Eulanda M. dos Santos

Fagner Cunha, Eulanda M. dos Santos, Juan G. Colonna

Camera traps are a method for monitoring wildlife and they collect a large number of pictures. The number of images collected of each species usually follows a long-tail distribution, i.e., a few classes have a large number of instances, while a lot of species have just a small percentage. Although in most cases these rare species are the ones of interest to ecologists, they are often neglected when using deep-learning models because these models require a large number of images for the training. In this work, a simple and effective framework called Square-Root Sampling Branch (SSB) is proposed, which combines two classification branches that are trained using square-root sampling and instance sampling to improve long-tail visual recognition, and this is compared to state-of-the-art methods for handling this task: square-root sampling, class-balanced focal loss, and balanced group softmax. To achieve a more general conclusion, the methods for handling long-tail visual recognition were systematically evaluated in four families of computer vision models (ResNet, MobileNetV3, EfficientNetV2, and Swin Transformer) and four camera-trap datasets with different characteristics. Initially, a robust baseline with the most recent training tricks was prepared and, then, the methods for improving long-tail recognition were applied. Our experiments show that square-root sampling was the method that most improved the performance for minority classes by around 15%; however, this was at the cost of reducing the majority classes' accuracy by at least 3%. Our proposed framework (SSB) demonstrated itself to be competitive with the other methods and achieved the best or the second-best results for most of the cases for the tail classes; but, unlike the square-root sampling, the loss in the performance of the head classes was minimal, thus achieving the best trade-off among all the evaluated methods.

Fagner Cunha, Eulanda M. dos Santos, Raimundo Barreto et al.

Monitoring wildlife through camera traps produces a massive amount of images, whose a significant portion does not contain animals, being later discarded. Embedding deep learning models to identify animals and filter these images directly in those devices brings advantages such as savings in the storage and transmission of data, usually resource-constrained in this type of equipment. In this work, we present a comparative study on animal recognition models to analyze the trade-off between precision and inference latency on edge devices. To accomplish this objective, we investigate classifiers and object detectors of various input resolutions and optimize them using quantization and reducing the number of model filters. The confidence threshold of each model was adjusted to obtain 96% recall for the nonempty class, since instances from the empty class are expected to be discarded. The experiments show that, when using the same set of images for training, detectors achieve superior performance, eliminating at least 10% more empty images than classifiers with comparable latencies. Considering the high cost of generating labels for the detection problem, when there is a massive number of images labeled for classification (about one million instances, ten times more than those available for detection), classifiers are able to reach results comparable to detectors but with half latency.

Bernardo B. Gatto, Juan G. Colonna, Eulanda M. dos Santos et al.

Automatic analysis of bioacoustic signals is a fundamental tool to evaluate the vitality of our planet. Frogs and bees, for instance, may act like biological sensors providing information about environmental changes. This task is fundamental for ecological monitoring still includes many challenges such as nonuniform signal length processing, degraded target signal due to environmental noise, and the scarcity of the labeled samples for training machine learning. To tackle these challenges, we present a bioacoustic signal classifier equipped with a discriminative mechanism to extract useful features for analysis and classification efficiently. The proposed classifier does not require a large amount of training data and handles nonuniform signal length natively. Unlike current bioacoustic recognition methods, which are task-oriented, the proposed model relies on transforming the input signals into vector subspaces generated by applying Singular Spectrum Analysis (SSA). Then, a subspace is designed to expose discriminative features. The proposed model shares end-to-end capabilities, which is desirable in modern machine learning systems. This formulation provides a segmentation-free and noise-tolerant approach to represent and classify bioacoustic signals and a highly compact signal descriptor inherited from SSA. The validity of the proposed method is verified using three challenging bioacoustic datasets containing anuran, bee, and mosquito species. Experimental results on three bioacoustic datasets have shown the competitive performance of the proposed method compared to commonly employed methods for bioacoustics signal classification in terms of accuracy.

Bernardo B. Gatto, Eulanda M. dos Santos, Alessandro L. Koerich et al.

The increasing use of multiple sensors, which produce a large amount of multi-dimensional data, requires efficient representation and classification methods. In this paper, we present a new method for multi-dimensional data classification that relies on two premises: 1) multi-dimensional data are usually represented by tensors, since this brings benefits from multilinear algebra and established tensor factorization methods; and 2) multilinear data can be described by a subspace of a vector space. The subspace representation has been employed for pattern-set recognition, and its tensor representation counterpart is also available in the literature. However, traditional methods do not use discriminative information of the tensors, degrading the classification accuracy. In this case, generalized difference subspace (GDS) provides an enhanced subspace representation by reducing data redundancy and revealing discriminative structures. Since GDS does not handle tensor data, we propose a new projection called n-mode GDS, which efficiently handles tensor data. We also introduce the n-mode Fisher score as a class separability index and an improved metric based on the geodesic distance for tensor data similarity. The experimental results on gesture and action recognition show that the proposed method outperforms methods commonly used in the literature without relying on pre-trained models or transfer learning.