paper-with-me

홈 › Papers

Deep Regression Tracking with Shrinkage Loss

2018-09-01 · ECCV 2018 9 · Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, Ian Reid, Ming-Hsuan Yang

Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions. Due to the potential for fast-tracking and easy implementation, regression trackers have received increasing attention recently. However, state-of-the-art deep regression trackers do not perform as well as discriminative correlation filters (DCFs) trackers. We identify the main bottleneck of training regression networks as extreme foreground-background data imbalance. To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data. Additionally, we apply residual connections to fuse multiple convolutional layers as well as their output response maps. Without bells and whistles, the proposed deep regression tracking method performs favorably against state-of-the-art trackers, especially in comparison with DCFs trackers, on five benchmark datasets including OTB-2013, OTB-2015, Temple-128, UAV-123 and VOT-2016.

📄 PDF Abstract BibTeX

Code (1)

chaoma99/DSLT 공식 구현 pytorch

Tasks

regression

Similar Papers 제목 키워드 기반

Improving evidential deep learning via multi-task learning

2021-12-17 · Dongpin Oh, Bonggun Shin

The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the …

Deep LearningMulti-Task LearningOut-of-Distribution Detectionregression

High dimensional thresholded regression and shrinkage effect

2016-05-11 · Zemin Zheng, Yingying Fan, Jinchi Lv

High-dimensional sparse modeling via regularization provides a powerful tool for analyzing large-scale data sets and obtaining meaningful, interpretable models. The use of nonconvex penalty functions shows advantage in s…

PredictionregressionVariable SelectionVocal Bursts Intensity Prediction

Decoupling Shrinkage and Selection for the Bayesian Quantile Regression

2021-07-18 · David Kohns, Tibor Szendrei

This paper extends the idea of decoupling shrinkage and sparsity for continuous priors to Bayesian Quantile Regression (BQR). The procedure follows two steps: In the first step, we shrink the quantile regression posterio…

quantile regressionregressionvalidVariable Selection

Automatic Inference for Value-Added Regressions

2025-03-24 · Tian Xie

It is common to use shrinkage methods such as empirical Bayes to improve estimates of teacher value-added. However, when the goal is to perform inference on coefficients in the regression of long-term outcomes on value-a…

regression

Liu-type Shrinkage Estimators for Mixture of Poisson Regressions with Experts: A Heart Disease Study

2023-09-11 · Elsayed Ghanem, Moein Yoosefi, Armin Hatefi

Count data play a critical role in medical research, such as heart disease. The Poisson regression model is a common technique for evaluating the impact of a set of covariates on the count responses. The mixture of Poiss…

regression