RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

By Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Sharath Pankanti, Rogério Schmidt Feris, Raja Giryes, A. Bronstein. 2018

355 citations recorded by the source corpus.

Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Incremental Few-Shot Object Detection (2020, neutral): “Few-shot object detection and beyond A few recent works have attempted to exploit few-shot learning techniques for object detection [53, 22, 23].”
Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning (2019, background): “More recently, low-shot object detection has been extended from recognition [4, 22, 21].”
Central Similarity Quantization for Efficient Image and Video Retrieval (2019, methodology): “However, we empirically find that learned centers by some common methods [11, 43, 29] cannot provide better hash functions than the analytically constructed ones.”
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (2020, methodology): “Subsequent works [17,8,16,41] strengthen this pipeline by bringing more advanced methods on few-shot image classification, and commonly emphasize to improve classification performance of Region-of-Interest (RoI) in FSOD by using metric learning techniques.”
Any-Shot Object Detection (2020, background): “Later, [15] proposed a distant metric learning-based approach that learned representative vectors to facilitate FSD.”
The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation (2020, background): “For example, AP 1 corresponds to the commonly referred few-shot object detection regime [8], [23], [25].”
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (2020, background): “[46] exploits distance metric learning to model a multi-modal distribution of each object class.”
Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (2019, methodology): “Recent works for few-shot object detection [9, 10, 11, 12] on the other hand all require fine-tuning and thus cannot be directly applied on novel categories.”
Meta-Learning to Detect Rare Objects (2019, methodology): “In particular, our MetaDet, built upon Faster R-CNN with VGG16, outperforms RepMet which uses a more powerful detector architecture (i.e., the FPN backbone [35] in its deformable convolutions variant [10]).”
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation (2020, background): “For example, AP1 corresponds to the commonly referred few-shot object detection regime [8], [23], [25].”
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (2021, methodology): “Note, this is different from the N-Way Kshot settings commonly used in meta-learning based methods [44].”
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, methodology): “RepMet [20] incorporates a modified prototypical network as classification head into a standard object detector.”