Related papers: Optimal Neural Summarisation for Full-Field Weak L…
Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the relation between the sharpness of the loss landscape and the generalization error…
This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling…
Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images. NeRF and relevant neural field methods (e.g., neural surface…
Dark matter cannot be observed directly, but its weak gravitational lensing slightly distorts the apparent shapes of background galaxies, making weak lensing one of the most promising probes of cosmology. Several observational studies have…
An unprecedented amount of existing functional Magnetic Resonance Imaging (fMRI) data provides a new opportunity to understand the relationship between functional fluctuation and human cognition/behavior using a data-driven approach. To…
This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update…
We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus…
Symbolic Regression is the study of algorithms that automate the search for analytic expressions that fit data. While recent advances in deep learning have generated renewed interest in such approaches, the development of symbolic…
This paper presents a procedure for and evaluation of using a semantic similarity metric as a loss function for neural source code summarization. Code summarization is the task of writing natural language descriptions of source code. Neural…
Accurate beam prediction is essential for mitigating signalling overhead and latency in integrated sensing and communication-enabled massive multi-input multi-output systems. With the aid of multimodal learning, the prediction accuracy can…
We address the problem of maximizing an unknown submodular function that can only be accessed via noisy evaluations. Our work is motivated by the task of summarizing content, e.g., image collections, by leveraging users' feedback in form of…
Simulation-based inference (SBI) enables cosmological parameter estimation when closed-form likelihoods or models are unavailable. However, SBI relies on machine learning for neural compression and density estimation. This requires large…
Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this work proposes a novel approach that bridges 2D vision…
Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, but constrained to the retained summary statistics (e.g., the…
Self-supervised depth estimators have recently shown results comparable to the supervised methods on the challenging single image depth estimation (SIDE) task, by exploiting the geometrical relations between target and reference views in…
There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…
Accurate real-time simulation of lens optics remains challenging due to the computational expense of full ray tracing and the limitations of existing approximations. The commonly used pinhole model and thin-lens model ignore many optical…
This paper presents a weakly supervised image segmentation method that adopts tight bounding box annotations. It proposes generalized multiple instance learning (MIL) and smooth maximum approximation to integrate the bounding box tightness…
The standard approach to inference from cosmic large-scale structure data employs summary statistics that are compared to analytic models in a Gaussian likelihood with pre-computed covariance. To overcome the idealising assumptions about…
Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn the segmentation labels from class-level labels. In the literature, exploiting the information obtained from Class Activation Maps (CAMs) is widely used…