Related papers: A Linked Aggregate Code for Processing Faces (Revi…
As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…
Multimodal AI models capable of associating images and text hold promise for numerous domains, ranging from automated image captioning to accessibility applications for blind and low-vision users. However, uncertainty about bias has in some…
Language-Assisted Image Clustering (LAIC) augments the input images with additional texts with the help of vision-language models (VLMs) to promote clustering performance. Despite recent progress, existing LAIC methods often overlook two…
In this dissertation, we present a generative model to capture the relation between facial image quality features (like pose, illumination direction, etc) and face recognition performance. Such a model can be used to predict the performance…
Perceptual judgment of image similarity by humans relies on rich internal representations ranging from low-level features to high-level concepts, scene properties and even cultural associations. However, existing methods and datasets…
Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ in numerous ways from those that give rise to human…
Perceptual similarity is a cognitive judgment that represents the end-stage of a complex cascade of hierarchical processing throughout visual cortex. Previous studies have shown a correspondence between the similarity of coarse-scale fMRI…
The proliferation of facial recognition systems presents major privacy risks, driving the need for effective countermeasures. Current adversarial techniques apply generalized methods rather than adapting to individual facial…
In this paper, we utilize structured learning to simultaneously address two intertwined problems: human pose estimation (HPE) and garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative…
Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…
Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations…
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various neural architectures, spanning Transformer-based models like Vision Transformers (ViTs) to Convolutional Networks…
A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions…
Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of…
Similarity scores in face recognition represent the proximity between pairs of images as computed by a matching algorithm. Given a large set of images and the proximities between all pairs, a similarity score space is defined. Cluster…
Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics…
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. However, challenges arise in handling visual states due to their less distinguishable representation compared to…
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…