Relationnet2: Deep Comparison Columns For Few-shot Learning

Abstract

Few-shot deep learning is a topical challenge area for scaling visual recognition to open ended growth of unseen new classes with limited labeled examples. A promising approach is based on metric learning, which trains a deep embedding to support image similarity matching. Our insight is that effective general purpose matching requires non-linear comparison of features at multiple abstraction levels. We thus propose a new deep comparison network comprised of embedding and relation modules that learn multiple non-linear distance metrics based on different levels of features simultaneously. Furthermore, to reduce over-fitting and enable the use of deeper embeddings, we represent images as distributions rather than vectors via learning parameterized Gaussian noise regularization. The resulting network achieves excellent performance on both miniImageNet and tieredImageNet.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2018relationnet2

Related papers

• Revisiting Metric Learning For Few-shot Image Classification (2019)14.90
• Object-level Representation Learning For Few-shot Image Classification (2018)0.00
• Rankdnn: Learning To Rank For Few-shot Learning (2022)12.58
• Compare More Nuanced:pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning (2019)11.39
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification (2020)20.42
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Deepsim-nets: Deep Similarity Networks For Stereo Image Matching (2023)5.24