Search Results for author:
Found 14 papers, 2 papers with code
Domain Generalization by Learning from Privileged Medical Imaging Information
This paper demonstrates that by using privileged information to predict the severity of intra-layer retinal fluid in optical coherence tomography scans, the classification accuracy of a deep learning model operating on out-of-distribution data improves from $0. 911$ to $0. 934$.
Single Domain Generalization via Normalised Cross-correlation Based Convolutions
This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions.
IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation
Distribution shift between train (source) and test (target) datasets is a common problem encountered in machine learning applications.
ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains.
Maximum Consensus by Weighted Influences of Monotone Boolean Functions
In particular, we study endowing the Boolean cube with the Bernoulli measure and performing biased (as opposed to uniform) sampling.
Robust Pooling through the Data Mode
The proposed pooling layer looks for data a mode/cluster using two methods, RANSAC, and histogram, as clusters are indicative of models.
Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning
We provide evidence that demonstrates that learning of features in the synthetic domain by a stereo matching network is heavily influenced by two "shortcuts" presented in the synthetic data: (1) identical local statistics (RGB colour features) between matching pixels in the synthetic stereo images and (2) lack of realism in synthetic textures on 3D objects simulated in game engines.
Consensus Maximisation Using Influences of Monotone Boolean Functions
Consensus maximisation (MaxCon), which is widely used for robust fitting in computer vision, aims to find the largest subset of data that fits the model within some tolerance level.
Rotation Averaging with Attention Graph Neural Networks
In this paper we propose a single-stage graph neural network that can robustly perform rotation averaging in the presence of noise and outliers.
Adjusting Bias in Long Range Stereo Matching: A semantics guided approach
Consequently, the learning algorithms often produce unreliable depth estimates of foreground objects, particularly at large distances~($>50$m).
Robust Object Classification Approach using Spherical Harmonics
In this paper, we present a robust spherical harmonics approach for the classification of point cloud-based objects.
Monotone Boolean Functions, Feasibility/Infeasibility, LP-type problems and MaxCon
This paper outlines connections between Monotone Boolean Functions, LP-Type problems and the Maximum Consensus Problem.
Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting
In this paper, we propose an effective sampling method to obtain a highly accurate approximation of the full graph required to solve multi-structural model fitting problems in computer vision.
Labeled Multi-Bernoulli Tracking for Industrial Mobile Platform Safety
This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial mobile platform safety applications.
