PointNetLK Revisited
- URL: http://arxiv.org/abs/2008.09527v2
- Date: Tue, 30 Mar 2021 02:11:50 GMT
- Title: PointNetLK Revisited
- Authors: Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey
- Abstract summary: We show that PointNetLK can exhibit remarkable generalization properties while reaping the inherent fidelity benefits of a learning framework.
Our approach not only outperforms the state-of-the-art in mismatched conditions but also produces results competitive with current learning methods.
- Score: 37.594591809918185
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We address the generalization ability of recent learning-based point cloud
registration methods. Despite their success, these approaches tend to have poor
performance when applied to mismatched conditions that are not well-represented
in the training set, such as unseen object categories, different complex
scenes, or unknown depth sensors. In these circumstances, it has often been
better to rely on classical non-learning methods (e.g., Iterative Closest
Point), which have better generalization ability. Hybrid learning methods, that
use learning for predicting point correspondences and then a deterministic step
for alignment, have offered some respite, but are still limited in their
generalization abilities. We revisit a recent innovation -- PointNetLK -- and
show that the inclusion of an analytical Jacobian can exhibit remarkable
generalization properties while reaping the inherent fidelity benefits of a
learning framework. Our approach not only outperforms the state-of-the-art in
mismatched conditions but also produces results competitive with current
learning methods when operating on real-world test data close to the training
set.
Related papers
- Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation [5.296260279593993]
Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.
We propose an optimal transport (OT)-guided prompt learning framework that mitigates forgetting by preserving the structural consistency of feature distributions.
Our approach enforces joint constraints on both vision and text representations, ensuring a holistic feature alignment.
arXiv Detail & Related papers (2025-03-11T21:38:34Z) - Probably Approximately Precision and Recall Learning [62.912015491907994]
Precision and Recall are foundational metrics in machine learning.
One-sided feedback--where only positive examples are observed during training--is inherent in many practical problems.
We introduce a PAC learning framework where each hypothesis is represented by a graph, with edges indicating positive interactions.
arXiv Detail & Related papers (2024-11-20T04:21:07Z) - Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation [19.20874993309959]
vision-language foundation models, such as CLIP, have showcased remarkable effectiveness in numerous zero-shot image-level tasks.
We propose a baseline for training-free OVSS, termed Neighbour-Aware CLIP (NACLIP)
Our method enforces localization of patches in the self-attention of CLIP's vision transformer which, despite being crucial for dense prediction tasks, has been overlooked in the OVSS literature.
arXiv Detail & Related papers (2024-04-12T01:08:04Z) - A Unified and General Framework for Continual Learning [58.72671755989431]
Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge.
Various methods have been developed to address the challenge of catastrophic forgetting, including regularization-based, Bayesian-based, and memory-replay-based techniques.
This research aims to bridge this gap by introducing a comprehensive and overarching framework that encompasses and reconciles these existing methodologies.
arXiv Detail & Related papers (2024-03-20T02:21:44Z) - A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity.
Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks.
We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
arXiv Detail & Related papers (2024-02-06T15:45:27Z) - Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot
Filling [2.6056468338837457]
Slot filling poses a critical challenge to handle a novel domain whose samples are never seen during training.
Most prior works deal with this problem in a two-pass pipeline manner based on metric learning.
We propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling.
arXiv Detail & Related papers (2023-10-23T19:01:16Z) - Understanding prompt engineering may not require rethinking
generalization [56.38207873589642]
We show that the discrete nature of prompts, combined with a PAC-Bayes prior given by a language model, results in generalization bounds that are remarkably tight by the standards of the literature.
This work provides a possible justification for the widespread practice of prompt engineering.
arXiv Detail & Related papers (2023-10-06T00:52:48Z) - Efficient Performance Bounds for Primal-Dual Reinforcement Learning from
Demonstrations [1.0609815608017066]
We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations.
Existing inverse reinforcement learning methods come with strong theoretical guarantees, but are computationally expensive.
We introduce a novel bilinear saddle-point framework using Lagrangian duality to bridge the gap between theory and practice.
arXiv Detail & Related papers (2021-12-28T05:47:24Z) - Of Moments and Matching: Trade-offs and Treatments in Imitation Learning [26.121994149869767]
We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching.
By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance.
We derive two novel algorithm templates, AdVIL and AdRIL, with strong guarantees, simple implementation, and competitive empirical performance.
arXiv Detail & Related papers (2021-03-04T18:57:11Z) - A Wholistic View of Continual Learning with Deep Neural Networks:
Forgotten Lessons and the Bridge to Active and Open World Learning [8.188575923130662]
We argue that notable lessons from open set recognition, the identification of statistically deviating data outside of the observed dataset, and the adjacent field of active learning, are frequently overlooked in the deep learning era.
Our results show that this not only benefits each individual paradigm, but highlights the natural synergies in a common framework.
arXiv Detail & Related papers (2020-09-03T16:56:36Z) - DISK: Learning local features with policy gradient [63.12124363163665]
Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints.
We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveraging principles from Reinforcement Learning (RL)
Our simple yet expressive probabilistic model lets us keep the training and inference regimes close, while maintaining good enough convergence properties to reliably train from scratch.
arXiv Detail & Related papers (2020-06-24T08:57:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.