Instance Similarity Learning for Unsupervised Feature Representation
This work addresses the challenge of obtaining discriminative representations in unsupervised learning for computer vision, though it appears incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of learning unsupervised feature representations by addressing the limitations of Euclidean distance in capturing semantic similarity, proposing an instance similarity learning method that uses GANs to mine the feature manifold and achieves superior performance in image classification compared to state-of-the-art methods.
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature space with high similarity, which usually leads to wrong pairwise relationship for large neighborhoods because the Euclidean distance fails to depict the true semantic similarity on the feature manifold. On the contrary, our method mines the feature manifold in an unsupervised manner, through which the semantic similarity among instances is learned in order to obtain discriminative representations. Specifically, we employ the Generative Adversarial Networks (GAN) to mine the underlying feature manifold, where the generated features are applied as the proxies to progressively explore the feature manifold so that the semantic similarity among instances is acquired as reliable pseudo supervision. Extensive experiments on image classification demonstrate the superiority of our method compared with the state-of-the-art methods. The code is available at https://github.com/ZiweiWangTHU/ISL.git.