Search Results for author:
Found 30 papers, 10 papers with code
Conformal Contextual Robust Optimization
Data-driven approaches to predict-then-optimize decision-making problems seek to mitigate the risk of uncertainty region misspecification in safety-critical settings.
Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach
The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments.
Diffusion Models for Probabilistic Deconvolution of Galaxy Images
As an alternative, we propose a classifier-free conditional diffusion model for PSF deconvolution of galaxy images.
Amortized Variational Inference with Coverage Guarantees
We prove lower bounds on the predictive efficiency of the regions produced by CANVI and explore how the quality of a posterior approximation relates to the predictive efficiency of prediction regions based on that approximation.
FUSegNet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation
As the top decoder stage carries a limited number of feature maps, max-out scSE is bypassed there to form a shorted P-scSE.
Neural Network Training and Non-Differentiable Objective Functions
An appropriate proxy has to be designed for a novel task, which may not be feasible for a non-specialist.
DocILE Benchmark for Document Information Localization and Extraction
This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition.
SimCon Loss with Multiple Views for Text Supervised Semantic Segmentation
Instead of purely relying on the alignment from the noisy data, this paper proposes a novel loss function termed SimCon, which accounts for intra-modal similarities to determine the appropriate set of positive samples to align.
DocILE 2023 Teaser: Document Information Localization and Extraction
The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for the tasks of Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) from business documents.
MultiNet with Transformers: A Model for Cancer Diagnosis Using Images
Cancer is a leading cause of death in many countries.
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems.
Generalized Differentiable RANSAC
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
RL Boltzmann Generators for Conformer Generation in Data-Sparse Environments
The generation of conformers has been a long-standing interest to structural chemists and biologists alike.
Contrastive Classification and Representation Learning with Probabilistic Interpretation
In this work, we investigate the possibility of learning both the representation and the classifier using one objective function that combines the robustness of contrastive learning and the probabilistic interpretation of cross entropy loss.
Wound Severity Classification using Deep Neural Network
This study used wound photos to construct a deep neural network-based wound severity classifier that classified them into one of three classes: green, yellow, or red.
Multi-modal Wound Classification using Wound Image and Location by Deep Neural Network
This study developed a deep neural network-based multi-modal classifier using wound images and their corresponding locations to categorize wound images into multiple classes, including diabetic, pressure, surgical, and venous ulcers.
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.
Ranked #1 on
Vehicle Re-Identification
on VehicleID Small
FEDS -- Filtered Edit Distance Surrogate
This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance.
Neural Network-based Acoustic Vehicle Counting
This distance is predicted from audio using a two-stage (coarse-fine) regression, with both stages realised via neural networks (NNs).
A Mobile App for Wound Localization using Deep Learning
We present an automated wound localizer from 2D wound and ulcer images by using deep neural network, as the first step towards building an automated and complete wound diagnostic system.
Learning Surrogates via Deep Embedding
The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate.
Saliency Driven Perceptual Image Compression
The proposed compression model incorporates the salient regions and optimizes on the proposed perceptual similarity metric.
Human Perceptual Evaluations for Image Compression
Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG).
Deep Perceptual Compression
In several cases, the MS-SSIM for deep learned techniques is higher than say a conventional, non-deep learned codec such as JPEG-2000 or BPG.
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense.
Cultural Vocal Bursts Intensity Prediction
General Classification
+2
Self-Supervised Visual Representations for Cross-Modal Retrieval
Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places.
TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration.
Learning Sampling Policies for Domain Adaptation
We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning.
E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed.
Self-supervised learning of visual features through embedding images into text topic spaces
End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible.
