Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
원문 초록
Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grounding under data-scarce settings in this paper. To address the data scarcity, we propose a novel framework, POBF (Paint Outside the Box and Filter). POBF synthesizes images by inpainting outside the box, tackling a label misalignment issue encountered in previous works. Furthermore, POBF leverages an innovative filtering scheme to select the most effective training data. This scheme combines a hardness score and an overfitting score, balanced by a penalty term. Extensive experiments across four benchmark datasets demonstrate that POBF consistently improves performance, achieving an average gain of 5.83\% over the real-data-only method and outperforming leading baselines by 2.29\%-3.85\% in accuracy. Additionally, we validate the robustness and generalizability of POBF across various generative models, training data sizes, and model architectures.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GTA1: GUI Test-time Scaling Agent
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.