paper-with-me

Papers

Localization with Sampling-Argmax

2021-10-17 · NeurIPS 2021 12 · Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-Lu Li, Cewu Lu

Soft-argmax operation is commonly adopted in detection-based methods to localize the target position in a differentiable manner. However, training the neural network with soft-argmax makes the shape of the probability map unconstrained. Consequently, the model lacks pixel-wise supervision through the map during training, leading to performance degradation. In this work, we propose sampling-argmax, a differentiable training method that imposes implicit constraints to the shape of the probability map by minimizing the expectation of the localization error. To approximate the expectation, we introduce a continuous formulation of the output distribution and develop a differentiable sampling process. The expectation can be approximated by calculating the average error of all samples drawn from the output distribution. We show that sampling-argmax can seamlessly replace the conventional soft-argmax operation on various localization tasks. Comprehensive experiments demonstrate the effectiveness and flexibility of the proposed method. Code is available at https://github.com/Jeff-sjtu/sampling-argmax

📄 PDF Abstract BibTeX arXiv:2110.08825

Code (1)

Jeff-sjtu/sampling-argmax 공식 구현 pytorch

Tasks

3D Human Pose Estimation

Similar Papers 제목 키워드 기반

Argmax Flows: Learning Categorical Distributions with Normalizing Flows

2020-11-23 · pproximateinference AABI Symposium 2021 1 · Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré 외

This paper introduces a new method to define and train continuous distributions such as normalizing flows directly on categorical data, for example text and image segmentation. The generative model is defined by a compos…

Image SegmentationSemantic Segmentation

The Sampling-Gaussian for stereo matching

2024-10-09 · Baiyu Pan, Jichao Jiao, Bowen Yao, Jianxin Pang 외

The soft-argmax operation is widely adopted in neural network-based stereo matching methods to enable differentiable regression of disparity. However, network trained with soft-argmax is prone to being multimodal due to …

Stereo Matching

Building a stable classifier with the inflated argmax

2024-05-22 · Jake A. Soloff, Rina Foygel Barber, Rebecca Willett

We propose a new framework for algorithmic stability in the context of multiclass classification. In practice, classification algorithms often operate by first assigning a continuous score (for instance, an estimated pro…

A Generalized Argmax Theorem with Applications

2022-09-19 · Gregory Cox

The argmax theorem is a useful result for deriving the limiting distribution of estimators in many applications. The conclusion of the argmax theorem states that the argmax of a sequence of stochastic processes converges…

Optimal Exploration is no harder than Thompson Sampling

2023-10-09 · Zhaoqi Li, Kevin Jamieson, Lalit Jain

Given a set of arms $\mathcal{Z}\subset \mathbb{R}^d$ and an unknown parameter vector $\theta_\ast\in\mathbb{R}^d$, the pure exploration linear bandit problem aims to return $\arg\max_{z\in \mathcal{Z}} z^{\top}\theta_{\…

Thompson Sampling