Search

Recently, newly developed Vision-Language Models (VLMs), such as OpenAI's GPT-4o, have emerged, seemingly demonstrating advanced reasoning capabilities across text and image modalities. Yet, the depth of these advances in language-guided perception and abstract reasoning remains underexplored, and it is unclear whether these models can truly live up to their ambitious promises. To assess the progress and identify shortcomings, we enter the wonderland of Bongard problems, a set of classical visual reasoning puzzles that require human-like abilities of pattern recognition and abstract reasoning. While VLMs occasionally succeed in identifying discriminative concepts and solving some of the problems, they frequently falter, failing to understand and reason about visual concepts. Surprisingly, even elementary concepts that may seem trivial to humans, such as simple spirals, pose significant challenges. Moreover, even when asked to explicitly focus on and analyze these concepts, they continue to falter, suggesting not only a lack of understanding of these elementary visual concepts but also an inability to generalize to unseen concepts. These observations underscore the current limitations of VLMs, emphasize that a significant gap remains between human-like visual reasoning and machine cognition, and highlight the ongoing need for innovation in this area.

Time series data is prevalent across numerous fields, necessitating the development of robust and accurate forecasting models. Capturing patterns both within and between temporal and multivariate components is crucial for reliable predictions. We introduce xLSTM-Mixer, a model designed to effectively integrate temporal sequences, joint time-variate information, and multiple perspectives for robust forecasting. Our approach begins with a linear forecast shared across variates, which is then refined by xLSTM blocks. These blocks serve as key elements for modeling the complex dynamics of challenging time series data. xLSTM-Mixer ultimately reconciles two distinct views to produce the final forecast. Our extensive evaluations demonstrate xLSTM-Mixer's superior long-term forecasting performance compared to recent state-of-the-art methods. A thorough model analysis provides further insights into its key components and confirms its robustness and effectiveness. This work contributes to the resurgence of recurrent models in time series forecasting.

Company fundamentals are key to assessing companies' financial and overall success and stability. Forecasting them is important in multiple fields, including investing and econometrics. While statistical and contemporary machine learning methods have been applied to many time series tasks, there is a lack of comparison of these approaches on this particularly challenging data regime. To this end, we try to bridge this gap and thoroughly evaluate the theoretical properties and practical performance of 22 deterministic and probabilistic company fundamentals forecasting models on real company data. We observe that deep learning models provide superior forcasting performance to classical models, in particular when considering uncertainty estimation. To validate the findings, we compare them to human analyst expectations and find that their accuracy is comparable to the automatic forecasts. We further show how these high-quality forecasts can benefit automated stock allocation. We close by presenting possible ways of integrating domain experts to further improve performance and increase reliability., Comment: 24 pages, 9 figures, under review

Most work on causality in machine learning assumes that causal relationships are driven by a constant underlying process. However, the flexibility of agents' actions or tipping points in the environmental process can change the qualitative dynamics of the system. As a result, new causal relationships may emerge, while existing ones change or disappear, resulting in an altered causal graph. To analyze these qualitative changes on the causal graph, we propose the concept of meta-causal states, which groups classical causal models into clusters based on equivalent qualitative behavior and consolidates specific mechanism parameterizations. We demonstrate how meta-causal states can be inferred from observed agent behavior, and discuss potential methods for disentangling these states from unlabeled data. Finally, we direct our analysis towards the application of a dynamical system, showing that meta-causal states can also emerge from inherent system dynamics, and thus constitute more than a context-dependent framework in which mechanisms emerge only as a result of external factors., Comment: 19 pages, 3 figures, 4 tables

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that use mixtures of both logic and neural policies. We empirically demonstrate that BlendRL agents outperform both neural and symbolic baselines in standard Atari environments, and showcase their robustness to environmental changes. Additionally, we analyze the interaction between neural and symbolic policies, illustrating how their hybrid use helps agents overcome each other's limitations., Comment: Preprint

Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and propose Characteristic Interventional Sum-Product Network ($\chi$SPN) that is capable of estimating interventional distributions in presence of random variables drawn from mixed distributions. $\chi$SPN uses characteristic functions in the leaves of an interventional SPN (iSPN) thereby providing a unified view for discrete and continuous random variables through the Fourier-Stieltjes transform of the probability measures. A neural network is used to estimate the parameters of the learned iSPN using the intervened data. Our experiments on 3 synthetic heterogeneous datasets suggest that $\chi$SPN can effectively capture the interventional distributions for both discrete and continuous variables while being expressive and causally adequate. We also show that $\chi$SPN generalize to multiple interventions while being trained only on a single intervention data., Comment: 17 pages, 11 figures. Accepted as poster at UAI (Uncertainty in Artificial Intelligence) 2024

Antiferromagnetic intermetallic compound EuRhGe3 crystalizes in a non-centrosymmetric BaNiSn3-type (I4mm) structure. We studied its pressure-dependent crystal structure by using synchrotron powder x-ray diffraction at room temperature. Our results show a smooth contraction of the unit cell volume by applying pressure while preserving I4mm symmetry. No structural transition was observed up to 35 GPa. By the equation of state fitting analysis, the bulk modulus and its pressure derivative were determined to be 73 (1) GPa and 5.5 (2), respectively. Furthermore, similar to the isostructural EuCoGe3, an anisotropic compression of a and c lattice parameters was observed. Our experimental results show a good agreement with the pressure-dependent structural evolution expected from theoretical calculations below 13 GPa. Reflecting a strong deviation from integer Eu valence, the experimental volume data appear to be smaller than those of DFT calculated values at higher pressures.

Unmanned Aerial Vehicles (UAVs) equipped with high-resolution sensors enable extensive data collection from previously inaccessible areas at a remarkable spatio-temporal scale, promising to revolutionize fields such as precision agriculture and infrastructure inspection. To fully exploit their potential, developing autonomy algorithms for planning and perception is crucial. This dissertation focuses on developing planning and perception algorithms tailored to UAVs used in monitoring applications. In the first part, we address object monitoring and its associated planning challenges. Object monitoring involves continuous observation, tracking, and analysis of specific objects. We tackle the problem of visual reconstruction where the goal is to maximize visual coverage of an object in an unknown environment efficiently. Leveraging shape prediction deep learning models, we optimize planning for quick information gathering. Extending this to multi-UAV systems, we create efficient paths around objects based on reconstructed 3D models, crucial for close-up inspections aimed at detecting changes. Next, we explore inspection scenarios where an object has changed or no prior information is available, focusing on infrastructure inspection. We validate our planning algorithms through real-world experiments and high-fidelity simulations, integrating defect detection seamlessly into the process. In the second part, we shift focus to monitoring entire environments, distinct from object-specific monitoring. Here, the goal is to maximize coverage to understand spatio-temporal changes. We investigate slow-changing environments like vegetative growth estimation and fast-changing environments such as wildfire management. For wildfires, we employ informative path planning to validate and localize fires early, utilizing LSTM networks for enhanced early detection., Comment: 186 pages, 13 tables, 52 figures, Dissertation presented to UMD to fulfill PhD

We study the problem of visual surface inspection of infrastructure for defects using an Unmanned Aerial Vehicle (UAV). We do not assume that the geometric model of the infrastructure is known beforehand. Our planner, termed GATSBI, plans a path in a receding horizon fashion to inspect all points on the surface of the infrastructure. The input to GATSBI consists of a 3D occupancy map created online with 3D pointclouds. Occupied voxels corresponding to the infrastructure in this map are semantically segmented and used to create an infrastructure-only occupancy map. Inspecting an infrastructure voxel requires the UAV to take images from a desired viewing angle and distance. We then create a Generalized Traveling Salesperson Problem (GTSP) instance to cluster candidate viewpoints for inspecting the infrastructure voxels and use an off-the-shelf GTSP solver to find the optimal path for the given instance. As the algorithm sees more parts of the environment over time, it replans the path to inspect uninspected parts of the infrastructure while avoiding obstacles. We evaluate the performance of our algorithm through high-fidelity simulations conducted in AirSim and real-world experiments. We compare the performance of GATSBI with a baseline inspection algorithm where the map is known a priori. Our evaluation reveals that targeting the inspection to only the segmented infrastructure voxels and planning carefully using a GTSP solver leads to a more efficient and thorough inspection than the baseline inspection algorithm., Comment: 10 pages, 12 figures, 2 tables. Submitted to IEEE TAES. arXiv admin note: text overlap with arXiv:2012.04803

Employing Unmanned Aircraft Systems (UAS) beyond visual line of sight (BVLOS) is an endearing and challenging task. While UAS have the potential to significantly enhance today's logistics and emergency response capabilities, unmanned flying objects above the heads of unprotected pedestrians induce similarly significant safety risks. In this work, we make strides towards improved safety and legal compliance in applying UAS in two ways. First, we demonstrate navigation within the Probabilistic Mission Design (ProMis) framework. To this end, our approach translates Probabilistic Mission Landscapes (PML) into a navigation graph and derives a cost from the probability of complying with all underlying constraints. Second, we introduce the clearance, explanation, and optimization (CEO) cycle on top of ProMis by leveraging the declaratively encoded domain knowledge, legal requirements, and safety assertions to guide the mission design process. Based on inaccurate, crowd-sourced map data and a synthetic scenario, we illustrate the application and utility of our methods in UAS navigation.

Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Recent research has attempted to address this issue by using the guidance of pretrained neural agents to encode logic-based policies, allowing for interpretable decisions. A drawback of such approaches is the requirement of large amounts of predefined background knowledge in the form of predicates, limiting its applicability and scalability. In this work, we propose a novel approach, Explanatory Predicate Invention for Learning in Games (EXPIL), that identifies and extracts predicates from a pretrained neural agent, later used in the logic-based agents, reducing the dependency on predefined background knowledge. Our experimental evaluation on various games demonstrate the effectiveness of EXPIL in achieving explainable behavior in logic agents while requiring less background knowledge., Comment: 9 pages, 2 pages references, 8 figures, 3 tables

Advanced Air Mobility (AAM) is a growing field that demands a deep understanding of legal, spatial and temporal concepts in navigation. Hence, any implementation of AAM is forced to deal with the inherent uncertainties of human-inhabited spaces. Enabling growth and innovation requires the creation of a system for safe and robust mission design, i.e., the way we formalize intentions and decide their execution as trajectories for the Unmanned Aerial Vehicle (UAV). Although legal frameworks have emerged to govern urban air spaces, their full integration into the decision process of autonomous agents and operators remains an open task. In this work we present ProMis, a system architecture for probabilistic mission design. It links the data available from various static and dynamic data sources with legal text and operator requirements by following principles of formal verification and probabilistic modeling. Hereby, ProMis enables the combination of low-level perception and high-level rules in AAM to infer validity over the UAV's state-space. To this end, we employ Hybrid Probabilistic Logic Programs (HPLP) as a unifying, intermediate representation between perception and action-taking. Furthermore, we present methods to connect ProMis with crowd-sourced map data by generating HPLP atoms that represent spatial relations in a probabilistic fashion. Our claims of the utility and generality of ProMis are supported by experiments on a diverse set of scenarios and a discussion of the computational demands associated with probabilistic missions.

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually, common belief is that multi-dataset pretraining does not work for time series! Au contraire, we introduce a new self-supervised contrastive pretraining approach to learn one encoding from many unlabeled and diverse time series datasets, so that the single learned representation can then be reused in several target domains for, say, classification. Specifically, we propose the XD-MixUp interpolation method and the Soft Interpolation Contextual Contrasting (SICC) loss. Empirically, this outperforms both supervised training and other self-supervised pretraining methods when finetuning on low-data regimes. This disproves the common belief: We can actually learn from multiple time series datasets, even from 75 at once.

Large-scale, pre-trained neural networks have demonstrated strong capabilities in various tasks, including zero-shot image segmentation. To identify concrete objects in complex scenes, humans instinctively rely on deictic descriptions in natural language, i.e., referring to something depending on the context such as "The object that is on the desk and behind the cup.". However, deep learning approaches cannot reliably interpret such deictic representations due to their lack of reasoning capabilities in complex scenarios. To remedy this issue, we propose DeiSAM -- a combination of large pre-trained neural networks with differentiable logic reasoners -- for deictic promptable segmentation. Given a complex, textual segmentation description, DeiSAM leverages Large Language Models (LLMs) to generate first-order logic rules and performs differentiable forward reasoning on generated scene graphs. Subsequently, DeiSAM segments objects by matching them to the logically inferred image regions. As part of our evaluation, we propose the Deictic Visual Genome (DeiVG) dataset, containing paired visual input and complex, deictic textual prompts. Our empirical results demonstrate that DeiSAM is a substantial improvement over purely data-driven baselines for deictic promptable segmentation., Comment: Preprint

The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for human users to be able to understand a model's learnt concepts and potentially revise false behaviours. To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. This is achieved by retrieving object representations from images and synthesizing relational concepts as lambda-calculus programs. We evaluate the diverse properties of Pix2Code on the challenging reasoning domains, Kandinsky Patterns and CURI, thereby testing its ability to identify compositional visual concepts that generalize to novel data and concept configurations. Particularly, in stark contrast to neural approaches, we show that Pix2Code's representations remain human interpretable and can be easily revised for improved performance.

Structural causal models (SCMs) are a powerful tool for understanding the complex causal relationships that underlie many real-world systems. As these systems grow in size, the number of variables and complexity of interactions between them does, too. Thus, becoming convoluted and difficult to analyze. This is particularly true in the context of machine learning and artificial intelligence, where an ever increasing amount of data demands for new methods to simplify and compress large scale SCM. While methods for marginalizing and abstracting SCM already exist today, they may destroy the causality of the marginalized model. To alleviate this, we introduce the concept of consolidating causal mechanisms to transform large-scale SCM while preserving consistent interventional behaviour. We show consolidation is a powerful method for simplifying SCM, discuss reduction of computational complexity and give a perspective on generalizing abilities of consolidated SCM., Comment: 19 pages, 8 figures

Some argue scale is all what is needed to achieve AI, covering even causal models. We make it clear that large language models (LLMs) cannot be causal and give reason onto why sometimes we might feel otherwise. To this end, we define and exemplify a new subgroup of Structural Causal Model (SCM) that we call meta SCM which encode causal facts about other SCM within their variables. We conjecture that in the cases where LLM succeed in doing causal inference, underlying was a respective meta SCM that exposed correlations between causal facts in natural language on whose data the LLM was ultimately trained. If our hypothesis holds true, then this would imply that LLMs are like parrots in that they simply recite the causal knowledge embedded in the data. Our empirical analysis provides favoring evidence that current LLMs are even weak `causal parrots.', Comment: Published in Transactions in Machine Learning Research (TMLR) (08/2023). Main paper: 17 pages, References: 3 pages, Appendix: 7 pages. Figures: 5 main, 3 appendix. Tables: 3 main

Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on top of an object encoder-decoder backbone. Unfortunately, current SGG methods suffer from an information loss regarding the entities local-level cues during the relation encoding process. To mitigate this, we introduce the Vision rElation TransfOrmer (VETO), consisting of a novel local-level entity relation encoder. We further observe that many existing SGG methods claim to be unbiased, but are still biased towards either head or tail classes. To overcome this bias, we introduce a Mutually Exclusive ExperT (MEET) learning strategy that captures important relation features without bias towards head or tail classes. Experimental results on the VG and GQA datasets demonstrate that VETO + MEET boosts the predictive performance by up to 47 percentage over the state of the art while being 10 times smaller., Comment: Accepted for publication in ICCV 2023

Next-Best View (NBV) planning is a long-standing problem of determining where to obtain the next best view of an object from, by a robot that is viewing the object. There are a number of methods for choosing NBV based on the observed part of the object. In this paper, we investigate how predicting the unobserved part helps with the efficiency of reconstructing the object. We present, Multi-Agent Prediction-Guided NBV (MAP-NBV), a decentralized coordination algorithm for active 3D reconstruction with multi-agent systems. Prediction-based approaches have shown great improvement in active perception tasks by learning the cues about structures in the environment from data. However, these methods primarily focus on single-agent systems. We design a decentralized next-best-view approach that utilizes geometric measures over the predictions and jointly optimizes the information gain and control effort for efficient collaborative 3D reconstruction of the object. Our method achieves 19% improvement over the non-predictive multi-agent approach in simulations using AirSim and ShapeNet. We make our code publicly available through our project website: http://raaslab.org/projects/MAPNBV/., Comment: 8 pages, 7 figures, 1 table. Submitted to IROS 2024

Visual reasoning is essential for building intelligent agents that understand the world and perform problem-solving beyond perception. Differentiable forward reasoning has been developed to integrate reasoning with gradient-based machine learning paradigms. However, due to the memory intensity, most existing approaches do not bring the best of the expressivity of first-order logic, excluding a crucial ability to solve abstract visual reasoning, where agents need to perform reasoning by using analogies on abstract concepts in different scenarios. To overcome this problem, we propose NEUro-symbolic Message-pAssiNg reasoNer (NEUMANN), which is a graph-based differentiable forward reasoner, passing messages in a memory-efficient manner and handling structured programs with functors. Moreover, we propose a computationally-efficient structure learning algorithm to perform explanatory program induction on complex visual scenes. To evaluate, in addition to conventional visual reasoning tasks, we propose a new task, visual reasoning behind-the-scenes, where agents need to learn abstract programs and then answer queries by imagining scenes that are not observed. We empirically demonstrate that NEUMANN solves visual reasoning tasks efficiently, outperforming neural, symbolic, and neuro-symbolic baselines., Comment: under review

The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic Programming Languages (DPPLs) have been developed for probabilistic logic programming to be carried out via the probability estimations of deep neural networks. However, recent SOTA DPPL approaches allow only for limited conditional probabilistic queries and do not offer the power of true joint probability estimation. In our work, we propose an easy integration of tractable probabilistic inference within a DPPL. To this end, we introduce SLASH, a novel DPPL that consists of Neural-Probabilistic Predicates (NPPs) and a logic program, united via answer set programming (ASP). NPPs are a novel design principle allowing for combining all deep model types and combinations thereof to be represented as a single probabilistic predicate. In this context, we introduce a novel $+/-$ notation for answering various types of probabilistic queries by adjusting the atom notations of a predicate. To scale well, we show how to prune the stochastically insignificant parts of the (ground) program, speeding up reasoning without sacrificing the predictive performance. We evaluate SLASH on a variety of different tasks, including the benchmark task of MNIST addition and Visual Question Answering (VQA)., Comment: 37 pages, 14 figures

Despite the successes of recent developments in visual AI, different shortcomings still exist; from missing exact logical reasoning, to abstract generalization abilities, to understanding complex and noisy scenes. Unfortunately, existing benchmarks, were not designed to capture more than a few of these aspects. Whereas deep learning datasets focus on visually complex data but simple visual reasoning tasks, inductive logic datasets involve complex logical learning tasks, however, lack the visual component. To address this, we propose the diagnostic visual logical learning dataset, V-LoL, that seamlessly combines visual and logical challenges. Notably, we introduce the first instantiation of V-LoL, V-LoL-Train, - a visual rendition of a classic benchmark in symbolic AI, the Michalski train problem. By incorporating intricate visual scenes and flexible logical reasoning tasks within a versatile framework, V-LoL-Train provides a platform for investigating a wide range of visual logical learning challenges. We evaluate a variety of AI systems including traditional symbolic AI, neural AI, as well as neuro-symbolic AI. Our evaluations demonstrate that even SOTA AI faces difficulties in dealing with visual logical learning challenges, highlighting unique advantages and limitations of each methodology. Overall, V-LoL opens up new avenues for understanding and enhancing current abilities in visual logical learning for AI systems.

The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's behaviour, especially when working on the image level. Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE). NUDGE exploits trained neural network-based agents to guide the search of candidate-weighted logic rules, then uses differentiable logic to train the logic agents. Our experimental evaluation demonstrates that NUDGE agents can induce interpretable and explainable policies while outperforming purely neural ones and showing good flexibility to environments of different initial states and problem sizes., Comment: 9 main pages + appendix (19 in total)

Prediction-based active perception has shown the potential to improve the navigation efficiency and safety of the robot by anticipating the uncertainty in the unknown environment. The existing works for 3D shape prediction make an implicit assumption about the partial observations and therefore cannot be used for real-world planning and do not consider the control effort for next-best-view planning. We present Pred-NBV, a realistic object shape reconstruction method consisting of PoinTr-C, an enhanced 3D prediction model trained on the ShapeNet dataset, and an information and control effort-based next-best-view method to address these issues. Pred-NBV shows an improvement of 25.46% in object coverage over the traditional methods in the AirSim simulator, and performs better shape completion than PoinTr, the state-of-the-art shape completion model, even on real data obtained from a Velodyne 3D LiDAR mounted on DJI M600 Pro., Comment: 6 pages, 4 figures, 2 tables. Accepted to IROS 2023

Material deformation and failure under impact loading is a subject of active investigation in space science and often requires very specialized equipment for testing. In this work, we present the design, operational analysis and application of a low-velocity ($\sim 100$ m/s) projectile impact framework for evaluating the deformation and failure of space-grade materials. The system is designed to be modular and easily adaptable to various test geometries, while enabling accurate quantitative evaluation of plastic flow. Using coupled numerical methods and experimental techniques, we first establish an operating procedure for the system. Following this, its performance in two complementary impact configurations is demonstrated using numerical and experimental analysis. In the first, a Taylor impact test is performed for predicting the deformed shape of a cylindrical projectile impinging on a rigid substrate. In the second, deformation of a plate struck by a rigid projectile is evaluated. In both cases, physics-based models are used to interpret the resulting fields. We present a discussion of how the system may be used both for material property estimation (e.g., dynamic yield strength) as well as for failure evaluation (e.g., perforation and fracture) in the same projectile impact configuration.

We report on the pressure evolution of the electronic and crystal structures of the noncentrosymmetric antiferromagnet EuCoGe3. Using a diamond anvil cell, we performed high pressure fluorescence detected near-edge x-ray absorption spectroscopy at the Eu L3, Co K, and Ge K edges and synchrotron powder x-ray diffraction. In the Eu L3 spectrum, both divalent and trivalent Eu peaks are observed from the lowest pressure measurement (~2 GPa). By increasing pressure, the relative intensity of the trivalent Eu peak increases, and an average Eu valence continuously increases from 2.2 at 2 GPa to 2.31 at~50 GPa. On the other hand, no discernible changes are observed in the Co K and Ge K spectra as a function of pressure. With the increase in pressure, lattice parameters continuously decrease without changing I4mm symmetry. Our study revealed a robust divalent Eu state and an unchanged crystal symmetry of EuCoGe3 against pressure., Comment: Accepted in PRB https://journals.aps.org/prb/accepted/b2073O6fL9e1ca40307905b1de5bf05de12d8fc1a

Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems. As in any other growing subfield, patience seems to be a virtue since significant progress on integrating notions from both fields takes time, yet, major challenges such as the lack of ground truth benchmarks or a unified perspective on classical problems such as computer vision seem to hinder the momentum of the research movement. This present work exemplifies how the Pearl Causal Hierarchy (PCH) can be understood on image data by providing insights on several intricacies but also challenges that naturally arise when applying key concepts from Pearlian causality to the study of image data., Comment: Main paper: 9 pages, References: 2 pages. Main paper: 7 figures