We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within a single 3B-para...
<p><strong>Tác giả:</strong> Anindya Mondal, Sauradip Nag, Anjan Dutta</p>
<p>We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within a single 3B-parameter model. ABACUS introduces three contributions: density-aware adaptive zooming paired with an objectness map from multi-head self-attention decomposition to spatially ground count predictions; a boundary-aware count policy trained via GRPO with nested local, boundary, and global rewards to elimi...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3842572" target="_blank" rel="noopener">https://doi.org/10.1145/3842572</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3842572" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
