40 citations · 168 across the 23 of their papers we have counts for
26 papers
Learning to Segment from Noisy Annotations: A Spatial Correction Approach
Jiachen Yao, Yikai Zhang, Songzhu Zheng +3
Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in ann…
A Manifold View of Adversarial Risk
Wenjia Zhang, Yikai Zhang, Xiaoling Hu +3
The adversarial risk of a machine learning model has been widely studied. Most previous works assume that the data lies in the whole ambient space. We propose to take a new angle a…
Obtaining Approximately Optimal and Diverse Solutions via Dispersion
Jie Gao, Mayank Goswami, Karthik C. S. +3
There has been a long-standing interest in computing diverse solutions to optimization problems. Motivated by reallocation of governmental institutions in Sweden, in 1995 J. Krarup…
AI and conventional methods for UCT projection data estimation
Ankur Kumar, Prasunika Khare, Mayank Goswami
A 2D Compact ultrasound computerized tomography (UCT) system is developed. Fully automatic post processing tools involving signal and image processing are developed as well. Square…
AI Algorithm for Mode Classification of PCF SPR Sensor Design
Prasunika Khare, Mayank Goswami
Photonic Crystal Fiber design based on surface plasmon resonance phenomenon (PCF SPR) is optimized before it is fabricated for a particular application. An artificial intelligence…
Deep Learning models for benign and malign Ocular Tumor Growth Estimation
Mayank Goswami
Relatively abundant availability of medical imaging data has provided significant support in the development and testing of Neural Network based image processing methods. Clinician…
Topological Detection of Trojaned Neural Networks
Songzhu Zheng, Yikai Zhang, Hubert Wagner +2
Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through…
Learning with Feature-Dependent Label Noise: A Progressive Approach
Yikai Zhang, Songzhu Zheng, Pengxiang Wu +2
Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing…
Stability of SGD: Tightness Analysis and Improved Bounds
Yikai Zhang, Wenjia Zhang, Sammy Bald +3
Stochastic Gradient Descent (SGD) based methods have been widely used for training large-scale machine learning models that also generalize well in practice. Several explanations h…
A Topological Filter for Learning with Label Noise
Pengxiang Wu, Songzhu Zheng, Mayank Goswami +2
Noisy labels can impair the performance of deep neural networks. To tackle this problem, in this paper, we propose a new method for filtering label noise. Unlike most existing meth…
Error-Bounded Correction of Noisy Labels
Songzhu Zheng, Pengxiang Wu, Aman Goswami +3
To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on th…
Cutting Polygons into Small Pieces with Chords: Laser-Based Localization
Esther M. Arkin, Rathish Das, Jie Gao +4
Motivated by indoor localization by tripwire lasers, we study the problem of cutting a polygon into small-size pieces, using the chords of the polygon. Several versions are conside…
Batched Predecessor and Sorting with Size-Priced Information in External Memory
Michael A. Bender, Mayank Goswami, Dzejla Mededovic +2
In the unit-cost comparison model, a black box takes an input two items and outputs the result of the comparison. Problems like sorting and searching have been studied in this mode…
On the I/O complexity of the k-nearest neighbor problem
Mayank Goswami, Riko Jacob, Rasmus Pagh
We consider static, external memory indexes for exact and approximate versions of the -nearest neighbor (-NN) problem, and show new lower bounds under a standard indivisibili…
Multi-finger binary search trees
Parinya Chalermsook, Mayank Goswami, László Kozma +2
We study multi-finger binary search trees (BSTs), a far-reaching extension of the classical BST model, with connections to the well-studied -server problem. Finger search is a p…
Buffered Count-Min Sketch on SSD: Theory and Experiments
Mayank Goswami, Dzejla Medjedovic, Emina Mekic +1
Frequency estimation data structures such as the count-min sketch (CMS) have found numerous applications in databases, networking, computational biology and other domains. Many app…
Bloom Filters, Adaptivity, and the Dictionary Problem
Michael A. Bender, Martin Farach-Colton, Mayank Goswami +3
The Bloom filter---or, more generally, an approximate membership query data structure (AMQ)---maintains a compact, probabilistic representation of a set S of keys from a universe U…
Distance Sensitive Bloom Filters Without False Negatives
Mayank Goswami, Rasmus Pagh, Francesco Silvestri +1
A Bloom filter is a widely used data-structure for representing a set and answering queries of the form "Is in ?". By allowing some false positive answers (saying "yes"…
The landscape of bounds for binary search trees
Parinya Chalermsook, Mayank Goswami, László Kozma +2
Binary search trees (BSTs) with rotations can adapt to various kinds of structure in search sequences, achieving amortized access times substantially better than the Theta(log n) w…
Pattern-avoiding access in binary search trees
Parinya Chalermsook, Mayank Goswami, Laszlo Kozma +2
The dynamic optimality conjecture is perhaps the most fundamental open question about binary search trees (BST). It postulates the existence of an asymptotically optimal online BST…
Space Filling Curves for 3D Sensor Networks with Complex Topology
Mayank Goswami, Siming Li, Junwei Zhang +3
Several aspects of managing a sensor network (e.g., motion planning for data mules, serial data fusion and inference) benefit once the network is linearized to a path. The lineariz…
Greedy Is an Almost Optimal Deque
Parinya Chalermsook, Mayank Goswami, Laszlo Kozma +2
In this paper we extend the geometric binary search tree (BST) model of Demaine, Harmon, Iacono, Kane, and Patrascu (DHIKP) to accommodate for insertions and deletions. Within this…
Self-Adjusting Binary Search Trees: What Makes Them Tick?
Parinya Chalermsook, Mayank Goswami, Laszlo Kozma +2
Splay trees (Sleator and Tarjan) satisfy the so-called access lemma. Many of the nice properties of splay trees follow from it. What makes self-adjusting binary search trees (BSTs)…
Uniformity of point samples in metric spaces using gap ratio
Arijit Bishnu, Sameer Desai, Arijit Ghosh +2
Teramoto et al. defined a new measure called the gap ratio that measures the uniformity of a finite point set sampled from , a bounded subset of . We generali…