Delta-encoder: An Effective Sample Synthesis Method For Few-shot Object Recognition

Authors:
Eli Schwartz IBM-Research
Leonid Karlinsky IBM-Research
Joseph Shtok IBM-Reseach
Sivan Harary IBM-Research
Mattias Marder IBM-Research
Abhishek Kumar Google
Rogerio Feris IBM Research AI
Raja Giryes Tel Aviv University
Alex Bronstein Technion

Introduction:

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision.In this work, the authors propose a simple yet effective method for few-shot (and one-shot) object recognition.

Abstract:

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we propose a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or "deltas", between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves the state-of-the-art of one-shot object-recognition and performs comparably in the few-shot case.

You may want to know: