Abstract

$\Delta$-ENCODER：學習僅基於一個或幾個示例對新類別進行分類是現代計算機視覺中的一個長期挑戰。在這項工作中，我們提出了一種簡單而有效的方法，用於少樣本（和單樣本）物體識別。我們的方法基於一個改進的自動編碼器，表示為 $\Delta$-encoder ，可以通過檢視來自其中的幾個示例來學習合成未見類別的新的樣本。然後將合成的樣本用於訓練分類器。** 所提出的方法學習提取同類訓練例項對之間的可遷移的類內變形或“變化”，並將這些變化應用於少數提供的新類別（訓練階段未見）的例子，以便有效地合成新類別的樣本。** 所提出的方法改善了單樣本物體識別中的最新技術，並且在少數情況下比較有利。一經接受，程式碼將被提供。

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 proposes 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 over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case. Upon acceptance code will be made available.

問題

小樣本問題。具體來說是解決樣本不足的問題。

方法

一種基於自編碼器的樣本生成方法。具體來說，提取訓練類別的例項對之間的變化/差異，將該差異應用在僅有的新類別的少數樣本上，生成新的樣本。

資料

輸入：2048維的VGG或Resnet特徵 輸出：1024個新類的樣本