category and inter-modality correlations. This is supported by a scheduled adaptive margin function, that is smoothly activated, replacing a static margin by an adaptively inferred one reflecting triplet-specific semantic correlations while accounting for the incremental learning behaviour of neural networks to enforce category cluster formation and enforcement. Experiments on widely used datasets show that our model improved upon state-of-the-art approaches, by achieving a relative improvement of up to ~12.5% over the second best method, thus confirming the effectiveness of our scheduled adaptive margin formulation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Attributes Shape the Embedding Space of Face Recognition Models
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
Improving Large Language Model Safety with Contrastive Representation Learning
Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm
토론
이 논문과 연결된 포럼 글이 아직 없습니다.