Represent, Compare, And Learn: A Similarity-aware Framework For Class-agnostic Counting
2022 · Min Shi, Hao Lu, Chen Feng, et al.
Abstract
Class-agnostic counting (CAC) aims to count all instances in a query image given few exemplars. A standard pipeline is to extract visual features from exemplars and match them with query images to infer object counts. Two essential components in this pipeline are feature representation and similarity metric. Existing methods either adopt a pretrained network to represent features or learn a new one, while applying a naive similarity metric with fixed inner product. We find this paradigm leads to noisy similarity matching and hence harms counting performance. In this work, we propose a similarity-aware CAC framework that jointly learns representation and similarity metric. We first instantiate our framework with a naive baseline called Bilinear Matching Network (BMNet), whose key component is a learnable bilinear similarity metric. To further embody the core of our framework, we extend BMNet to BMNet+ that models similarity from three aspects: 1) representing the instances via their sel
Authors
(none)
Tags
Stats
Related papers
- Few-shot Object Counting With Similarity-aware Feature Enhancement (2022)18.62
- Attributable Visual Similarity Learning (2022)11.68
- Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification (2020)20.42
- Effectively Leveraging Attributes For Visual Similarity (2021)3.66
- Conditional Similarity Networks (2016)15.06
- Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
- Genecis: A Benchmark For General Conditional Image Similarity (2023)10.07
- Cross-domain Visual Matching Via Generalized Similarity Measure And Feature Learning (2016)15.54