Viktoriia Sharmanska

Michail Christos Doukas, Evangelos Ververas, Viktoriia Sharmanska et al.

We present Free-HeadGAN, a person-generic neural talking head synthesis system. We show that modeling faces with sparse 3D facial landmarks are sufficient for achieving state-of-the-art generative performance, without relying on strong statistical priors of the face, such as 3D Morphable Models. Apart from 3D pose and facial expressions, our method is capable of fully transferring the eye gaze, from a driving actor to a source identity. Our complete pipeline consists of three components: a canonical 3D key-point estimator that regresses 3D pose and expression-related deformations, a gaze estimation network and a generator that is built upon the architecture of HeadGAN. We further experiment with an extension of our generator to accommodate few-shot learning using an attention mechanism, in case more than one source images are available. Compared to the latest models for reenactment and motion transfer, our system achieves higher photo-realism combined with superior identity preservation, while offering explicit gaze control.

Myles Bartlett, Sara Romiti, Viktoriia Sharmanska et al.

We propose Okapi, a simple, efficient, and general method for robust semi-supervised learning based on online statistical matching. Our method uses a nearest-neighbours-based matching procedure to generate cross-domain views for a consistency loss, while eliminating statistical outliers. In order to perform the online matching in a runtime- and memory-efficient way, we draw upon the self-supervised literature and combine a memory bank with a slow-moving momentum encoder. The consistency loss is applied within the feature space, rather than on the predictive distribution, making the method agnostic to both the modality and the task in question. We experiment on the WILDS 2.0 datasets Sagawa et al., which significantly expands the range of modalities, applications, and shifts available for studying and benchmarking real-world unsupervised adaptation. Contrary to Sagawa et al., we show that it is in fact possible to leverage additional unlabelled data to improve upon empirical risk minimisation (ERM) results with the right method. Our method outperforms the baseline methods in terms of out-of-distribution (OOD) generalisation on the iWildCam (a multi-class classification task) and PovertyMap (a regression task) image datasets as well as the CivilComments (a binary classification task) text dataset. Furthermore, from a qualitative perspective, we show the matches obtained from the learned encoder are strongly semantically related. Code for our paper is publicly available at https://github.com/wearepal/okapi/.

Sara Romiti, Christopher Inskip, Viktoriia Sharmanska et al.

Machine learning classifiers are typically trained to minimise the average error across a dataset. Unfortunately, in practice, this process often exploits spurious correlations caused by subgroup imbalance within the training data, resulting in high average performance but highly variable performance across subgroups. Recent work to address this problem proposes model patching with CAMEL. This previous approach uses generative adversarial networks to perform intra-class inter-subgroup data augmentations, requiring (a) the training of a number of computationally expensive models and (b) sufficient quality of model's synthetic outputs for the given domain. In this work, we propose RealPatch, a framework for simpler, faster, and more data-efficient data augmentation based on statistical matching. Our framework performs model patching by augmenting a dataset with real samples, mitigating the need to train generative models for the target task. We demonstrate the effectiveness of RealPatch on three benchmark datasets, CelebA, Waterbirds and a subset of iWildCam, showing improvements in worst-case subgroup performance and in subgroup performance gap in binary classification. Furthermore, we conduct experiments with the imSitu dataset with 211 classes, a setting where generative model-based patching such as CAMEL is impractical. We show that RealPatch can successfully eliminate dataset leakage while reducing model leakage and maintaining high utility. The code for RealPatch can be found at https://github.com/wearepal/RealPatch.

Tetiana Martyniuk, Orest Kupyn, Yana Kurliak et al.

We present DAD-3DHeads, a dense and diverse large-scale dataset, and a robust model for 3D Dense Head Alignment in the wild. It contains annotations of over 3.5K landmarks that accurately represent 3D head shape compared to the ground-truth scans. The data-driven model, DAD-3DNet, trained on our dataset, learns shape, expression, and pose parameters, and performs 3D reconstruction of a FLAME mesh. The model also incorporates a landmark prediction branch to take advantage of rich supervision and co-training of multiple related tasks. Experimentally, DAD-3DNet outperforms or is comparable to the state-of-the-art models in (i) 3D Head Pose Estimation on AFLW2000-3D and BIWI, (ii) 3D Face Shape Reconstruction on NoW and Feng, and (iii) 3D Dense Head Alignment and 3D Landmarks Estimation on DAD-3DHeads dataset. Finally, the diversity of DAD-3DHeads in camera angles, facial expressions, and occlusions enables a benchmark to study in-the-wild generalization and robustness to distribution shifts. The dataset webpage is https://p.farm/research/dad-3dheads.

Thomas Kehrenberg, Myles Bartlett, Viktoriia Sharmanska et al.

When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate or non-deliberate censorship, and other problems during data collection and curation, the labeled training set might exhibit a systematic shortage of data for certain groups. We investigate a scenario in which the absence of certain data is linked to the second level of a two-level hierarchy in the data. Inspired by the idea of protected groups from algorithmic fairness, we refer to the partitions carved by this second level as "subgroups"; we refer to combinations of subgroups and classes, or leaves of the hierarchy, as "sources". To characterize the problem, we introduce the concept of classes with incomplete subgroup support. The representational bias in the training set can give rise to spurious correlations between the classes and the subgroups which render standard classification models ungeneralizable to unseen sources. To overcome this bias, we make use of an additional, diverse but unlabeled dataset, called the "deployment set", to learn a representation that is invariant to subgroup. This is done by adversarially matching the support of the training and deployment sets in representation space. In order to learn the desired invariance, it is paramount that the sets of samples observed by the discriminator are balanced by class; this is easily achieved for the training set, but requires using semi-supervised clustering for the deployment set. We demonstrate the effectiveness of our method with experiments on several datasets and variants of the problem.

Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with full, or sufficiently large overlap across tasks, i.e., each input sample is annotated for all, or most of the tasks. However, collecting such annotations is prohibitive in many real applications, and cannot benefit from datasets available for individual tasks. In this work, we challenge this setup and show that MTL can be successful with classification tasks with little, or non-overlapping annotations, or when there is big discrepancy in the size of labeled data per task. We explore task-relatedness for co-annotation and co-training, and propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching. To demonstrate the general applicability of our method, we conducted diverse case studies in the domains of affective computing, face recognition, species recognition, and shopping item classification using nine datasets. Our large-scale study of affective tasks for basic expression recognition and facial action unit detection illustrates that our approach is network agnostic and brings large performance improvements compared to the state-of-the-art in both tasks and across all studied databases. In all case studies, we show that co-training via task-relatedness is advantageous and prevents negative transfer (which occurs when MT model's performance is worse than that of at least one single-task model).

Leonidas Gee, Wing Yan Li, Viktoriia Sharmanska et al.

The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to runtime, making them ill-suited for online (real-time) inference, where a prediction is made on any new input as it comes in. We introduce the $\textbf{Visual Word Tokenizer}$ (VWT), a training-free method for reducing power costs while retaining performance and runtime. The VWT groups visual subwords (image patches) that are frequently used into visual words while infrequent ones remain intact. To do so, $\textit{intra}$-image or $\textit{inter}$-image statistics are leveraged to identify similar visual concepts for sequence compression. Experimentally, we demonstrate a reduction in wattage of up to 25% with only a 20% increase in runtime at most. Comparative approaches of 8-bit quantization and token merging achieve a lower or similar power efficiency but exact a higher toll on runtime (up to 100% or more). Our results indicate that VWTs are well-suited for efficient online inference with a marginal compromise on performance.

Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou

Multi-Task Learning has emerged as a methodology in which multiple tasks are jointly learned by a shared learning algorithm, such as a DNN. MTL is based on the assumption that the tasks under consideration are related; therefore it exploits shared knowledge for improving performance on each individual task. Tasks are generally considered to be homogeneous, i.e., to refer to the same type of problem. Moreover, MTL is usually based on ground truth annotations with full, or partial overlap across tasks. In this work, we deal with heterogeneous MTL, simultaneously addressing detection, classification & regression problems. We explore task-relatedness as a means for co-training, in a weakly-supervised way, tasks that contain little, or even non-overlapping annotations. Task-relatedness is introduced in MTL, either explicitly through prior expert knowledge, or through data-driven studies. We propose a novel distribution matching approach, in which knowledge exchange is enabled between tasks, via matching of their predictions' distributions. Based on this approach, we build FaceBehaviorNet, the first framework for large-scale face analysis, by jointly learning all facial behavior tasks. We develop case studies for: i) continuous affect estimation, action unit detection, basic emotion recognition; ii) attribute detection, face identification. We illustrate that co-training via task relatedness alleviates negative transfer. Since FaceBehaviorNet learns features that encapsulate all aspects of facial behavior, we conduct zero-/few-shot learning to perform tasks beyond the ones that it has been trained for, such as compound emotion recognition. By conducting a very large experimental study, utilizing 10 databases, we illustrate that our approach outperforms, by large margins, the state-of-the-art in all tasks and in all databases, even in these which have not been used in its training.

Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia Sharmanska et al.

Over the past years, a substantial amount of work has been done on the problem of facial reenactment, with the solutions coming mainly from the graphics community. Head reenactment is an even more challenging task, which aims at transferring not only the facial expression, but also the entire head pose from a source person to a target. Current approaches either train person-specific systems, or use facial landmarks to model human heads, a representation that might transfer unwanted identity attributes from the source to the target. We propose head2headFS, a novel easily adaptable pipeline for head reenactment. We condition synthesis of the target person on dense 3D face shape information from the source, which enables high quality expression and pose transfer. Our video-based rendering network is fine-tuned under a few-shot learning strategy, using only a few samples. This allows for fast adaptation of a generic generator trained on a multiple-person dataset, into a person-specific one.

Michail Christos Doukas, Stefanos Zafeiriou, Viktoriia Sharmanska

Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results. However, most of them either perform poorly in terms of photo-realism, or fail to meet the identity preservation problem, or do not fully transfer the driving pose and expression. We propose HeadGAN, a novel system that conditions synthesis on 3D face representations, which can be extracted from any driving video and adapted to the facial geometry of any reference image, disentangling identity from expression. We further improve mouth movements, by utilising audio features as a complementary input. The 3D face representation enables HeadGAN to be further used as an efficient method for compression and reconstruction and a tool for expression and pose editing.

Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia Sharmanska et al.

Facial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence. We leverage the 3D geometry of faces and Generative Adversarial Networks (GANs) to design a novel deep learning architecture for the task of facial and head reenactment. Our method is different to purely 3D model-based approaches, or recent image-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames. We manage to capture the complex non-rigid facial motion from the driving monocular performances and synthesise temporally consistent videos, with the aid of a sequential Generator and an ad-hoc Dynamics Discriminator network. We conduct a comprehensive set of quantitative and qualitative tests and demonstrate experimentally that our proposed method can successfully transfer facial expressions, head pose and eye gaze from a source video to a target subject, in a photo-realistic and faithful fashion, better than other state-of-the-art methods. Most importantly, our system performs end-to-end reenactment in nearly real-time speed (18 fps).

Viktoriia Sharmanska, Lisa Anne Hendricks, Trevor Darrell et al.

Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better represented in the training data. This happens because of the generalization that classifiers have to make. It is simpler to fit the majority groups as this fit is more important to overall error. We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened, minorities become majorities and vice versa. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples. We experiment with the equalized odds bias measure on tabular data as well as image data (CelebA and Diversity in Faces datasets). Contrastive examples allow us to expose correlations between group membership and other seemingly neutral features. Whenever a causal graph is available, we can put those contrastive examples in the perspective of counterfactuals.

Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou

Automatic facial behavior analysis has a long history of studies in the intersection of computer vision, physiology and psychology. However it is only recently, with the collection of large-scale datasets and powerful machine learning methods such as deep neural networks, that automatic facial behavior analysis started to thrive. Three of its iconic tasks are automatic recognition of basic expressions (e.g. happy, sad, surprised), estimation of continuous emotions (e.g., valence and arousal), and detection of facial action units (activations of e.g. upper/inner eyebrows, nose wrinkles). Up until now these tasks have been mostly studied independently collecting a dataset for the task. We present the first and the largest study of all facial behaviour tasks learned jointly in a single multi-task, multi-domain and multi-label network, which we call FaceBehaviorNet. For this we utilize all publicly available datasets in the community (around 5M images) that study facial behaviour tasks in-the-wild. We demonstrate that training jointly an end-to-end network for all tasks has consistently better performance than training each of the single-task networks. Furthermore, we propose two simple strategies for coupling the tasks during training, co-annotation and distribution matching, and show the advantages of this approach. Finally we show that FaceBehaviorNet has learned features that encapsulate all aspects of facial behaviour, and can be successfully applied to perform tasks (compound emotion recognition) beyond the ones that it has been trained in a zero- and few-shot learning setting.

Michail C. Doukas, Viktoriia Sharmanska, Stefanos Zafeiriou

Despite remarkable success in image-to-image translation that celebrates the advancements of generative adversarial networks (GANs), very limited attempts are known for video domain translation. We study the task of video-to-video translation in the context of visual speech generation, where the goal is to transform an input video of any spoken word to an output video of a different word. This is a multi-domain translation, where each word forms a domain of videos uttering this word. Adaptation of the state-of-the-art image-to-image translation model (StarGAN) to this setting falls short with a large vocabulary size. Instead we propose to use character encodings of the words and design a novel character-based GANs architecture for video-to-video translation called Visual Speech GAN (ViSpGAN). We are the first to demonstrate video-to-video translation with a vocabulary of 500 words.

Novi Quadrianto, Viktoriia Sharmanska, Oliver Thomas

Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may include photographs. One promising direction to achieve fairness is by learning data representations that remove the semantics of protected characteristics, and are therefore able to mitigate unfair outcomes. All available models however learn latent embeddings which comes at the cost of being uninterpretable. We propose to cast this problem as data-to-data translation, i.e. learning a mapping from an input domain to a fair target domain, where a fairness definition is being enforced. Here the data domain can be images, or any tabular data representation. This task would be straightforward if we had fair target data available, but this is not the case. To overcome this, we learn a highly unconstrained mapping by exploiting statistics of residuals - the difference between input data and its translated version - and the protected characteristics. When applied to the CelebA dataset of face images with gender attribute as the protected characteristic, our model enforces equality of opportunity by adjusting the eyes and lips regions. Intriguingly, on the same dataset we arrive at similar conclusions when using semantic attribute representations of images for translation. On face images of the recent DiF dataset, with the same gender attribute, our method adjusts nose regions. In the Adult income dataset, also with protected gender attribute, our model achieves equality of opportunity by, among others, obfuscating the wife and husband relationship. Analyzing those systematic changes will allow us to scrutinize the interplay of fairness criterion, chosen protected characteristics, and prediction performance.

Anastasia Pentina, Viktoriia Sharmanska, Christoph H. Lampert

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks.

Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the computers to be able to learn faster at the expense of providing extra information during training time. As additional information about the image data, we look at several scenarios that have been studied in computer vision before: attributes, bounding boxes and image tags. The information is privileged as it is available at training time but not at test time. We explore two maximum-margin techniques that are able to make use of this additional source of information, for binary and multiclass object classification. We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space. We provide a thorough analysis and comparison of information transfer from privileged to the original data spaces for both LUPI methods. Our experiments show that incorporating privileged information can improve the classification accuracy. Finally, we conduct user studies to understand which samples are easy and which are hard for human learning, and explore how this information is related to easy and hard samples when learning a classifier.

Daniel Hernández-Lobato, Viktoriia Sharmanska, Kristian Kersting et al.

The learning with privileged information setting has recently attracted a lot of attention within the machine learning community, as it allows the integration of additional knowledge into the training process of a classifier, even when this comes in the form of a data modality that is not available at test time. Here, we show that privileged information can naturally be treated as noise in the latent function of a Gaussian Process classifier (GPC). That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.

Novi Quadrianto, Viktoriia Sharmanska, David A. Knowles et al.

We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semantic concept have similar latent values, and objects in different concepts have dissimilar latent values. We formulate the supervised infinite latent variable problem based on an intuitive principle of pulling objects together if they are of the same type, and pushing them apart if they are not. We then combine this principle with a flexible Indian Buffet Process prior on the latent variables. We show that the inferred supervised latent variables can be directly used to perform a nearest neighbour search for the purpose of retrieval. We introduce a new application of dynamically extending hash codes, and show how to effectively couple the structure of the hash codes with continuously growing structure of the neighbourhood preserving infinite latent feature space.