Seminars

Synthetic face datasets are increasingly used to overcome the limitations of real-world biometric data, including privacy concerns, demographic imbalance, and high collection costs. However, many existing methods lack fine-grained control over identity attributes and fail to produce paired, identity-consistent images under structured capture conditions. In this talk, I will present FLUXSynID, a framework for generating high-resolution synthetic face datasets with user-defined identity attribute distributions and paired document-style and trusted live capture images. The dataset generated using FLUXSynID shows improved alignment with real-world identity distributions and greater diversity compared to prior work. I will also discuss how FLUXSynID’s dataset and generation tools can support research in face recognition and morphing attack detection (MAD), enhancing model robustness in both academic and practical applications.

Trends in NeuroAI is a reading group hosted by the MedARC Neuroimaging & AI lab (https://medarc.ai/fmri). Title: Brain-optimized inference improves reconstructions of fMRI brain activity Abstract: The release of large datasets and developments in AI have led to dramatic improvements in decoding methods that reconstruct seen images from human brain activity. We evaluate the prospect of further improving recent decoding methods by optimizing for consistency between reconstructions and brain activity during inference. We sample seed reconstructions from a base decoding method, then iteratively refine these reconstructions using a brain-optimized encoding model that maps images to brain activity. At each iteration, we sample a small library of images from an image distribution (a diffusion model) conditioned on a seed reconstruction from the previous iteration. We select those that best approximate the measured brain activity when passed through our encoding model, and use these images for structural guidance during the generation of the small library in the next iteration. We reduce the stochasticity of the image distribution at each iteration, and stop when a criterion on the "width" of the image distribution is met. We show that when this process is applied to recent decoding methods, it outperforms the base decoding method as measured by human raters, a variety of image feature metrics, and alignment to brain activity. These results demonstrate that reconstruction quality can be significantly improved by explicitly aligning decoding distributions to brain activity distributions, even when the seed reconstruction is output from a state-of-the-art decoding algorithm. Interestingly, the rate of refinement varies systematically across visual cortex, with earlier visual areas generally converging more slowly and preferring narrower image distributions, relative to higher-level brain areas. Brain-optimized inference thus offers a succinct and novel method for improving reconstructions and exploring the diversity of representations across visual brain areas. Speaker: Reese Kneeland is a Ph.D. student at the University of Minnesota working in the Naselaris lab. Paper link: https://arxiv.org/abs/2312.07705

Trends in NeuroAI is a reading group hosted by the MedARC Neuroimaging & AI lab (https://medarc.ai/fmri). This will be an informal journal club presentation, we do not have an author of the paper joining us. Title: Brain decoding: toward real-time reconstruction of visual perception Abstract: In the past five years, the use of generative and foundational AI systems has greatly improved the decoding of brain activity. Visual perception, in particular, can now be decoded from functional Magnetic Resonance Imaging (fMRI) with remarkable fidelity. This neuroimaging technique, however, suffers from a limited temporal resolution (≈0.5 Hz) and thus fundamentally constrains its real-time usage. Here, we propose an alternative approach based on magnetoencephalography (MEG), a neuroimaging device capable of measuring brain activity with high temporal resolution (≈5,000 Hz). For this, we develop an MEG decoding model trained with both contrastive and regression objectives and consisting of three modules: i) pretrained embeddings obtained from the image, ii) an MEG module trained end-to-end and iii) a pretrained image generator. Our results are threefold: Firstly, our MEG decoder shows a 7X improvement of image-retrieval over classic linear decoders. Second, late brain responses to images are best decoded with DINOv2, a recent foundational image model. Third, image retrievals and generations both suggest that MEG signals primarily contain high-level visual features, whereas the same approach applied to 7T fMRI also recovers low-level features. Overall, these results provide an important step towards the decoding - in real time - of the visual processes continuously unfolding within the human brain. Speaker: Dr. Paul Scotti (Stability AI, MedARC) Paper link: https://arxiv.org/abs/2310.19812

Ophthalmology is ideally placed to benefit from recent advances in artificial intelligence. It is a highly image-based specialty and provides unique access to the microvascular circulation and the central nervous system. This talk will demonstrate diverse applications of machine learning and deep learning techniques in ophthalmology, including in age-related macular degeneration (AMD), the leading cause of blindness in industrialized countries, and cataract, the leading cause of blindness worldwide. This will include deep learning approaches to automated diagnosis, quantitative severity classification, and prognostic prediction of disease progression, both from images alone and accompanied by demographic and genetic information. The approaches discussed will include deep feature extraction, label transfer, and multi-modal, multi-task training. Cluster analysis, an unsupervised machine learning approach to data classification, will be demonstrated by its application to geographic atrophy in AMD, including exploration of genotype-phenotype relationships. Finally, mediation analysis will be discussed, with the aim of dissecting complex relationships between AMD disease features, genotype, and progression.

With the increasing use of automated face recognition (AFR) technologies, it is important to consider whether these systems not only perform accurately, but also equitability or without “bias”. Despite rising public, media, and scientific attention to this issue, the sources of bias in AFR are not fully understood. This talk will explore how human cognitive biases may impact our assessments of performance differentials in AFR systems and our subsequent use of those systems to make decisions. We’ll also show how, if we adjust our definition of what a “biased” AFR algorithm looks like, we may be able to create algorithms that optimize the performance of a human+algorithm team, not simply the algorithm itself.

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching – and sometimes even surpassing – human accuracy on a variety of visual recognition tasks. In this talk, however, I will show that these neural networks and their recent extensions exhibit a limited ability to solve seemingly simple visual reasoning problems involving incremental grouping, similarity, and spatial relation judgments. Our group has developed a recurrent network model of classical and extra-classical receptive field circuits that is constrained by the anatomy and physiology of the visual cortex. The model was shown to account for diverse visual illusions providing computational evidence for a novel canonical circuit that is shared across visual modalities. I will show that this computational neuroscience model can be turned into a modern end-to-end trainable deep recurrent network architecture that addresses some of the shortcomings exhibited by state-of-the-art feedforward networks for solving complex visual reasoning tasks. This suggests that neuroscience may contribute powerful new ideas and approaches to computer science and artificial intelligence.

With the increasing development of automatic systems and artificial intelligence, face recognition is becoming increasingly important in forensic and civil contexts. However, face recognition has yet to be thoroughly empirically studied to provide an adequate scientific and legal framework for investigative and court purposes. This observation sets the foundation for the research. We focus on issues related to face images and the use of automatic systems. Our objective is to validate a likelihood ratio computation methodology for interpreting comparison scores from automatic face recognition systems (score-based likelihood ratio, SLR). We collected three types of traces: portraits (ID), video surveillance footage recorded by ATM and by a wide-angle camera (CCTV). The performance of two automatic face recognition systems is compared: the commercial IDEMIA Morphoface (MFE) system and the open source FaceNet algorithm.

3D Morphable Models are my favorite class of generative models and are commonly used to model faces. They are typically applied to ill-posed problems such as 3D reconstruction from 2D data. I'll start my presentation with an introduction into 3D Morphable Models and show what they are capable of doing. I'll then focus on our recent finding, the Identity-Expression Ambiguity: We demonstrate that non-orthogonality of the variation in identity and expression can cause identity-expression ambiguity in 3D Morphable Models, and that in practice expression and identity are far from orthogonal and can explain each other surprisingly well. Whilst previously reported ambiguities only arise in an inverse rendering setting, identity-expression ambiguity emerges in the 3D shape generation process itself. The goal of this presentation is to demonstrate the ambiguity and discuss its potential consequences in a computer vision setting as well as for understanding face perception mechanisms in the human brain.

Building conceptual abstractions from sensory information and then reasoning about them is central to human intelligence. Abstract reasoning both relies on, and is facilitated by, our ability to make analogies about concepts from known domains to novel domains. Structure Mapping Theory of human analogical reasoning posits that analogical mappings rely on (higher-order) relations and not on the sensory content of the domain. This enables humans to reason systematically about novel domains, a problem with which machine learning (ML) models tend to struggle. We introduce a two-stage neural net framework, which we label Neural Structure Mapping (NSM), to learn visual analogies from Raven's Progressive Matrices, an abstract visual reasoning test of fluid intelligence. Our framework uses (1) a multi-task visual relationship encoder to extract constituent concepts from raw visual input in the source domain, and (2) a neural module net analogy inference engine to reason compositionally about the inferred relation in the target domain. Our NSM approach (a) isolates the relational structure from the source domain with high accuracy, and (b) successfully utilizes this structure for analogical reasoning in the target domain.

In this talk, Jonathan aims to frame the current challenges of explainability and understanding in ML-driven approaches to image processing, and their potential solution through explicit inference techniques.

Many tasks that are easy for humans are difficult for machines. In particular, while humans excel at tasks that require generalising across problems, machine systems notably struggle. One such task that has received a good amount of attention is the Synthetic Visual Reasoning Test (SVRT). The SVRT consists of a range of problems where simple visual stimuli must be categorised into one of two categories based on an unknown rule that must be induced. Conventional machine learning approaches perform well only when trained to categorise based on a single rule and are unable to generalise without extensive additional training to tasks with any additional rules. Multiple theories of higher-level cognition posit that humans solve such tasks using structured relational representations. Specifically, people learn rules based on structured representations that generalise to novel instances quickly and easily. We believe it is possible to model this approach in a single system which learns all the required relational representations from scratch and performs tasks such as SVRT in a single run. Here, we present a system which expands the DORA/LISA architecture and augments the existing model with principally novel components, namely a) visual reasoning based on the established theories of recognition by components; b) the process of learning complex relational representations by synthesis (in addition to learning by analysis). The proposed augmented model matches human behaviour on SVRT problems. Moreover, the proposed system stands as perhaps a more realistic account of human cognition, wherein rather than using tools that has been shown successful in the machine learning field to inform psychological theorising, we use established psychological theories to inform developing a machine system.

A panel discussion on "What might we still require to achieve AGI?", a set of Reinforcement Learning and Computer Vision domain tuts and a talk from George Konidaris

There has been a recent surge of interest in the question of whether and how deep learning algorithms might be capable of abstract reasoning, much of which has centered around datasets based on Raven’s Progressive Matrices (RPM), a visual analogy problem set commonly employed to assess fluid intelligence. This has led to the development of algorithms that are capable of solving RPM-like problems directly from pixel-level inputs. However, these algorithms require extensive direct training on analogy problems, and typically generalize poorly to novel problem types. This is in stark contrast to human reasoners, who are capable of solving RPM and other analogy problems zero-shot — that is, with no direct training on those problems. Indeed, it’s this capacity for zero-shot reasoning about novel problem types, i.e. fluid intelligence, that RPM was originally designed to measure. I will present some results from our recent efforts to model this capacity for zero-shot reasoning, based on an extension of a recently proposed approach to analogical mapping we refer to as Probabilistic Analogical Mapping (PAM). Our RPM model uses deep learning to extract attributed graph representations from pixel-level inputs, and then performs alignment of objects between source and target analogs using gradient descent to optimize a graph-matching objective. This extended version of PAM features a number of new capabilities that underscore the flexibility of the overall approach, including 1) the capacity to discover solutions that emphasize either object similarity or relation similarity, based on the demands of a given problem, 2) the ability to extract a schema representing the overall abstract pattern that characterizes a problem, and 3) the ability to directly infer the answer to a problem, rather than relying on a set of possible answer choices. This work suggests that PAM is a promising framework for modeling human zero-shot reasoning.

Even young children seem to have an early understanding of the world around them, and the people in it. Before children can reliably say "ball", "wall", or "Saul", they expect balls to not go through walls, and for Saul to go right for a ball (if there's no wall). What is the formal conceptual structure underlying this commonsense reasoning about objects and agents? I will raise several possibilities for models underlying core intuitive physics as a way of talking about models of core knowledge and intuitive theories more generally. In particular, I will present some recent ML work trying to capture early expectations about object solidly, cohesion, and permanence, that relies on a rough-derendering approach.

A key component of humans' striking creativity in solving problems is our ability to construct novel descriptions to help us characterize novel categories. Bongard problems, which challenge the problem solver to come up with a rule for distinguishing visual scenes that fall into two categories, provide an elegant test of this ability. Bongard problems are challenging for both human and machine category learners because only a handful of example scenes are presented for each category, and they often require the open-ended creation of new descriptions. A new sub-type of Bongard problem called Physical Bongard Problems (PBPs) is introduced, which require solvers to perceive and predict the physical spatial dynamics implicit in the depicted scenes. The PATHS (Perceiving And Testing Hypotheses on Structures) computational model which can solve many PBPs is presented, and compared to human performance on the same problems. PATHS and humans are similarly affected by the ordering of scenes within a PBP, with spatially and temporally juxtaposed scenes promoting category learning when they are similar and belong to different categories, or dissimilar and belong to the same category. The core theoretical commitments of PATHS which we believe to also exemplify human open-ended category learning are a) the continual perception of new scene descriptions over the course of category learning; b) the context-dependent nature of that perceptual process, in which the scenes establish the context for one another; c) hypothesis construction by combining descriptions into logical expressions; and d) bi-directional interactions between perceiving new aspects of scenes and constructing hypotheses for the rule that distinguishes categories.

Climate change is one of our generation's greatest challenges, with increasingly severe consequences on global ecosystems and populations. Machine Learning has the potential to address many important challenges in climate change, from both mitigation (reducing its extent) and adaptation (preparing for unavoidable consequences) aspects. To present the extent of these opportunities, I will describe some of the projects that I am involved in, spanning from generative model to computer vision and natural language processing. There are many opportunities for fundamental innovation in this field, advancing the state-of-the-art in Machine Learning while ensuring that this fundamental progress translates into positive real-world impact.

While meta-learning algorithms are often viewed as algorithms that learn to learn, an alternative viewpoint frames meta-learning as inferring a hidden task variable from experience consisting of observations and rewards. From this perspective, learning to learn is learning to infer. This viewpoint can be useful in solving problems in meta-RL, which I’ll demonstrate through two examples: (1) enabling off-policy meta-learning, and (2) performing efficient meta-RL from image observations. I’ll also discuss how this perspective leads to an algorithm for few-shot image segmentation.

Deep learning is an emerging computational approach inspired by the human brain’s neural connectivity that has transformed machine-based image analysis. By using histopathology as a model of an expert-level pattern recognition exercise, we explore the ability for humans to teach machines to learn and mimic image-recognition and decision making. Moreover, these models also allow exploration into the ability for computers to independently learn salient histological patterns and complex ontological relationships that parallel biological and expert knowledge without the need for explicit direction or supervision. Deciphering the overlap between human and unsupervised machine reasoning may aid in eliminating biases and improving automation and accountability for artificial intelligence-assisted vision tasks and decision-making. Aleksandar Ivanov Title: