This paper describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversity Variables accessible and understandable to everyone through dynamic maps and fact sheets. Its core purpose is to allow users to explore high-resolution AI-generated maps of species distributions, habitat types, and biodiversity indicators across Europe. These maps, developed through a cascading pipeline involving convolutional neural networks and large language models, provide an intuitive yet information-rich interface to better understand biodiversity, with resolutions as precise as 50×50 meters. The website also enables exploration of specific regions, allowing users to select areas of interest on the map (e.g., urban green spaces, protected areas, or riverbanks) to view local species and their coverage. Additionally, GeoPl@ntNet generates comprehensive reports for selected regions, including insights into the number of protected species, invasive species, and endemic species.

Average- K classification is an alternative to top- K clas-sification in which the number of labels returned varies with the ambiguity of the input image but must average to K over all the samples. A simple method to solve this task is to threshold the softmax output of a model trained with the cross-entropy loss. This approach is theoretically proven to be asymptotically consistent, but it is not guaranteed to be optimal for a finite set of samples. In this paper, we pro-pose a new loss function based on a multi-label classification head in addition to the classical softmax. This second head is trained using pseudo-labels generated by thresholding the softmax head while guaranteeing that K classes are returned on average. We show that this approach allows the model to better capture ambiguities between classes and, as a result, to return more consistent sets of possible classes. Experiments on two datasets from the literature demon-strate that our approach outperforms the softmax baseline, as well as several other loss functions more generally de-signed for weakly supervised multi-label classification. The gains are larger the higher the uncertainty, especially for classes with few samples.

The difficulty of monitoring biodiversity at fine scales and over large areas limits ecological knowledge and conservation efforts. To fill this gap, Species Distribution Models (SDMs) predict species across space from spatially explicit features. Yet, they face the challenge of integrating the rich but heterogeneous data made available over the past decade, notably millions of opportunistic species observations and standardized surveys, as well as multi-modal remote sensing data.In light of that, we have designed and developed a new European-scale dataset for SDMs at high spatial resolution (10--50m), including more than 10k species (i.e., most of the European flora). The dataset comprises 5M heterogeneous Presence-Only records and 90k exhaustive Presence-Absence survey records, all accompanied by diverse environmental rasters (e.g., elevation, human footprint, and soil) traditionally used in SDMs. In addition, it provides Sentinel-2 RGB and NIR satellite images with 10 m resolution, a 20-year time series of climatic variables, and satellite time series from the Landsat program.In addition to the data, we provide an openly accessible SDM benchmark (hosted on Kaggle), which has already attracted an active community and a set of strong baselines for single predictor/modality and multimodal approaches.All resources, e.g., the dataset, pre-trained models, and baseline methods (in the form of notebooks), are available on Kaggle, allowing one to start with our dataset literally with two mouse clicks.

Controversy refers to content attracting different point-of-views, as well as positive and negative feedback on a specific event, gathering users into different communities. Research on controversy led to two main categories of works: controversy detection/quantification and controversy explainability. When the former aims to quantify controversy on a topic, the latter aims to understand why a topic is controversial or not. This paper mainly contributes to the controversy explainability. We analyze topic discussions on Twitter from the community perspective to investigate the power of text in classifying tweets into the right community. We propose a SHAP-based pipeline to quantify impactful text features on predictions of three tweet classifiers. We also rely on the use of different text features namely BERT, TF − IDF, and LIWC. The results we obtain from both SHAP plots and statistical analysis show clearly significant impacts of some text features in classifying tweets.It also highlights the relevance of the study as well as the potential benefits of combining text and user interactions to quantify controversy.

Mental and physical health are strongly linked in a bidirectional relationship. Due to the stigma, ignorance, prejudice, fear, and many other reasons, there exists a large universal treatment gap for people with mental disorders. This could motivate those at-risk individuals to find their way into social networks, asking for information or emotional support. Language could provide a natural eyepiece for the study and detection of such at-risk individuals through their writings on social media platforms. In this paper, we consider the problem of detecting at-risk users with clear signs of depression, anorexia, self-harm, and suicidal thoughts. We introduce NCNL, a novel deep learning ensemble architecture that makes use of multiple noisy base learners in Negative Correlation Learning (NCL) configuration for text classification. NCNL is designed to be, backbone-independent, and we examine it with modern Transformer-based architectures. We evaluate our models on six different tasks for at-risk user detection and classification. Our models achieve significant improvements over existing state-of-the-art results reported for five out of the six tasks. Extensive experiments show how NCNL improves diversity over the classical conventional ensemble and the effect of using noisy base learners.

While neural networks (NN) have been successfully applied to many NLP tasks, the way they function is often difficult to interpret. In this article, we focus on binary text classification via NNs and propose a new tool, which includes a visualization of the decision boundary and the distances of data elements to this boundary. This tool increases the interpretability of NN. Our approach uses two innovative views: (1) an overview of the text representation space and (2) a local view allowing data exploration around the decision boundary for various localities of this representation space. These views are integrated into a visual platform, EBBE-Text, which also contains state-of-the-art visualizations of NN representation spaces and several kinds of information obtained from the classification process. The various views are linked through numerous interactive functionalities that enable easy exploration of texts and classification results via the various complementary views. A user study shows the effectiveness of the visual encoding and a case study illustrates the benefits of using our tool for the analysis of the classifications obtained with several recent NNs and two datasets.

In modern classification tasks, the number of labels is getting larger and larger, as is the size of the datasets encountered in practice. As the number of classes increases, class ambiguity and class imbalance become more and more problematic to achieve high top-1 accuracy. Meanwhile, Top-K metrics (metrics allowing K guesses) have become popular, especially for performance reporting. Yet, proposing top-K losses tailored for deep learning remains a challenge, both theoretically and practically. In this paper we introduce a stochastic top-K hinge loss inspired by recent developments on top-K calibrated losses. Our proposal is based on the smoothing of the top-K operator building on the flexible "perturbed optimizer" framework. We show that our loss function performs very well in the case of balanced datasets, while benefiting from a significantly lower computational time than the state-of-the-art top-K loss function. In addition, we propose a simple variant of our loss for the imbalanced case. Experiments on a heavy-tailed dataset show that our loss function significantly outperforms other baseline loss functions.

Convolutional Neural Networks (CNNs) are statistical models suited for learning complex visual patterns. In the context of Species Distribution Models (SDM) and in line with predictions of landscape ecology and island biogeography, CNN could grasp how local landscape structure affects prediction of species occurrence in SDMs. The prediction can thus reflect the signatures of entangled ecological processes. Although previous machine-learning based SDMs can learn complex influences of environmental predictors, they cannot acknowledge the influence of environmental structure in local landscapes (hence denoted "punctual models"). In this study, we applied CNNs to a large dataset of plant occurrences in France (GBIF), on a large taxonomical scale, to predict ranked relative probability of species (by joint learning) to any geographical position. We examined the way local environmental landscapes improve prediction by performing alternative CNN models deprived of information on landscape heterogeneity and structure ("ablation experiments"). We found that the landscape structure around location crucially contributed to improve predictive performance of CNN-SDMs. CNN models can classify the predicted distributions of many species, as other joint modelling approaches, but they further prove efficient in identifying the influence of local environmental landscapes. CNN can then represent signatures of spatially structured environmental drivers. The prediction gain is noticeable for rare species, which open promising perspectives for biodiversity monitoring and conservation strategies. Therefore, the approach is of both theoretical and practical interest. We discuss the way to test hypotheses on the patterns learnt by CNN, which should be essential for further interpretation of the ecological processes at play.

Large-scale annotated corpora have yielded impressive performance improvements in computer vision and multimedia content analysis. However, such datasets depend on an enormous amount of human labeling effort. When the labels correspond to well-known concepts, it is straightforward to train the annotators by giving a few examples with known answers. It is also straightforward to judge the quality of their labels. Neither is true when there are thousands of complex domain-specific labels. Training on all labels is infeasible and the quality of an annotator's judgements may be vastly different for some subsets of labels than for others. This paper proposes a set of data-driven algorithms to 1) train image annotators on how to disambiguate among automatically generated candidate labels, 2) evaluate the quality of annotators' label suggestions, and 3) weigh predictions. The algorithms adapt to the skills of each annotator both in the questions asked and the weights given to their answers. The underlying judgements are Bayesian, based on adaptive priors. We measure the benefits of these algorithms on a live user experiment related to image-based plant identification involving around 1000 people. The proposed methods are shown to enable huge gains in annotation accuracy. A standard user can correctly label around 2% of our data. This goes up to 80% with machine learning assisted training and assignment and up to almost 90% when doing a weighted combination of several annotators' labels.

In a typical citizen science/crowdsourcing environment, the contributors label items. When there are few labels, it is straightforward to train contributors and judge the quality of their labels by giving a few examples with known answers. Neither is true when there are thousands of domain-specific labels and annotators with heterogeneous skills. This demo paper presents an Active User Training framework implemented as a serious game called ThePlantGame. It is based on a set of data-driven algorithms allowing to (i) actively train annotators, and (ii) evaluate the quality of contributors' answers on new test items to optimize predictions.