Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915375340322816 |
|---|---|
| author | Kim, Jaeyoon Cho, Yoonki Kim, Taeyoung Yoon, Sung-Eui |
| author_facet | Kim, Jaeyoon Cho, Yoonki Kim, Taeyoung Yoon, Sung-Eui |
| contents | Nearest neighbor (NN) graph based visual re-ranking has emerged as a powerful approach for improving retrieval accuracy, offering the advantages of effectively exploring high-dimensional manifolds without requiring additional fine-tuning. However, the effectiveness of NN graph-based re-ranking is fundamentally constrained by the quality of its edge connectivity, as incorrect connections between dissimilar (negative) images frequently occur. This is known as a noisy edge problem, which hinders the re-ranking performance of existing techniques and limits their potential. To remedy this issue, we propose a complementary denoising method based on Continuous Conditional Random Fields (C-CRF) that leverages statistical distances derived from similarity-based distributions. As a pre-processing step for enhancing NN graph-based retrieval, our approach constructs fully connected cliques around each anchor image and employs a novel statistical distance metric to robustly alleviate noisy edges before re-ranking while achieving efficient processing through offline computation. Extensive experimental results demonstrate that our method consistently improves three different NN graph-based re-ranking approaches, yielding significant gains in retrieval accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13875 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF Kim, Jaeyoon Cho, Yoonki Kim, Taeyoung Yoon, Sung-Eui Computer Vision and Pattern Recognition Nearest neighbor (NN) graph based visual re-ranking has emerged as a powerful approach for improving retrieval accuracy, offering the advantages of effectively exploring high-dimensional manifolds without requiring additional fine-tuning. However, the effectiveness of NN graph-based re-ranking is fundamentally constrained by the quality of its edge connectivity, as incorrect connections between dissimilar (negative) images frequently occur. This is known as a noisy edge problem, which hinders the re-ranking performance of existing techniques and limits their potential. To remedy this issue, we propose a complementary denoising method based on Continuous Conditional Random Fields (C-CRF) that leverages statistical distances derived from similarity-based distributions. As a pre-processing step for enhancing NN graph-based retrieval, our approach constructs fully connected cliques around each anchor image and employs a novel statistical distance metric to robustly alleviate noisy edges before re-ranking while achieving efficient processing through offline computation. Extensive experimental results demonstrate that our method consistently improves three different NN graph-based re-ranking approaches, yielding significant gains in retrieval accuracy. |
| title | Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.13875 |