CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition

• URL: http://arxiv.org/abs/2004.09215v1
• Date: Mon, 20 Apr 2020 11:36:02 GMT
• Title: CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition
• Abstract summary: Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. Traditional deep learning methods require storing all previous class samples in the system and training the model again from scratch. In this work, we demonstrate a lifelong 3D convolutional framework -- c(C)la(a)ss increment(t)al net(Net)work (CatNet) We propose a two-stream CatNet, which deploys RGB and depth modalities to train two separate networks.
• Score: 24.706843543488763
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for real-world applications is that may easily become necessary to add new gestures to the system e.g., a proper VR system should allow users to customize gestures incrementally. Traditional deep learning methods require storing all previous class samples in the system and training the model again from scratch by incorporating previous samples and new samples, which costs humongous memory and significantly increases computation over time. In this work, we demonstrate a lifelong 3D convolutional framework -- c(C)la(a)ss increment(t)al net(Net)work (CatNet), which considers temporal information in videos and enables lifelong learning for egocentric gesture video recognition by learning the feature representation of an exemplar set selected from previous class samples. Importantly, we propose a two-stream CatNet, which deploys RGB and depth modalities to train two separate networks. We evaluate CatNets on a publicly available dataset -- EgoGesture dataset, and show that CatNets can learn many classes incrementally over a long period of time. Results also demonstrate that the two-stream architecture achieves the best performance on both joint training and class incremental training compared to 3 other one-stream architectures. The codes and pre-trained models used in this work are provided at https://github.com/villawang/CatNet.

Related papers

• Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor [9.54964908165465]
  This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning problem in 3D point cloud environments. We leverage a foundational 3D model trained extensively on point cloud data. Our approach uses a dual cache system: first, it uses previous test samples based on how confident the model was in its predictions to prevent forgetting, and second, it includes a small number of new task samples to prevent overfitting.
  arXiv  Detail & Related papers  (2024-10-11T20:23:00Z)
• Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment [55.11291053011696]
  This work presents a framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy. In the limited reconstruction case, our proposed approach, termed WS3D++, ranks 1st on the large-scale ScanNet benchmark.
  arXiv  Detail & Related papers  (2023-12-01T15:47:04Z)
• Learning from One Continuous Video Stream [70.30084026960819]
  We introduce a framework for online learning from a single continuous video stream. This poses great challenges given the high correlation between consecutive video frames. We employ pixel-to-pixel modelling as a practical and flexible way to switch between pre-training and single-stream evaluation.
  arXiv  Detail & Related papers  (2023-12-01T14:03:30Z)
• AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration [69.21282992341007]
  Auto Synth automatically generates 3D training data for point cloud registration. We replace the point cloud registration network with a much smaller surrogate network, leading to a $4056.43$ speedup. Our results on TUD-L, LINEMOD and Occluded-LINEMOD evidence that a neural network trained on our searched dataset yields consistently better performance than the same one trained on the widely used ModelNet40 dataset.
  arXiv  Detail & Related papers  (2023-09-20T09:29:44Z)
• Dynamic Clustering Transformer Network for Point Cloud Segmentation [23.149220817575195]
  We propose a novel 3D point cloud representation network, called Dynamic Clustering Transformer Network (DCTNet) It has an encoder-decoder architecture, allowing for both local and global feature learning. Our method was evaluated on an object-based dataset (ShapeNet), an urban navigation dataset (Toronto-3D), and a multispectral LiDAR dataset.
  arXiv  Detail & Related papers  (2023-05-30T01:11:05Z)
• Human activity recognition using deep learning approaches and single frame cnn and convolutional lstm [0.0]
  We explore two deep learning-based approaches, namely single frame Convolutional Neural Networks (CNNs) and convolutional Long Short-Term Memory to recognise human actions from videos. The two models were trained and evaluated on a benchmark action recognition dataset, UCF50, and another dataset that was created for the experimentation. Though both models exhibit good accuracies, the single frame CNN model outperforms the Convolutional LSTM model by having an accuracy of 99.8% with the UCF50 dataset.
  arXiv  Detail & Related papers  (2023-04-18T01:33:29Z)
• What Makes for Effective Few-shot Point Cloud Classification? [18.62689395276194]
  We show that 3D few-shot learning is more challenging with unordered structures, high intra-class variances, and subtle inter-class differences. We propose a novel plug-and-play component called Cross-Instance Adaptation (CIA) module, to address the high intra-class variances and subtle inter-class differences issues.
  arXiv  Detail & Related papers  (2023-03-31T15:55:06Z)
• ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding [110.07170245531464]
  Current 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. Recent advances have shown that similar problems can be significantly alleviated by employing knowledge from other modalities, such as language. We learn a unified representation of images, texts, and 3D point clouds by pre-training with object triplets from the three modalities.
  arXiv  Detail & Related papers  (2022-12-10T01:34:47Z)
• Cross-Modal Adapter for Vision-Language Retrieval [60.59577149733934]
  We present a novel Cross-Modal Adapter for parameter-efficient transfer learning.<n>Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers.<n>Our approach has three notable benefits: (1) reduces the vast majority of fine-tuned parameters, (2) saves training time, and (3) allows all the pre-trained parameters to be fixed.
  arXiv  Detail & Related papers  (2022-11-17T16:15:30Z)
• Learning Rate Curriculum [75.98230528486401]
  We propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC) LeRaC uses a different learning rate for each layer of a neural network to create a data-agnostic curriculum during the initial training epochs. We compare our approach with Curriculum by Smoothing (CBS), a state-of-the-art data-agnostic curriculum learning approach.
  arXiv  Detail & Related papers  (2022-05-18T18:57:36Z)
• Optimization Planning for 3D ConvNets [123.43419144051703]
  It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. We decompose the path into a series of training "states" and specify the hyper- parameters, e.g., learning rate and the length of input clips, in each state. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path.
  arXiv  Detail & Related papers  (2022-01-11T16:13:31Z)
• Learning Compositional Shape Priors for Few-Shot 3D Reconstruction [36.40776735291117]
  We show that complex encoder-decoder architectures exploit large amounts of per-category data. We propose three ways to learn a class-specific global shape prior, directly from data. Experiments on the popular ShapeNet dataset show that our method outperforms a zero-shot baseline by over 40%.
  arXiv  Detail & Related papers  (2021-06-11T14:55:49Z)
• 2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework [57.847010327319964]
  We propose a data-efficient framework that can train the model from scratch on small datasets. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D neural network-based two-stream framework. It is proved that our method can achieve a promising result even without a pre-trained model on large scale datasets.
  arXiv  Detail & Related papers  (2020-08-10T09:50:28Z)

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.