Riwal Lefort

Weakly supervised classification of objects in images using soft random forests

The development of robust classification model is among the important issues in computer vision. This paper deals with weakly supervised learning that generalizes the supervised and semi-supervised learning. In weakly supervised learning training data are given as the priors of each class for each sample. We first propose a weakly supervised strategy for learning soft decision trees. Besides, the introduction of class priors for training samples instead of hard class labels makes natural the formulation of an iterative learning procedure. We report experiments for UCI object recognition datasets. These experiments show that recognition performance close to the supervised learning can be expected using the propose framework. Besides, an application to semi-supervised learning, which can be regarded as a particular case of weakly supervised learning, further demonstrates the pertinence of the contribution. We further discuss the relevance of weakly supervised learning for computer vision applications.

Object recognition using proportion-based prior information: Application to fisheries acoustics

This paper addresses the inference of probabilistic classification models using weakly supervised learning. The main contribution of this work is the development of learning methods for training datasets consisting of groups of objects with known relative class priors. This can be regarded as a generalization of the situation addressed by Bishop and Ulusoy (2005), where training information is given as the presence or absence of object classes in each set. Generative and discriminative classification methods are conceived and compared for weakly supervised learning, as well as a non-linear version of the probabilistic discriminative models. The considered models are evaluated on standard datasets and an application to fisheries acoustics is reported. The proposed proportion-based training is demonstrated to outperform model learning based on presence/absence information and the potential of the non-linear discriminative model is shown.

Weakly supervised learning using proportion-based information: An application to fisheries acoustics

This paper addresses the inference of probabilistic classification models using weakly supervised learning. In contrast to previous work, the use of proportion-based training data is investigated in combination to non-linear classification models. An application to fisheries acoustics and fish school classification is considered and experiments are reported for synthetic and real datasets.

Spatial Statistics of Objects in 3-D Sonar Images: Application to Fisheries Acoustics

In this letter, we address the characterization of objects in 3-D sonar images of the water column obtained by a multibeam echo sounder. Compared with classic 2-D images from a monobeam echo sounder, these 3-D images provide finer scale observation of the pelagic biomasses and new tools to characterize 3-D distributions. By viewing object patterns as realizations of spatial point processes, we investigate descriptive spatial statistics. This method is then applied to 3-D fisheries acoustics data set for characterization of the distribution of pelagic fish schools. Reported experiments illustrate the relevance of the proposed descriptors. The comparison of our method with 2-D sonar data analysis further demonstrates the information gain from using 3-D sonar imagery.

Combining image-level and object-level inference for weakly supervised object recognition. Application to fisheries acoustics

This paper addresses weakly supervised object recognition. We show how the combination of an image-level inference, in terms of image-level object class priors, can lead to better training of object recognition models. Stated within a probabilistic setting, the proposed approach is applied to fisheries acoustics and fish school recognition.

Weakly supervised learning with decision trees applied to fisheries acoustics.

This paper addresses the training of classification trees for weakly labelled data. We call “weakly labelled data”, a training set such as the prior labelling information provided refers to vector that indicates the probabilities for instances to belong to each class. Classification tree typically deals with hard labelled data, in this paper a new procedure is suggested in order to train a tree from weakly labelled data. Resulting tree is different than usual in the sense that weak labels are taking into account and affected to test instances. Considering a forest, we show how trees can be associated in the test step. The proposed method is compared with typical models such as generative and discriminative methods for object recognition and we show that our model can outperform the two previous. The considered models are evaluated on standard datasets from UCI and an application to fisheries acoustics is considered.

Weakly Supervised Learning: Application to Fish School Recognition

This chapter deals with object recognition in images involving a weakly supervised classification model. In weakly supervised learning, the label information of the training dataset is provided as a prior knowledge for each class. This prior knowledge is coming from a global proportion annotation of images. In this chapter, we compare three opposed classification models in a weakly supervised classification issue: a generative model, a discriminative model and a model based on random forests. Models are first introduced and discussed, and an application to fisheries acoustics is presented. Experiments show that random forests outperform discriminative and generative models in supervised learning but random forests are not robust to high complexity class proportions. Finally, a compromise is achieved by taking a combination of classifiers that keeps the accuracy of random forests and exploits the robustness of discriminative models.

Weakly supervised classification with bagging in fisheries acoustics

Statistical training allows the establishment of a probabilistic classification model. In the supervised case, the model is assessed from a labelled dataset, i.e. each observed data has a label. In the weakly-supervised case, the label is not exactly known. In our instance, the probability to associate the observation to the different classes is known. Thus, labels for the data are a probability vector. Methods developed in this paper are applied to object recognition in images. These images contain objects that must be classified according to their class membership. The ground truth is the knowledge of the relative proportion of classes in each labelled images. This global proportion leads to probability vector label for each training object. The originality of this paper consists in the association between weakly labelled data and several probabilistic discriminative models that are mixed using a bagging technique. Two classification models (Bayesian and discriminative) are compared on oceanographic data. The objective is to recognize the species of fish schools in acoustic images. The relative class proportion in labelled images is given by successive trawl catches. The results show that the discriminative model is more robust than the Bayesian model. The contribution of the bagging is shown for the discriminative model.

Automatic fish school classification for acoustic sensing of marine ecosystem

With the human demand for fish and the global warming effects, we know that marine populations are changing. Developing methods for observing and analyzing the spatio-temporal variations of marine ecosystems is then of primary importance. In this context, underwater acoustics remote sensing has a great potential. Operational systems mainly rely on expert interpretation of echograms acquired by sonar echosounders. In this works, we propose new algorithms for the analysis of acoustic survey regarding the inference of species mixing proportion. They rely on the definition and training of probabilistic school classification models from survey data.