English
Related papers

Related papers: IoU is not submodular

200 papers

Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Ruiqi Lu , Huimin Ma

Quantifying the similarity between two mathematical structures or datasets constitutes a particularly interesting and useful operation in several theoretical and applied problems. Aimed at this specific objective, the Jaccard index has been…

Machine Learning · Computer Science 2021-11-19 Luciano da F. Costa

It has been hypothesized that some form of "modular" structure in artificial neural networks should be useful for learning, compositionality, and generalization. However, defining and quantifying modularity remains an open problem. We cast…

Machine Learning · Computer Science 2022-06-23 Richard D. Lange , David S. Rolnick , Konrad P. Kording

An alternative foundation for 2-categories is explored by studying graph-theoretically a partial operation on 2-cells named juncture, which can replace vertical and horizontal composition. Juncture is a generalized vertical composition of…

Combinatorics · Mathematics 2015-05-07 Kosta Dosen , Zoran Petric

In this paper, we investigate a class of submodular problems which in general are very hard. These include minimizing a submodular cost function under combinatorial constraints, which include cuts, matchings, paths, etc., optimizing a…

Machine Learning · Computer Science 2019-02-28 Rishabh Iyer , Jeff Bilmes

In this paper, we study the submodularity of the covolume function in global function fields. The submodular property is often needed in the study of homogeneous dynamics, especially to define a Margulis function. We proved that the…

Number Theory · Mathematics 2024-04-25 Gukyeong Bang

As scene segmentation systems reach visually accurate results, many recent papers focus on making these network architectures faster, smaller and more efficient. In particular, studies often aim at designingreal-time'systems. Achieving this…

Computer Vision and Pattern Recognition · Computer Science 2022-04-21 Evann Courdier , Francois Fleuret

In this note, we present a conjecture on intersections of set families, and a rephrasing of the conjecture in terms of principal downsets of Boolean lattices. The conjecture informally states that, whenever we can express the measure of a…

Combinatorics · Mathematics 2024-01-30 Antoine Amarilli , Mikaël Monet , Dan Suciu

In medicine, visualizing chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosomes often overlap and it is necessary to identify and distinguish between the overlapping…

Computer Vision and Pattern Recognition · Computer Science 2017-12-21 R. Lily Hu , Jeremy Karnowski , Ross Fadely , Jean-Patrick Pommier

We establish analogues in the context of group actions or group representations of some classical problems and results in additive combinatorics of groups. We also study the notion of left invariant submodular function defined on power sets…

Combinatorics · Mathematics 2024-04-17 Vincent Beck , Cédric Lecouvey

Federated learning is an emerging distributed machine learning framework for privacy preservation. However, models trained in federated learning usually have worse performance than those trained in the standard centralized learning mode,…

Machine Learning · Computer Science 2021-06-15 Hangyu Zhu , Jinjin Xu , Shiqing Liu , Yaochu Jin

With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effectively solved at an additional labeling cost by targeted data…

Machine Learning · Computer Science 2021-05-04 Suraj Kothawade , Vishal Kaushal , Ganesh Ramakrishnan , Jeff Bilmes , Rishabh Iyer

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…

Machine Learning · Computer Science 2024-01-30 Jonas Pfeiffer , Sebastian Ruder , Ivan Vulić , Edoardo Maria Ponti

Recently, it has become evident that submodularity naturally captures widely occurring concepts in machine learning, signal processing and computer vision. Consequently, there is need for efficient optimization procedures for submodular…

Machine Learning · Computer Science 2013-11-19 Stefanie Jegelka , Francis Bach , Suvrit Sra

Machine learning (ML) has become a go-to solution for improving how we use, experience, and interact with technology (and the world around us). Unfortunately, studies have repeatedly shown that machine learning technologies may not provide…

Machine Learning · Computer Science 2025-05-15 Michelle Nashla Turcios , Alicia E. Boyd , Angela D. R. Smith , Brittany Johnson

We describe a new measure for the evaluation of region level segmentation of objects, as applied to evaluating the accuracy of leaf-level segmentation of plant images. The proposed approach enforces the rule that a region (e.g. a leaf) in…

Computer Vision and Pattern Recognition · Computer Science 2016-11-22 Jonathan Bell , Hannah M. Dee

Submodularity is an important concept in integer and combinatorial optimization. A classical submodular set function models the utility of selecting homogenous items from a single ground set, and such selections can be represented by binary…

Optimization and Control · Mathematics 2023-04-06 Simge Küçükyavuz , Qimeng Yu

Decomposing the domain of a function into parts has many uses in mathematics. A domain may naturally be a union of pieces, a function may be defined by cases, or different boundary conditions may hold on different regions. For any…

Symbolic Computation · Computer Science 2010-05-03 Jacques Carette , Alan P. Sexton , Volker Sorge , Stephen M. Watt

Clustering with submodular functions has been of interest over the last few years. Symmetric submodular functions are of particular interest as minimizing them is significantly more efficient and they include many commonly used functions in…

Data Structures and Algorithms · Computer Science 2014-11-21 Amit Dhurandhar , Karthik Gurumoorthy

Functions with uniform sublevel sets can represent orders, preference relations or other binary relations and thus turn out to be a tool for scalarization that can be used in multicriteria optimization, decision theory, mathematical…

Optimization and Control · Mathematics 2017-12-06 Petra Weidner