Paper Reading AI Learner

Open-world Contrastive Learning

2022-08-04 16:48:02
Yiyou Sun, Yixuan Li

Abstract

Recent advance in contrastive learning has shown remarkable performance. However, the vast majority of approaches are limited to the closed-world setting. In this paper, we enrich the landscape of representation learning by tapping into an open-world setting, where unlabeled samples from novel classes can naturally emerge in the wild. To bridge the gap, we introduce a new learning framework, open-world contrastive learning (OpenCon). OpenCon tackles the challenges of learning compact representations for both known and novel classes, and facilitates novelty discovery along the way. We demonstrate the effectiveness of OpenCon on challenging benchmark datasets and establish competitive performance. On the ImageNet dataset, OpenCon significantly outperforms the current best method by 11.9% and 7.4% on novel and overall classification accuracy, respectively. We hope that our work will open up new doors for future work to tackle this important problem.

Abstract (translated)

URL

https://arxiv.org/abs/2208.02764

PDF

https://arxiv.org/pdf/2208.02764


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Attention Autonomous Bert Boundary_Detection Caption Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Drone Dynamic_Memory_Network Edge_Detection Embedding Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot