Published on Wed Mar 10 2021

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang
0
0
0
Abstract

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive approaches. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intra-class compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https: //github.com/MegviiDetection/FSCE

Thu Apr 15 2021
Computer Vision
Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
Few-shot object detection (FSOD) aims to detect objects using only few examples. We propose a meta-learning based few- shot object detection method. Our method incorporates a coarse-to-fine approach into the proposal based object detection framework.
4
0
1
Thu Oct 22 2020
Artificial Intelligence
Restoring Negative Information in Few-Shot Object Detection
Few-shot learning has recently emerged as a new challenge in the deep learning field. It asks for the generalization of deep neural networks on new classes with few annotated samples. Negatives, especially hard negatives, are essential to the embedding space learning in few-shot object detection.
0
0
0
Wed Dec 30 2020
Machine Learning
MM-FSOD: Meta and metric integrated few-shot object detection
In the object detection task, CNN (Convolutional neural networks) models need a large amount of annotated examples in the training process. We present an effective object detection framework (MM-FSOD) that integrates metric learning and meta-learning.
0
0
0
Mon Mar 01 2021
Computer Vision
Universal-Prototype Enhancing for Few-Shot Object Detection
Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. We propose a new prototype,namely universal prototype, that is learned from all object categories. We impose a consistency loss to maximize the agreement between the enhanced features and original ones.
0
0
0
Fri Mar 16 2018
Computer Vision
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts
Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image. We propose a new experimental protocol for ZSD based on the highly challenging ILSVRC dataset, adhering to the rarity of unseen objects.
0
0
0
Sat Jul 18 2020
Computer Vision
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances. We propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids.
0
0
0