Few-shot Action Recognition with Prototype-centered Attentive Learning
- URL: http://arxiv.org/abs/2101.08085v2
- Date: Wed, 3 Feb 2021 23:39:54 GMT
- Title: Few-shot Action Recognition with Prototype-centered Attentive Learning
- Authors: Xiatian Zhu and Antoine Toisoul and Juan-Manuel Prez-Ra and Li Zhang
and Brais Martinez and Tao Xiang
- Abstract summary: Prototype-centered Attentive Learning (PAL) model composed of two novel components.
First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective.
Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
- Score: 88.10852114988829
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Few-shot action recognition aims to recognize action classes with few
training samples. Most existing methods adopt a meta-learning approach with
episodic training. In each episode, the few samples in a meta-training task are
split into support and query sets. The former is used to build a classifier,
which is then evaluated on the latter using a query-centered loss for model
updating. There are however two major limitations: lack of data efficiency due
to the query-centered only loss design and inability to deal with the support
set outlying samples and inter-class distribution overlapping problems. In this
paper, we overcome both limitations by proposing a new Prototype-centered
Attentive Learning (PAL) model composed of two novel components. First, a
prototype-centered contrastive learning loss is introduced to complement the
conventional query-centered learning objective, in order to make full use of
the limited training samples in each episode. Second, PAL further integrates a
hybrid attentive learning mechanism that can minimize the negative impacts of
outliers and promote class separation. Extensive experiments on four standard
few-shot action benchmarks show that our method clearly outperforms previous
state-of-the-art methods, with the improvement particularly significant (10+\%)
on the most challenging fine-grained action recognition benchmark.
Related papers
- Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple
Logits Retargeting Approach [102.0769560460338]
We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class.
Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
arXiv Detail & Related papers (2024-03-01T03:27:08Z) - Partner-Assisted Learning for Few-Shot Image Classification [54.66864961784989]
Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation.
In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples.
We propose a two-stage training scheme, which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance.
arXiv Detail & Related papers (2021-09-15T22:46:19Z) - Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and
Contrastive Meta-Learning [51.03781020616402]
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications.
We propose a few-shot fine-grained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class.
Although progress has been made in coarse-grained actions, existing few-shot recognition methods encounter two issues handling fine-grained actions.
arXiv Detail & Related papers (2021-08-15T02:21:01Z) - Trainable Class Prototypes for Few-Shot Learning [5.481942307939029]
We propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework.
Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning.
Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset.
arXiv Detail & Related papers (2021-06-21T04:19:56Z) - Contrastive Prototype Learning with Augmented Embeddings for Few-Shot
Learning [58.2091760793799]
We propose a novel contrastive prototype learning with augmented embeddings (CPLAE) model.
With a class prototype as an anchor, CPL aims to pull the query samples of the same class closer and those of different classes further away.
Extensive experiments on several benchmarks demonstrate that our proposed CPLAE achieves new state-of-the-art.
arXiv Detail & Related papers (2021-01-23T13:22:44Z) - Few-Shot Image Classification via Contrastive Self-Supervised Learning [5.878021051195956]
We propose a new paradigm of unsupervised few-shot learning to repair the deficiencies.
We solve the few-shot tasks in two phases: meta-training a transferable feature extractor via contrastive self-supervised learning.
Our method achieves state of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification datasets.
arXiv Detail & Related papers (2020-08-23T02:24:31Z) - One-Shot Object Detection without Fine-Tuning [62.39210447209698]
We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module.
We also propose novel training strategies that effectively improve detection performance.
Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
arXiv Detail & Related papers (2020-05-08T01:59:23Z)
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.