Contrastive Learning for Object Detection
Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the requirement of large batch sizes and memory banks has made it difficult and slow to train. This has motivated the rise of Supervised Contrasative approaches that overcome these problems by using annotated data. We look to further improve supervised contrastive learning by ranking classes based on their similarity, and observe the impact of human bias (in the form of ranking) on the learned representations. We feel this is an important question to address, as learning good feature embeddings has been a long sought after problem in computer vision.
Code (1)
Tasks
Contrastive LearningObjectobject-detectionObject DetectionSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
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 ke…
Contrastive LearningCross-Domain Few-Shot Object DetectionFew-Shot LearningFew-Shot Object Detection+4Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection
Contrastive learning has emerged as a competitive pretraining method for object detection. Despite this progress, there has been minimal investigation into the robustness of contrastively pretrained detectors when faced …
Contrastive LearningObjectobject-detectionObject DetectionVideo Salient Object Detection via Contrastive Features and Attention Modules
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, t…
Contrastive LearningObjectobject-detectionObject Detection+7Aligning Pretraining for Detection via Object-Level Contrastive Learning
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a…
Contrastive LearningObjectobject-detectionObject Detection+4DetCo: Unsupervised Contrastive Learning for Object Detection
Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive l…
Contrastive Learningimage-classificationImage ClassificationObject+1