Search Results for author:
Found 37 papers, 15 papers with code
BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
To mitigate these challenges, we propose Bias-based Weight Masking Fine-Tuning (BMFT), a novel post-processing method that enhances the fairness of a trained model in significantly fewer epochs without requiring access to the original training data.
einspace: Searching for Neural Architectures from Fundamental Operations
Using this search space, we perform experiments to find novel architectures as well as improvements on existing ones on the diverse Unseen NAS datasets.
Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction
This paper shows that machine unlearning is possible in MRI tasks and has the potential to benefit for bias removal.
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation
To build MuLAn, we developed a training free pipeline which decomposes a monocular RGB image into a stack of RGBA layers comprising of background and isolated instances.
Optimisation-Based Multi-Modal Semantic Image Editing
Image editing affords increased control over the aesthetics and content of generated images.
Multi-task Learning with 3D-Aware Regularization
Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations in high dimensional feature space across tasks.
Learning to Name Classes for Vision and Language Models
Large scale vision and language models can achieve impressive zero-shot recognition performance by mapping class specific text queries to image content.
Tunable Convolutions with Parametric Multi-Loss Optimization
Behavior of neural networks is irremediably determined by the specific loss and data used during training.
Label-Efficient Object Detection via Region Proposal Network Pre-Training
In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance.
Content-Diverse Comparisons improve IQA
This restricts the diversity and number of image pairs that the model is exposed to during training.
CLAD: A realistic Continual Learning benchmark for Autonomous Driving
In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection.
Out-of-Distribution Detection with Class Ratio Estimation
In this work, we propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Re-examining Distillation For Continual Object Detection
Training models continually to detect and classify objects, from new classes and new domains, remains an open problem.
CroMo: Cross-Modal Learning for Monocular Depth Estimation
Learning-based depth estimation has witnessed recent progress in multiple directions; from self-supervision using monocular video to supervised methods offering highest accuracy.
Model-Based Image Signal Processors via Learnable Dictionaries
Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP).
Long-tail Recognition via Compositional Knowledge Transfer
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer.
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals
In the era of deep learning, supervised residual learning (ResL) has led to many breakthroughs in low-level vision such as image restoration and enhancement tasks.
Spread Flows for Manifold Modelling
Flow-based models typically define a latent space with dimensionality identical to the observational space.
On the Out-of-distribution Generalization of Probabilistic Image Modelling
Out-of-distribution (OOD) detection and lossless compression constitute two problems that can be solved by the training of probabilistic models on a first dataset with subsequent likelihood evaluation on a second dataset, where data distributions differ.
Out-of-Distribution Generalization
Out of Distribution (OOD) Detection
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images
We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs.
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
Fewmatch: Dynamic Prototype Refinement for Semi-Supervised Few-Shot Learning
Semi-Supervised Few-shot Learning (SS-FSL) investigates the benefit of incorporating unlabelled data in few-shot settings.
On the Latent Space of Flow-based Models
Flow-based generative models typically define a latent space with dimensionality identical to the observational space.
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Object detection has witnessed significant progress by relying on large, manually annotated datasets.
Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping
Advances in low-light video RAW-to-RGB translation are opening up the possibility of fast low-light imaging on commodity devices (e. g. smartphone cameras) without the need for a tripod.
Image and Video Processing
DeepLPF: Deep Local Parametric Filters for Image Enhancement
We introduce a deep neural network, dubbed Deep Local Parametric Filters (DeepLPF), which regresses the parameters of these spatially localized filters that are then automatically applied to enhance the image.
Ranked #8 on
Image Enhancement
on MIT-Adobe 5k
(SSIM on proRGB metric)
A Multi-Hypothesis Approach to Color Constancy
Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images.
CURL: Neural Curve Layers for Global Image Enhancement
We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool.
Ranked #4 on
Photo Retouching
on MIT-Adobe 5k
SteReFo: Efficient Image Refocusing with Stereo Vision
Whether to attract viewer attention to a particular object, give the impression of depth or simply reproduce human-like scene perception, shallow depth of field images are used extensively by professional and amateur photographers alike.
Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem
In this work, we propose a new approach that affords fast adaptation to previously unseen cameras, and robustness to changes in capture device by leveraging annotated samples across different cameras and datasets.
Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents
Navigating through target anatomy to find the required view plane is tedious and operator-dependent.
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
In this paper, we propose a general Riemannian formulation of the pose estimation problem.
Attention U-Net: Learning Where to Look for the Pancreas
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes.
Ranked #1 on
Pancreas Segmentation
on CT-150
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
Deep learning approaches such as convolutional neural nets have consistently outperformed previous methods on challenging tasks such as dense, semantic segmentation.
3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
We extensively evaluate the effectiveness of our approach quantitatively on simulated Magnetic Resonance Imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline.
Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging
Fast imaging is required for targets that move to avoid motion artefacts.
Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion
Our approach is attractive in challenging imaging scenarios, where significant subject motion complicates reconstruction performance of 3D volumes from 2D slice data.
