FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
- URL: http://arxiv.org/abs/2103.05950v1
- Date: Wed, 10 Mar 2021 09:15:05 GMT
- Title: FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
- Authors: Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang
- Abstract summary: We present Few-Shot object detection via Contrastive proposals (FSCE)
FSCE is a simple yet effective approach to learning contrastive-aware object encodings that facilitate the classification of detected objects.
Our design outperforms current state-of-the-art works in any shot and all data, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging benchmark.
- Score: 14.896822373116729
- License: http://creativecommons.org/licenses/by/4.0/
- 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/bsun0802/FSCE.git
Related papers
- Zero-shot Object Counting with Good Exemplars [35.7544908318547]
Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations.
We propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework.
VA-Count consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification while minimizing the consequences of incorrect object identification.
arXiv Detail & Related papers (2024-07-06T03:37:22Z) - Proposal-Contrastive Pretraining for Object Detection from Fewer Data [11.416621957617334]
We present Proposal Selection Contrast (ProSeCo), a novel unsupervised overall pretraining approach.
ProSeCo uses the large number of object proposals generated by the detector for contrastive learning.
We show that our method outperforms state of the art in unsupervised pretraining for object detection on standard and novel benchmarks.
arXiv Detail & Related papers (2023-10-25T17:59:26Z) - Few-shot Object Detection in Remote Sensing: Lifting the Curse of
Incompletely Annotated Novel Objects [23.171410277239534]
We propose a self-training-based FSOD (ST-FSOD) approach to object detection.
Our proposed method outperforms the state-of-the-art in various FSOD settings by a large margin.
arXiv Detail & Related papers (2023-09-19T13:00:25Z) - SOOD: Towards Semi-Supervised Oriented Object Detection [57.05141794402972]
This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework.
Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark.
arXiv Detail & Related papers (2023-04-10T11:10:42Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs.
We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset.
Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
arXiv Detail & Related papers (2022-03-10T23:35:00Z) - Robust Region Feature Synthesizer for Zero-Shot Object Detection [87.79902339984142]
We build a novel zero-shot object detection framework that contains an Intra-class Semantic Diverging component and an Inter-class Structure Preserving component.
It is the first study to carry out zero-shot object detection in remote sensing imagery.
arXiv Detail & Related papers (2022-01-01T03:09:15Z) - Context-Aware Transfer Attacks for Object Detection [51.65308857232767]
We present a new approach to generate context-aware attacks for object detectors.
We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks.
arXiv Detail & Related papers (2021-12-06T18:26:39Z) - Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object.
This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
arXiv Detail & Related papers (2021-08-15T14:36:02Z) - Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with
Attentive Feature Alignment [33.446875089255876]
Few-shot object detection (FSOD) aims to detect objects using only few examples.
We propose a meta-learning based few-shot object detection method by transferring meta-knowledge learned from data-abundant base classes to data-scarce novel classes.
arXiv Detail & Related papers (2021-04-15T19:01:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.