paper-with-me

홈 › Papers

Are We Recognizing the Jaguar or Its Background? A Diagnostic Framework for Jaguar Re-Identification

2026-04-06 · Antonio Rueda-Toicen, Abigail Allen Martin, Daniil Morozov, Matin Mahmood, Alexandra Schild, Shahabeddin Dayani, Davide Panza, Gerard de Melo arxiv

Jaguar re-identification (re-ID) from citizen-science imagery can look strong on standard retrieval metrics while still relying on the wrong evidence, such as background context or silhouette shape, instead of the coat pattern that defines identity. We introduce a diagnostic framework for wildlife re-ID with two axes: a leakage-controlled context ratio, background/foreground, computed from inpainted background-only versus foreground-only images, and a laterality diagnostic based on cross-flank retrieval and mirror self-similarity. To make these diagnostics measurable, we curate a Pantanal jaguar benchmark with per-pixel segmentation masks and an identity-balanced evaluation protocol. We then use representative mitigation families, ArcFace fine-tuning, anti-symmetry regularization, and Lorentz hyperbolic embeddings, as case studies under the same evaluation lens. The goal is not only to ask which model ranks best, but also what visual evidence it uses to do so.

📄 PDF Abstract BibTeX arXiv:2604.09690

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

JaGuard: Position Error Correction of GNSS Jamming with Deep Temporal Graphs

2025-09-17 · Ivana Kesić, Aljaž Blatnik, Carolina Fortuna, Blaž Bertalanič arxiv

Global Navigation Satellite Systems (GNSS) face growing disruption from intentional jamming, undermining critical infrastructure where precise positioning and timing are essential. Current position error correction (PEC)…

Graph Regression

Automatic Detection and Recognition of Individuals in Patterned Species

2020-05-06 · Gullal Singh Cheema, Saket Anand

Visual animal biometrics is rapidly gaining popularity as it enables a non-invasive and cost-effective approach for wildlife monitoring applications. Widespread usage of camera traps has led to large volumes of collected…

object-detectionObject Detection

Active Learning for Entity Filtering in Microblog Streams

2015-08-01 · Damiano Spina, Maria-Hendrike Peetz, Maarten de Rijke

Monitoring the reputation of entities such as companies or brands in microblog streams (e.g., Twitter) starts by selecting mentions that are related to the entity of interest. Entities are often ambiguous (e.g., "Jaguar'…

Active Learning

Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order

2025-06-04 · Egor Petrov, Grigoriy Evseev, Aleksey Antonov, Andrey Veprikov 외

Fine-tuning Large Language Models (LLMs) is essential for adapting pre-trained models to downstream tasks. Yet traditional first-order optimizers such as Stochastic Gradient Descent (SGD) and Adam incur prohibitive memor…

parameter-efficient fine-tuning

The phenomenon of growing surface interference explains the rosette pattern of jaguar

2017-11-15

One possible mechanism to explain how animals got their coat patterns was proposed by Alan Turing. He assumed that two kinds of morphogens diffuse on a surface and interact with each other, generating a reaction-diffusio…