English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Segment Anything Model (SAM) has emerged as a powerful tool for numerousvision applications. A key component that drives the impressive performance forzero-shot transfer and high versatility is a super large Transformer modeltrained on the extensive high-quality SA-1B dataset. While beneficial, the hugecomputation cost of SAM model has limited its applications to wider real-worldapplications. To address this limitation, we propose EfficientSAMs,light-weight SAM models that exhibits decent performance with largely reducedcomplexity. Our idea is based on leveraging masked image pretraining, SAMI,which learns to reconstruct features from SAM image encoder for effectivevisual representation learning. Further, we take SAMI-pretrained light-weightimage encoders and mask decoder to build EfficientSAMs, and finetune the modelson SA-1B for segment anything task. We perform evaluations on multiple visiontasks including image classification, object detection, instance segmentation,and semantic object detection, and find that our proposed pretraining method,SAMI, consistently outperforms other masked image pretraining methods. Onsegment anything task such as zero-shot instance segmentation, ourEfficientSAMs with SAMI-pretrained lightweight image encoders perform favorablywith a significant gain (e.g., ~4 AP on COCO/LVIS) over other fast SAM models.

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything