Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Peng, Liangzu"'
The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks. Howev
Externí odkaz:
http://arxiv.org/abs/2410.00645
Autor:
Peng, Liangzu, Yin, Wotao
Block coordinate descent is a powerful algorithmic template suitable for big data optimization. This template admits a lot of variants including block gradient descent (BGD), which performs gradient descent on a selected block of variables, while kee
Externí odkaz:
http://arxiv.org/abs/2405.16020
Estimating the rigid transformation with 6 degrees of freedom based on a putative 3D correspondence set is a crucial procedure in point cloud registration. Existing correspondence identification methods usually lead to large outlier ratios ($>$ 95 $\
Externí odkaz:
http://arxiv.org/abs/2404.06155
Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible. This is an important problem in computer vision, for which many highly accura
Externí odkaz:
http://arxiv.org/abs/2404.00915
Autor:
Peng, Liangzu, Vidal, René
Block coordinate descent is an optimization paradigm that iteratively updates one block of variables at a time, making it quite amenable to big data applications due to its scalability and performance. Its convergence behavior has been extensively st
Externí odkaz:
http://arxiv.org/abs/2305.14744
The goal of continual learning is to find a model that solves multiple learning tasks which are presented sequentially to the learner. A key challenge in this setting is that the learner may forget how to solve a previous task when learning a new tas
Externí odkaz:
http://arxiv.org/abs/2305.00316
Branch-and-bound-based consensus maximization stands out due to its important ability of retrieving the globally optimal solution to outlier-affected geometric problems. However, while the discovery of such solutions caries high scientific value, its
Externí odkaz:
http://arxiv.org/abs/2304.05156
We advance both the theory and practice of robust $\ell_p$-quasinorm regression for $p \in (0,1]$ by using novel variants of iteratively reweighted least-squares (IRLS) to solve the underlying non-smooth problem. In the convex case, $p=1$, we prove t
Externí odkaz:
http://arxiv.org/abs/2208.11846
The rotation search problem aims to find a 3D rotation that best aligns a given number of point pairs. To induce robustness against outliers for rotation search, prior work considers truncated least-squares (TLS), which is a non-convex optimization p
Externí odkaz:
http://arxiv.org/abs/2207.08350
This paper is about the old Wahba problem in its more general form, which we call "simultaneous rotation and correspondence search". In this generalization we need to find a rotation that best aligns two partially overlapping $3$D point sets, of size
Externí odkaz:
http://arxiv.org/abs/2203.14493