English
Related papers

Related papers: Unbiased Regression Loss for DETRs

200 papers

DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Xizhou Zhu , Weijie Su , Lewei Lu , Bin Li , Xiaogang Wang , Jifeng Dai

Detection Transformers have achieved competitive performance on the sample-rich COCO dataset. However, we show most of them suffer from significant performance drops on small-size datasets, like Cityscapes. In other words, the detection…

Computer Vision and Pattern Recognition · Computer Science 2022-08-26 Wen Wang , Jing Zhang , Yang Cao , Yongliang Shen , Dacheng Tao

Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Jeffrey Ouyang-Zhang , Jang Hyun Cho , Xingyi Zhou , Philipp Krähenbühl

I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Shuang Wang

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

DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-07 Byungseok Roh , JaeWoong Shin , Wuhyun Shin , Saehoon Kim

Estimating the ratio of two probability densities from a finite number of observations is a central machine learning problem. A common approach is to construct estimators using binary classifiers that distinguish observations from the two…

Machine Learning · Computer Science 2025-01-28 Werner Zellinger

We consider a high dimensional linear regression problem where the goal is to efficiently recover an unknown vector $\beta^*$ from $n$ noisy linear observations $Y=X\beta^*+W \in \mathbb{R}^n$, for known $X \in \mathbb{R}^{n \times p}$ and…

Statistics Theory · Mathematics 2018-11-12 David Gamarnik , Ilias Zadik

Most current detection methods have adopted anchor boxes as regression references. However, the detection performance is sensitive to the setting of the anchor boxes. A proper setting of anchor boxes may vary significantly across different…

Computer Vision and Pattern Recognition · Computer Science 2018-11-19 Lele Xie , Yuliang Liu , Lianwen Jin , Zecheng Xie

Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2018-05-08 Zhenhua Chen , David Crandall , Robert Templeman

This paper carries out a large dimensional analysis of a variation of kernel ridge regression that we call \emph{centered kernel ridge regression} (CKRR), also known in the literature as kernel ridge regression with offset. This modified…

Machine Learning · Statistics 2020-04-22 Khalil Elkhalil , Abla Kammoun , Xiangliang Zhang , Mohamed-Slim Alouini , Tareq Al-Naffouri

De-biased lasso has emerged as a popular tool to draw statistical inference for high-dimensional regression models. However, simulations indicate that for generalized linear models (GLMs), de-biased lasso inadequately removes biases and…

Methodology · Statistics 2020-06-24 Lu Xia , Bin Nan , Yi Li

In this work, we briefly revise the reduced dilation-erosion perceptron (r-DEP) models for binary classification tasks. Then, we present the so-called linear dilation-erosion perceptron (l-DEP), in which a linear transformation is applied…

Machine Learning · Computer Science 2020-11-13 Angelica Lourenço Oliveira , Marcos Eduardo Valle

The mainstream theory of hypothesis testing in high-dimensional regression typically assumes the underlying true model is a low-dimensional linear regression model, yet the Box-Cox transformation is a regression technique commonly used to…

Methodology · Statistics 2024-05-22 He Zhou , Hui Zou

Accurate lung nodule detection for computed tomography (CT) scan imagery is challenging in real-world settings due to the sparse occurrence of nodules and similarity to other anatomical structures. In a typical positive case, nodules may…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Hooman Ramezani , Dionne Aleman , Daniel Létourneau

In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact biased compressors often show…

Machine Learning · Computer Science 2024-01-17 Aleksandr Beznosikov , Samuel Horváth , Peter Richtárik , Mher Safaryan

Consider the regression problem where the response $Y\in\mathbb{R}$ and the covariate $X\in\mathbb{R}^d$ for $d\geq 1$ are \textit{unmatched}. Under this scenario, we do not have access to pairs of observations from the distribution of $(X,…

Statistics Theory · Mathematics 2023-09-19 Mona Azadkia , Fadoua Balabdaoui

Cross-dose denoising for low-dose positron emission tomography (LDPET) has been proposed to address the limited generalization of models trained at a single noise level. However, neural networks trained on a specific dose level often fail…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yichao Liu , Zongru Shao , Yueyang Teng , Junwen Guo

We consider statistical inference for a single coordinate of regression coefficients in high-dimensional linear models. Recently, the debiased estimators are popularly used for constructing confidence intervals and hypothesis testing in…

Statistics Theory · Mathematics 2020-10-20 Sai Li

We propose a new convex loss for Support Vector Machines, both for the binary classification and for the regression models. Therefore, we show the mathematical derivation of the dual problems and we experiment with them on several small…

Machine Learning · Computer Science 2026-03-02 Filippo Portera