English
Related papers

Related papers: Rank & Sort Loss for Object Detection and Instance…

200 papers

Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 Hao Fang , Daoxin Zhang , Yi Zhang , Minghao Chen , Jiawei Li , Yao Hu , Deng Cai , Xiaofei He

Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models. Despite years of effort, direct optimization for these metrics remains a challenge due to their non-differentiable and…

Machine Learning · Computer Science 2024-12-16 Michal Rolínek , Vít Musil , Anselm Paulus , Marin Vlastelica , Claudio Michaelis , Georg Martius

RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Wu Kehe , Chen Zuge , Zhang Xiaoliang , Li Wei

Recently, infrared small target detection (IRSTD) has been dominated by deep-learning-based methods. However, these methods mainly focus on the design of complex model structures to extract discriminative features, leaving the loss…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Qiankun Liu , Rui Liu , Bolun Zheng , Hongkui Wang , Ying Fu

Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise objects at a pixel…

Computer Vision and Pattern Recognition · Computer Science 2016-09-12 Anurag Arnab , Philip H. S. Torr

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Tsung-Yi Lin , Priya Goyal , Ross Girshick , Kaiming He , Piotr Dollár

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

Machine Learning · Computer Science 2022-03-01 Tao Huang , Zekang Li , Hua Lu , Yong Shan , Shusheng Yang , Yang Feng , Fei Wang , Shan You , Chang Xu

Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behaviour, zero-shot object detection…

Computer Vision and Pattern Recognition · Computer Science 2020-04-03 Shafin Rahman , Salman Khan , Nick Barnes

In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled deep distributed…

Machine Learning · Computer Science 2015-01-29 Xiao-Lei Zhang

This paper introduces a new comparison base stable sorting algorithm, named RS sort. RS Sort involves only the comparison of pair of elements in an array which ultimately sorts the array and does not involve the comparison of each element…

Data Structures and Algorithms · Computer Science 2014-07-23 Harsh Ranjan , Sumit Agarwal , Niraj Kumar Singh

Multi-object Tracking (MOT) generally can be split into two sub-tasks, i.e., detection and association. Many previous methods follow the tracking by detection paradigm, which first obtain detections at each frame and then associate them…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Mingfei Chen , Yue Liao , Si Liu , Fei Wang , Jenq-Neng Hwang

Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Cuong Manh Hoang

Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surrogate supervision and are poorly aligned with tracking optimization and evaluation metrics,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Xin Chen , Chuanyu Sun , Jiao Xu , Houwen Peng , Dong Wang , Huchuan Lu , Kede Ma

Since the rise of deep learning, many computer vision tasks have seen significant advancements. However, the downside of deep learning is that it is very data-hungry. Especially for segmentation problems, training a deep neural net requires…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Robby Neven , Davy Neven , Bert De Brabandere , Marc Proesmans , Toon Goedemé

In this paper, we propose a robust sequential learning strategy for training large-scale Recommender Systems (RS) over implicit feedback mainly in the form of clicks. Our approach relies on the minimization of a pairwise ranking loss over…

Information Retrieval · Computer Science 2021-09-15 Alexandra Burashnikova , Yury Maximov , Massih-Reza Amini

Vision problems ranging from image clustering to motion segmentation to semi-supervised learning can naturally be framed as subspace segmentation problems, in which one aims to recover multiple low-dimensional subspaces from noisy and…

Computer Vision and Pattern Recognition · Computer Science 2013-10-17 Ameet Talwalkar , Lester Mackey , Yadong Mu , Shih-Fu Chang , Michael I. Jordan

As a core problem in computer vision, the performance of object detection has improved drastically in the past few years. Despite their impressive performance, object detectors suffer from a lack of interpretability. Visualization…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Ang Cao , Justin Johnson

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Xinshao Wang , Yang Hua , Elyor Kodirov , Neil M. Robertson

The accuracy of deep learning methods for two foundational tasks in medical image analysis -- detection and segmentation -- can suffer from class imbalance. We propose a `switching loss' function that adaptively shifts the emphasis between…

Image and Video Processing · Electrical Eng. & Systems 2020-08-11 Deepak Anand , Gaurav Patel , Yaman Dang , Amit Sethi

We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual…

Computer Vision and Pattern Recognition · Computer Science 2020-11-19 Jaedong Hwang , Seohyun Kim , Jeany Son , Bohyung Han