Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstruction

• URL: http://arxiv.org/abs/2406.15982v1
• Date: Sun, 23 Jun 2024 02:21:48 GMT
• Title: Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstruction
• Authors: Yangdi Lu, Wenbo He,
• Abstract summary: We propose a formal definition unify the analysis of LNGT LNGT in the context of different machine learning tasks. We provide in-depth analysis on memorization effect and insightful discussion about potential future research opportunities.
• Score: 13.314778587751588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks has been highly successful in data-intense computer vision applications, while such success relies heavily on the massive and clean data. In real-world scenarios, clean data sometimes is difficult to obtain. For example, in image classification and segmentation tasks, precise annotations of millions samples are generally very expensive and time-consuming. In 3D static scene reconstruction task, most NeRF related methods require the foundational assumption of the static scene (e.g. consistent lighting condition and persistent object positions), which is often violated in real-world scenarios. To address these problem, learning with noisy ground truth (LNGT) has emerged as an effective learning method and shows great potential. In this short survey, we propose a formal definition unify the analysis of LNGT LNGT in the context of different machine learning tasks (classification and regression). Based on this definition, we propose a novel taxonomy to classify the existing work according to the error decomposition with the fundamental definition of machine learning. Further, we provide in-depth analysis on memorization effect and insightful discussion about potential future research opportunities from 2D classification to 3D reconstruction, in the hope of providing guidance to follow-up research.

Related papers

• Self-supervised cross-modality learning for uncertainty-aware object detection and recognition in applications which lack pre-labelled training data [6.892494758401737]
  We show how an uncertainty-aware, deep neural network can be trained to detect, recognise and localise objects in 2D RGB images. Our method can be applied to many important industrial tasks, where labelled datasets are typically unavailable.
  arXiv  Detail & Related papers  (2024-11-05T13:26:31Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [62.663113296987085]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. We introduce two novel components: the Redundant Feature Eliminator (RFE) and the Spatial Noise Compensator (SNC) Considering the imbalance in existing 3D datasets, we also propose new evaluation metrics that offer a more nuanced assessment of a 3D FSCIL model.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Recovering 3D Human Mesh from Monocular Images: A Survey [49.00136388529404]
  Estimating human pose and shape from monocular images is a long-standing problem in computer vision. This survey focuses on the task of monocular 3D human mesh recovery.
  arXiv  Detail & Related papers  (2022-03-03T18:56:08Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Secrets of 3D Implicit Object Shape Reconstruction in the Wild [92.5554695397653]
  Reconstructing high-fidelity 3D objects from sparse, partial observation is crucial for various applications in computer vision, robotics, and graphics. Recent neural implicit modeling methods show promising results on synthetic or dense datasets. But, they perform poorly on real-world data that is sparse and noisy. This paper analyzes the root cause of such deficient performance of a popular neural implicit model.
  arXiv  Detail & Related papers  (2021-01-18T03:24:48Z)
• 3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks [0.0]
  We propose a new deep transfer learning approach based on a dynamic architectural method to make robots capable of open-ended learning about new 3D object categories. Experimental results showed that the proposed model outperformed state-of-the-art approaches with regards to accuracy and also substantially minimizes computational overhead.
  arXiv  Detail & Related papers  (2020-09-15T16:44:18Z)

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.