Search Results for author:
Found 6 papers, 4 papers with code
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
We further demonstrate the effectiveness of our multi-modal reinforced training by training a CLIP model based on ViT-B/16 image backbone and achieving +2. 9% average performance improvement on 38 evaluation benchmarks compared to the previous best.
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
To this end, we introduce a novel token mixing operator, RepMixer, a building block of FastViT, that uses structural reparameterization to lower the memory access cost by removing skip-connections in the network.
MobileOne: An Improved One millisecond Mobile Backbone
Furthermore, we show that our model generalizes to multiple tasks - image classification, object detection, and semantic segmentation with significant improvements in latency and accuracy as compared to existing efficient architectures when deployed on a mobile device.
Ranked #583 on
Image Classification
on ImageNet
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model.
Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
When applied to datasets where one or more tasks can have noisy annotations, the proposed method learns to prioritize learning from clean labels for a given task, e. g. reducing surface estimation errors by up to 60%.
