PaperSummary16 : Continual unsupervised representation learningThe paper addresses the challenge of unsupervised continual learning, focusing on learning representations sequentially on task labels…1d ago1d ago
PaperSummary15 : Hopfield Networks is all you needThis paper enhances Hopfield networks, traditionally associative memory systems, by developing a modern variant with continuous states…2d ago2d ago
PaperSummary14 : SupMAEThe paper introduces SupMAE, a novel approach to supervised pre-training of vision transformers by integrating supervised learning into…3d ago3d ago
PaperSummary13 : MAEThe paper presents Masked Autoencoders (MAEs) as a simple yet scalable self-supervised learning approach for computer vision. Inspired by…4d ago4d ago
PaperSummary12 : Orthogonal Adaptation for modular customization of diffusion modelsThe paper introduces “Orthogonal Adaptation” a new approach for modular customization of text-to-image diffusion models. Traditional…5d ago5d ago
PaperSummary11 : MP-PolarMaskThe paper proposes MP-PolarMask, an extension of PolarMask using multiple auxiliary polar systems, to better handle complex shapes like…6d ago6d ago
PaperSummary10 : Applying eigencontours to polar mask-based instance segmentationThe paper discusses enhancing instance segmentation, which identifies object boundaries in images using eigencontours. Eigencontours are…Jan 10Jan 10
PaperSummary09 : PolarMask++The paper proposes PolarMask++, a framework that uses polar representation for efficient single-shot instance segmentation. It…Jan 9Jan 9
PaperSummary08 : PolarMaskThe paper introduces, PolarMask, an anchor box-free, single shot instance segmentation method. It uses polar coordinates to predict…Jan 8Jan 8
