Degradation-based augmented training for robust individual animal re-identification

TL;DR

This work is the first to systematically study image degradation in wildlife re-identification, while introducing all the necessary benchmarks, publicly available code and data, enabling further research on this topic.

Abstract

Wildlife re-identification aims to recognise individual animals by matching query images to a database of previously identified individuals, based on their fine-scale unique morphological characteristics. Current state-of-the-art models for multispecies re- identification are based on deep metric learning representing individual identities by fea- ture vectors in an embedding space, the similarity of which forms the basis for a fast automated identity retrieval. Yet very often, the discriminative information of individual wild animals gets significantly reduced due to the presence of several degradation factors in images, leading to reduced retrieval performance and limiting the downstream eco- logical studies. Here, starting by showing that the extent of this performance reduction greatly varies depending on the animal species (18 wild animal datasets), we introduce an augmented training framework for deep feature extractors, where we apply artificial but diverse degradations in images in the training set. We show that applying this augmented training only to a subset of individuals, leads to an overall increased re-identification performance, under the same type of degradations, even for individuals not seen during training. The introduction of diverse degradations during training leads to a gain of up to 8.5% Rank-1 accuracy to a dataset of real-world degraded animal images, selected using human re-ID expert annotations provided here for the first time. Our work is the first to systematically study image degradation in wildlife re-identification, while introducing all the necessary benchmarks, publicly available code and data, enabling further research on this topic.

Figures (10)

• Figure 1: Augmenting the training set of deep feature-based re-ID models, with artificial but complex degradations increases re-ID accuracy on real-world degraded images.
• Figure 2: Visualisation of the employed degradation pipelines (simple, diverse and diverse$^{+}$) used for training augmentation, along with corresponding image samples.
• Figure 3: Datasets used for training and testing our models and the corresponding split configuration into training, search database and query sets. A part of the training set is augmented using degradations, and a subgroup of individuals is not included in the training set to test the generalisability of the models.
• Figure 4: Samples from the two extreme groups of expert-annotated images of the SeaTurtleID2022 dataset adam_seaturtleid2022_2024 (cropped heads only) with respect to clarity factors affecting re-ID. Left: "Clarity 1"-images, where identifying details like facial scales (if present in the image) are clearly visible. Right: "Clarity 4"-images, where such details are hardly visible, due to factors like blur, low resolution, distortion artifacts, etc.
• Figure 5: Left: Rank-1 accuracies of the baseline model, and the models with diverse, and diverse$^{+}$ augmentations on their training set, evaluated on the original non-degraded query set and the two artificially degraded ones (diverse and diverse$^{+}$). Accuracies are averaged for all 18 datasets and reported separately for individuals seen and not seen during training. Right: Rank-1 accuracies for the same experiments reported separately for each of the 18 datasets, where we observe that the magnitude of the adverse effects of image degradations on re-ID performance is species-specific.