[Paper Review] Few-shot Action Recognition with Prototype-centered Attentive Learning

Xiatian Zhu, Antoine Toisoul+4 more|arXiv (Cornell University)|Jan 20, 2021

Human Pose and Action Recognition38 references36 citations

TL;DR

PAL introduces a prototype-centered contrastive loss and a hybrid attentive learning mechanism to improve data efficiency and handle outliers/inter-class overlap in few-shot action recognition, achieving state-of-the-art results on four benchmarks.

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.

Motivation & Objective

• Address data inefficiency and sensitivity to outliers in few-shot action recognition.
• Leverage limited episode data by combining prototype-centered contrastive learning with query-/support-set attention.
• Mitigate inter-class overlap and intra-class outliers through a hybrid attentive learning framework.
• Demonstrate state-of-the-art performance on four standard few-shot action benchmarks, especially fine-grained datasets.

Proposed method

• Adopt a ProtoNet-based framework augmented with Prototype-centered Attentive Learning (PAL).
• Introduce a hybrid attentive learning (HAL) module performing support-set self-attention and query-to-support cross-attention.
• Define a prototype-centered contrastive loss to complement the conventional query-centered objective.
• Compute per-class prototypes from contextually enriched support features and classify queries via cosine similarity to prototypes.
• Pretrain the TSN-based feature embedding network on the full training set before episodic meta-training.
• Train end-to-end in two stages: TSN pretraining, then meta-training with PAL (meta loss + prototype-centered contrastive loss).

Experimental results

Research questions

• RQ1 Can prototype-centered contrastive learning improve data utilization in each episode compared to traditional query-centered losses?
• RQ2 Does hybrid attention on support and query samples reduce the impact of outliers and inter-class overlap in few-shot tasks?
• RQ3 How does PAL perform relative to state-of-the-art methods across coarse-grained and fine-grained action benchmarks?
• RQ4 What is the contribution of pretraining the embedding network to overall performance in few-shot action recognition?

Key findings

• PAL achieves state-of-the-art results across four benchmarks, with notable gains on the fine-grained Sth-Sth-100 dataset (approx. 10% improvement in 5-shot).
• Hybrid Attentive Learning (HAL) and Prototype-centered Contrastive Learning (PCL) provide complementary gains over a pretrained baseline, improving 1-shot and 5-shot accuracy.
• Pretraining of the embedding network is crucial, enabling strong feature representations and reducing reliance on episodic adaptation.
• PAL reduces intra-class variation and inter-class overlap by combining query-centered and prototype-centered signals.
• PAL consistently outperforms OTAM and FEAT on challenging datasets, highlighting robustness to outliers and class overlap.