76 citations · 245 across the 28 of their papers we have counts for
22 papers · 1 filter
DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest
Alibek Kamiluly, Milana Muratova, Yash Patel +1
Breast mass segmentation is an important step in computer-aided mammography, but it remains difficult because masses can have low contrast, irregular shapes, and boundaries that bl…
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
Jason Rojas, Jiajie He, Yash Patel +3
Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development. Ima…
Information-Regularized Attention for Visual-Centric Reasoning
Guohao Sun, Xiaofang Wang, Yash Patel +3
Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting af…
Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach
Yash Patel, Tirth Shah, Mrinal Kanti Dhar +4
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.…
Neural Network Training and Non-Differentiable Objective Functions
Yash Patel
Many important computer vision tasks are naturally formulated to have a non-differentiable objective. Therefore, the standard, dominant training procedure of a neural network is no…
FUSegNet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation
Mrinal Kanti Dhar, Taiyu Zhang, Yash Patel +2
This paper presents FUSegNet, a new model for foot ulcer segmentation in diabetes patients, which uses the pre-trained EfficientNet-b7 as a backbone to address the issue of limited…
SimCon Loss with Multiple Views for Text Supervised Semantic Segmentation
Yash Patel, Yusheng Xie, Yi Zhu +2
Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the sample…
MultiNet with Transformers: A Model for Cancer Diagnosis Using Images
Hosein Barzekar, Yash Patel, Ling Tong +1
Cancer is a leading cause of death in many countries. An early diagnosis of cancer based on biomedical imaging ensures effective treatment and a better prognosis. However, biomedic…
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Filip Radenovic, Abhimanyu Dubey, Abhishek Kadian +6
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve th…
Generalized Differentiable RANSAC
Tong Wei, Yash Patel, Alexander Shekhovtsov +2
We propose -RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. The proposed approach enables the use of rela…
Contrastive Classification and Representation Learning with Probabilistic Interpretation
Rahaf Aljundi, Yash Patel, Milan Sulc +2
Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness an…
Multi-modal Wound Classification using Wound Image and Location by Deep Neural Network
D. M. Anisuzzaman, Yash Patel, Behrouz Rostami +3
Wound classification is an essential step of wound diagnosis. An efficient classifier can assist wound specialists in classifying wound types with less financial and time costs and…
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Yash Patel, Giorgos Tolias, Jiri Matas
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 appro…
FEDS -- Filtered Edit Distance Surrogate
Yash Patel, Jiri Matas
This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance. The proposed method borrows from self-paced learning and…
A Mobile App for Wound Localization using Deep Learning
D. M. Anisuzzaman, Yash Patel, Jeffrey Niezgoda +2
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 s…
Learning Surrogates via Deep Embedding
Yash Patel, Tomas Hodan, Jiri Matas
This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The su…
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
Nibal Nayef, Yash Patel, Michal Busta +8
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. With the go…
Self-Supervised Visual Representations for Cross-Modal Retrieval
Yash Patel, Lluis Gomez, Marçal Rusiñol +2
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. Ho…
TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
Yash Patel, Lluis Gomez, Raul Gomez +3
The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discri…
Learning Sampling Policies for Domain Adaptation
Yash Patel, Kashyap Chitta, Bhavan Jasani
We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning. The core idea is to consider the predictions of a source domain ne…
E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
Michal Bušta, Yash Patel, Jiri Matas
An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed. The approach is based on a single fully convolutional…
Self-supervised learning of visual features through embedding images into text topic spaces
Lluis Gomez, Yash Patel, Marçal Rusiñol +2
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. In this pape…