Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
원문 초록
Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current vision-language models is relation-level alignment: the ability to match directional semantic relations in text (e.g., "mug in grass") with spatial relationships in the image (e.g., the position of the mug relative to the grass). To tackle this problem, we show that relation alignment can be enforced by encouraging the directed language attention from 'mug' to 'grass' (capturing the semantic relation 'in') to match the directed visual attention from the mug to the grass. Tokens and their corresponding objects are softly identified using the cross-modal attention. We prove that this notion of soft relation alignment is equivalent to enforcing congruence between vision and language attention matrices under a 'change of basis' provided by the cross-modal attention matrix. Intuitively, our approach projects visual attention into the language attention space to calculate its divergence from the actual language attention, and vice versa. We apply our Cross-modal Attention Congruence Regularization (CACR) loss to UNITER and improve on the state-of-the-art approach to Winoground.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
Skywork-R1V3 Technical Report
Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.