Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining

Abstract

Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector of the embedded support points within a class. The performance of prototypical networks in extreme few-shot scenarios (like one-shot) degrades drastically, mainly due to the desuetude of variations within the clusters while constructing prototypes. In this paper, we propose to replace the typical prototypical loss function with an Episodic Triplet Mining (ETM) technique. The conventional triplet selection leads to overfitting, because of all possible combinations being used during training. We incorporate episodic training for mining the semi hard positive and the semi hard negative triplets to overcome the overfitting. We also propose an adaptation to make use of unlabeled training samples for better modeling. Experimenting on two different audio pro

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybhosale2021semi

Related papers

• Episodic Fine-tuning Prototypical Networks For Optimization-based Few-shot Learning: Application To Audio Classification (2024)2.26
• Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor (2024)6.21
• On The Transferability Of Large-scale Self-supervision To Few-shot Audio Classification (2024)3.58
• Halluaudio: Hallucinating Frequency As Concepts For Few-shot Audio Classification (2023)3.58
• Towards Robust Few-shot Class Incremental Learning In Audio Classification Using Contrastive Representation (2024)4.52
• Few-shot Speaker Identification Using Depthwise Separable Convolutional Network With Channel Attention (2022)5.24
• Few-shot Learning In Emotion Recognition Of Spontaneous Speech Using A Siamese Neural Network With Adaptive Sample Pair Formation (2021)9.92
• Two-stage Triplet Loss Training With Curriculum Augmentation For Audio-visual Retrieval (2023)0.00