Enhancing Post-Hoc Explanation Benchmark Reliability for Image Classification

Deep neural networks, while powerful for image classification, often operate as "black boxes," complicating the understanding of their decision-making processes. Various explanation methods, particularly those generating saliency maps, aim to address this challenge. However, the inconsistency issues of faithfulness metrics hinder reliable benchmarking of explanation methods. This paper employs an approach inspired by psychometrics, utilizing Krippendorf's alpha to quantify the benchmark reliability of post-hoc methods in image classification. The study proposes model training modifications, including feeding perturbed samples and employing focal loss, to enhance robustness and calibration. Empirical evaluations demonstrate significant improvements in benchmark reliability across metrics, datasets, and post-hoc methods. This pioneering work establishes a foundation for more reliable evaluation practices in the realm of post-hoc explanation methods, emphasizing the importance of model robustness in the assessment process.

Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study

An important limitation to the development of AI-based solutions for In Vitro Fertilization (IVF) is the black-box nature of most state-of-the-art models, due to the complexity of deep learning architectures, which raises potential bias and fairness issues. The need for interpretable AI has risen not only in the IVF field but also in the deep learning community in general. This has started a trend in literature where authors focus on designing objective metrics to evaluate generic explanation methods. In this paper, we study the behavior of recently proposed objective faithfulness metrics applied to the problem of embryo stage identification. We benchmark attention models and post-hoc methods using metrics and further show empirically that (1) the metrics produce low overall agreement on the model ranking and (2) depending on the metric approach, either post-hoc methods or attention models are favored. We conclude with general remarks about the difficulty of defining faithfulness and the necessity of understanding its relationship with the type of approach that is favored.

Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction

An important limitation to the development of Artificial Intelligence (AI)-based solutions for In Vitro Fertilization (IVF) is the absence of a public reference benchmark to train and evaluate deep learning (DL) models. In this work, we describe a fully annotated dataset of 756 videos of developing embryos, for a total of 337k images. We applied ResNet, LSTM, and ResNet-3D architectures to our dataset and demonstrate that they overperform algorithmic approaches to automatically annotate stage development phases. Altogether, we propose the first public benchmark that will allow the community to evaluate morphokinetic models. This is the first step towards deep learning-powered IVF. Of note, we propose highly detailed annotations with 16 different development phases, including early cell division phases, but also late cell divisions, phases after morulation, and very early phases, which have never been used before. We postulate that this original approach will help improve the overall performance of deep learning approaches on time-lapse videos of embryo development, ultimately benefiting infertile patients with improved clinical success rates (Code and data are available at https://gitlab.univ-nantes.fr/E144069X/bench_mk_pred.git).

Metrics for saliency map evaluation of deep learning explanation methods

Due to the black-box nature of deep learning models, there is a recent development of solutions for visual explanations of CNNs. Given the high cost of user studies, metrics are necessary to compare and evaluate these different methods. In this paper, we critically analyze the Deletion Area Under Curve (DAUC) and Insertion Area Under Curve (IAUC) metrics proposed by Petsiuk et al. (2018). These metrics were designed to evaluate the faithfulness of saliency maps generated by generic methods such as Grad-CAM or RISE. First, we show that the actual saliency score values given by the saliency map are ignored as only the ranking of the scores is taken into account. This shows that these metrics are insufficient by themselves, as the visual appearance of a saliency map can change significantly without the ranking of the scores being modified. Secondly, we argue that during the computation of DAUC and IAUC, the model is presented with images that are out of the training distribution which might lead to an unreliable behavior of the model being explained. %First, we show that one can drastically change the visual appearance of an explanation map without changing the pixel ranking, i.e. without changing the DAUC and IAUC values. %We argue that DAUC and IAUC only takes into account the scores ranking and ignore the score values. To complement DAUC/IAUC, we propose new metrics that quantify the sparsity and the calibration of explanation methods, two previously unstudied properties. Finally, we give general remarks about the metrics studied in this paper and discuss how to evaluate them in a user study.

Improve the Interpretability of Attention: A Fast, Accurate, and Interpretable High-Resolution Attention Model

The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model predictions is still highly dubious. The community is still seeking more interpretable strategies for better identifying local active regions that contribute the most to the final decision. To improve the interpretability of existing attention models, we propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-relevant human-interpretable information. The target model is first distilled to have higher-resolution intermediate feature maps. From which, representative features are then grouped based on local pairwise feature similarity, to produce finer-grained, more precise attention maps highlighting task-relevant parts of the input. The obtained attention maps are ranked according to the `active level' of the compound feature, which provides information regarding the important level of the highlighted regions. The proposed model can be easily adapted in a wide variety of modern deep models, where classification is involved. It is also more accurate, faster, and with a smaller memory footprint than usual neural attention modules. Extensive experiments showcase more comprehensive visual explanations compared to the state-of-the-art visualization model across multiple tasks including few-shot classification, person re-identification, fine-grained image classification. The proposed visualization model sheds imperative light on how neural networks `pay their attention' differently in different tasks.