Learning Noise-Assisted Robust Image Features for Fine-Grained Image Retrieval

Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.

An Optimized Framework for Surgical Team Selection

In the healthcare system,a surgical team is a unit of experienced personnel who provide medical care to surgical patients during surgery.Selecting a surgical team is challenging for a multispecialty hospital as the performance of its members affects the efficiency and reliability of the hospital’s patient care.The effectiveness of a surgical team depends not only on its individual members but also on the coordination among them.In this paper,we addressed the challenges of surgical team selection faced by a multispecialty hospital and proposed a decision-making framework for selecting the optimal list of surgical teams for a given patient.The proposed framework focused on improving the existing surgical history management system by arranging surgery-bound patients into optimal subgroups based on similar characteristics and selecting an optimal list of surgical teams for a new surgical patient based on the patient’s subgroups.For this end,two population-based meta-heuristic algorithms for clustering of mixed datasets and multi-objective optimization were proposed.The proposed algorithms were tested using different datasets and benchmark functions.Furthermore,the proposed framework was validated through a case study of a real postoperative surgical dataset obtained from the orthopedic surgery department of a multispecialty hospital in India.The results revealed that the proposed framework was efficient in arranging patients in optimal groups as well as selecting optimal surgical teams for a given patient.