Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915611664187392 |
|---|---|
| author | Ghosh, B. Harikumar, H. Rana, S. |
| author_facet | Ghosh, B. Harikumar, H. Rana, S. |
| contents | Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Targeted Manifold Manipulation-Nearest Neighbour (TMM-NN), which reconceptualises retrieval by assessing how readily each sample can be nudged into a designated region of the feature manifold; neighbourhoods are defined by a sample's responsiveness to a targeted perturbation rather than absolute geometric distance. TMM-NN implements this through a lightweight, query-specific trigger patch. The patch is added to the query image, and the network is weakly ``backdoored'' so that any input with the patch is steered toward a dummy class. Images similar to the query need only a slight shift and are classified as the dummy class with high probability, while dissimilar ones are less affected. By ranking candidates by this confidence, TMM-NN retrieves the most semantically related neighbours. Robustness analysis and benchmark experiments confirm this trigger-based ranking outperforms traditional metrics under noise and across diverse tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06261 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation Ghosh, B. Harikumar, H. Rana, S. Computer Vision and Pattern Recognition Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Targeted Manifold Manipulation-Nearest Neighbour (TMM-NN), which reconceptualises retrieval by assessing how readily each sample can be nudged into a designated region of the feature manifold; neighbourhoods are defined by a sample's responsiveness to a targeted perturbation rather than absolute geometric distance. TMM-NN implements this through a lightweight, query-specific trigger patch. The patch is added to the query image, and the network is weakly ``backdoored'' so that any input with the patch is steered toward a dummy class. Images similar to the query need only a slight shift and are classified as the dummy class with high probability, while dissimilar ones are less affected. By ranking candidates by this confidence, TMM-NN retrieves the most semantically related neighbours. Robustness analysis and benchmark experiments confirm this trigger-based ranking outperforms traditional metrics under noise and across diverse tasks. |
| title | Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.06261 |