-
Constellation Loss: Improving the efficiency of deep metric learning loss functions for optimal embedding
Metric learning has become an attractive field for research on the lates...
read it
-
Few-Shot Learning with Global Class Representations
In this paper, we propose to tackle the challenging few-shot learning (F...
read it
-
Smart Mining for Deep Metric Learning
To solve deep metric learning problems and producing feature embeddings,...
read it
-
Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem
Variants of Triplet networks are robust entities for learning a discrimi...
read it
-
TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification
The field of Few-Shot Learning (FSL), or learning from very few (typical...
read it
-
Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches
We analyze the effect of offline and online triplet mining for colorecta...
read it
-
Few-shot Action Recognition with Prototype-centered Attentive Learning
Few-shot action recognition aims to recognize action classes with few tr...
read it
Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining
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 processing tasks, namely speaker recognition and audio event detection; show improved performances and hence the efficacy of ETM over the prototypical loss function and other meta-learning frameworks. Further, we show improved performances when unlabeled training samples are used.
READ FULL TEXT
Comments
There are no comments yet.