ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning
Self-supervised learning (SSL) techniques have recently been integrated into the few-shot learning (FSL) framework and have shown promising results in improving the few-shot image classification performance. However, existing SSL approaches used in FSL typically seek the supervision signals from the global embedding of every single image. Therefore, during the episodic training of FSL, these methods cannot capture and fully utilize the local visual information in image samples and the data structure information of the whole episode, which are beneficial to FSL. To this end, we propose to augment the few-shot learning objective with a novel self-supervised Episodic Spatial Pretext Task (ESPT). Specifically, for each few-shot episode, we generate its corresponding transformed episode by applying a random geometric transformation to all the images in it. Based on these, our ESPT objective is defined as maximizing the local spatial relationship consistency between the original episode and the transformed one. With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples. Extensive experiments indicate that our ESPT method achieves new state-of-the-art performance for few-shot image classification on three mainstay benchmark datasets. The source code will be available at: https://github.com/Whut-YiRong/ESPT.
Code (1)
Tasks
Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage ClassificationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
GeoJEPA: Towards Eliminating Augmentation- and Sampling Bias in Multimodal Geospatial Learning
Existing methods for self-supervised representation learning of geospatial regions and map entities rely extensively on the design of pretext tasks, often involving augmentations or heuristic sampling of positive and neg…
Representation LearningA Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning
High annotation costs and limited labels for dense 3D medical imaging tasks have recently motivated an assortment of 3D self-supervised pretraining methods that improve transfer learning performance. However, these metho…
Image SegmentationMedical Image SegmentationRepresentation LearningSemantic Segmentation+1SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data
In medical image analysis, the cost of acquiring high-quality data and their annotation by experts is a barrier in many medical applications. Most of the techniques used are based on supervised learning framework and nee…
Medical DiagnosisMedical Image AnalysisMedical Image ClassificationMulti-Label Classification+2Self-Supervised Learning of Pretext-Invariant Representations
The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many …
Contrastive Learningobject-detectionObject DetectionRepresentation Learning+3Mixture of Self-Supervised Learning
Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learnin…
Classificationimage-classificationImage ClassificationSelf-Supervised Learning