English
Related papers

Related papers: Baseline Desensitizing In Translation Averaging

200 papers

Gradient-based interpretations often require an anchor point of comparison to avoid saturation in computing feature importance. We show that current baselines defined using static functions--constant mapping, averaging or blurring--inject…

Machine Learning · Computer Science 2025-02-12 Ching Lam Choi , Alexandre Duplessis , Serge Belongie

We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace standard empirical…

Machine Learning · Computer Science 2026-01-27 Javier Porras-Valenzuela , Samar Hadou , Alejandro Ribeiro

Layer normalization (LayerNorm) is a technique to normalize the distributions of intermediate layers. It enables smoother gradients, faster training, and better generalization accuracy. However, it is still unclear where the effectiveness…

Machine Learning · Computer Science 2019-11-19 Jingjing Xu , Xu Sun , Zhiyuan Zhang , Guangxiang Zhao , Junyang Lin

This paper presents a family of algorithms for decentralized convex composite problems. We consider the setting of a network of agents that cooperatively minimize a global objective function composed of a sum of local functions plus a…

Optimization and Control · Mathematics 2023-02-14 Yichuan Li , Petros G. Voulgaris , Dusan M. Stipanovic , Nikolaos M. Freris

Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the…

Computation and Language · Computer Science 2020-09-22 Pei Zhang , Boxing Chen , Niyu Ge , Kai Fan

In a recent, strongly emergent literature on few-shot CLIP adaptation, Linear Probe (LP) has been often reported as a weak baseline. This has motivated intensive research building convoluted prompt learning or feature adaptation strategies.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Yunshi Huang , Fereshteh Shakeri , Jose Dolz , Malik Boudiaf , Houda Bahig , Ismail Ben Ayed

Surface normal estimation from a single image is an important task in 3D scene understanding. In this paper, we address two limitations shared by the existing methods: the inability to estimate the aleatoric uncertainty and lack of detail…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Gwangbin Bae , Ignas Budvytis , Roberto Cipolla

The reduced basis method is a powerful model reduction technique designed to speed up the computation of multiple numerical solutions of parametrized partial differential equations. We consider a quantity of interest, which is a linear…

Analysis of PDEs · Mathematics 2014-07-11 Alexandre Janon , Maëlle Nodet , Clémentine Prieur

The purpose of this paper is to introduce a very efficient algorithm for signal extrapolation. It can widely be used in many applications in image and video communication, e. g. for concealment of block errors caused by transmission errors…

Image and Video Processing · Electrical Eng. & Systems 2022-07-05 Jürgen Seiler , André Kaup

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

Computation and Language · Computer Science 2020-10-07 Shijie Wu , Mark Dredze

We propose a general scheme for solving convex and non-convex optimization problems on manifolds. The central idea is that, by adding a multiple of the squared retraction distance to the objective function in question, we "convexify" the…

Computation · Statistics 2020-10-20 Lizhen Lin , Bayan Saparbayeva , Michael Minyi Zhang , David B. Dunson

Many applications in vision require estimation of thin structures such as boundary edges, surfaces, roads, blood vessels, neurons, etc. Unlike most previous approaches, we simultaneously detect and delineate thin structures with sub-pixel…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Dmitrii Marin , Yuri Boykov , Yuchen Zhong

Algorithmic Bias can be due to bias in the training data or issues with the algorithm itself. These algorithmic issues typically relate to problems with model capacity and regularisation. This underestimation bias may arise because the…

Machine Learning · Computer Science 2021-06-01 William Blanzeisky , Pádraig Cunningham

Bundle adjustment (BA) is a technique for refining sensor orientations of satellite images, while adjustment accuracy is correlated with feature matching results. Feature match-ing often contains high uncertainties in weak/repeat textures,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Xiao Ling , Xu Huang , Rongjun Qin

In transfer learning, the learner leverages auxiliary data to improve generalization on a main task. However, the precise theoretical understanding of when and how auxiliary data help remains incomplete. We provide new insights on this…

Machine Learning · Computer Science 2026-03-31 Meitong Liu , Christopher Jung , Rui Li , Xue Feng , Han Zhao

Many applications in signal processing benefit from the sparsity of signals in a certain transform domain or dictionary. Synthesis sparsifying dictionaries that are directly adapted to data have been popular in applications such as image…

Machine Learning · Statistics 2015-06-23 Saiprasad Ravishankar , Yoram Bresler

Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…

Computation and Language · Computer Science 2022-01-20 Yilin Yang , Akiko Eriguchi , Alexandre Muzio , Prasad Tadepalli , Stefan Lee , Hany Hassan

Multi-task learning with an unbalanced data distribution skews model learning towards high resource tasks, especially when model capacity is fixed and fully shared across all tasks. Sparse scaling architectures, such as BASELayers, provide…

Computation and Language · Computer Science 2021-10-18 Dheeru Dua , Shruti Bhosale , Vedanuj Goswami , James Cross , Mike Lewis , Angela Fan

Pose-Graph optimization is a crucial component of many modern SLAM systems. Most prominent state of the art systems address this problem by iterative non-linear least squares. Both number of iterations and convergence basin of these…

Robotics · Computer Science 2018-09-05 Irvin Aloise , Giorgio Grisetti

A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued to constitute a more…

Machine Learning · Computer Science 2026-03-11 George Bird