Recurrent Vision Transformer for Solving Visual Reasoning Problems
원문 초록
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the model, allowing it to learn using far fewer free parameters, using only 28k training samples. A comprehensive ablation study confirms the importance of a hybrid CNN + Transformer architecture and the role of the feedback connections, which iteratively refine the internal representation until a stable prediction is obtained. In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation
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
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.