# ML_Decoder
**Repository Path**: davidgao7/ML_Decoder
## Basic Information
- **Project Name**: ML_Decoder
- **Description**: Official PyTorch implementation of "ML-Decoder: Scalable and Versatile Classification Head" (2021)
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2022-02-11
- **Last Updated**: 2022-02-11
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# ML-Decoder: Scalable and Versatile Classification Head
[](https://paperswithcode.com/sota/multi-label-classification-on-ms-coco?p=ml-decoder-scalable-and-versatile)
[](https://paperswithcode.com/sota/multi-label-zero-shot-learning-on-nus-wide?p=ml-decoder-scalable-and-versatile)
[](https://paperswithcode.com/sota/fine-grained-image-classification-on-stanford?p=ml-decoder-scalable-and-versatile)
[](https://paperswithcode.com/sota/multi-label-classification-on-openimages-v6?p=ml-decoder-scalable-and-versatile)
[](https://paperswithcode.com/sota/image-classification-on-cifar-100?p=ml-decoder-scalable-and-versatile)
[Paper](http://arxiv.org/abs/2111.12933) |
[Pretrained Models](MODEL_ZOO.md) |
[Datasets](Datasets.md)
Official PyTorch Implementation
> Tal Ridnik, Gilad Sharir, Avi Ben-Cohen, Emanuel Ben-Baruch, Asaf Noy
>
DAMO Academy, Alibaba
> Group
**Abstract**
In this paper, we introduce ML-Decoder, a new attention-based classification head. ML-Decoder predicts the existence of class labels via queries, and enables better utilization of spatial data compared to global average pooling.
By redesigning the decoder architecture, and using a novel group-decoding scheme, ML-Decoder is highly efficient, and can scale well to thousands of classes. Compared to using a larger backbone, ML-Decoder consistently provides a better speed-accuracy trade-off.
ML-Decoder is also versatile - it can be used as a drop-in replacement for various classification heads, and generalize to unseen classes when operated with word queries. Novel query augmentations further improve its generalization ability.
Using ML-Decoder, we achieve state-of-the-art results on several classification tasks:
on MS-COCO multi-label, we reach 91.4% mAP; on NUS-WIDE zero-shot, we reach 31.1% ZSL mAP; and on ImageNet single-label, we reach with vanilla ResNet50 backbone a new top score of 80.7%, without extra data or distillation.
![]() |
![]() |
![]() |