Attention-Guided Masked Autoencoders For Learning Image Representations
원문 초록
Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to inform the reconstruction process through an attention-guided loss function. By leveraging advances in unsupervised object discovery, we obtain an attention map of the scene which we employ in the loss function to put increased emphasis on reconstructing relevant objects, thus effectively incentivizing the model to learn more object-focused representations without compromising the established masking strategy. Our evaluations show that our pre-trained models learn better latent representations than the vanilla MAE, demonstrated by improved linear probing and k-NN classification results on several benchmarks while at the same time making ViTs more robust against varying backgrounds.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Self-Supervised Visual Representation Learning with Semantic Grouping
When Does Pruning Benefit Vision Representations?
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Binding threshold units with artificial oscillatory neurons
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.