Carleton College

X-formers can be categorized into:

1. Module-level
2. Architecture-level
3. Pre-training methods
4. Applications

Categorization of Transformer variants

Lin, Tianyang & Wang, Yuxin & Liu, Xiangyang & Qiu, Xipeng. (2021). A Survey of Transformers. 

A Survey of Transformers (Lin et. al, 2021)

Taxonomy of Transformer variants

Variant with an augmentation to a specific module of the transformer model

Module-Level variant

These are high-level adaptations to transformers, past the module-level

- Lightweight Transformers
- Strengthening Cross-Block Connectivity
- Adaptive Computation Time (ACT)
- Divide-and-Conquer Strategies

Architecture-level variants of transformers

1. NLP
	- machine translation
	- language modeling
	- named entity recognition

2. Computer Vision
	- image classification
	- object detection
	- image generation
	- video processing

3. Audio Applications
	- speech recognition
	- speech synthesis
	- speech enhancement
	- music generation

4. Multimodal applications
	- Visual question-answering
	- visual common-sense reasoning
	- caption generation
	- speech-to-text translation
	- text-to-image generation

Applications of transformers

The pre-training and fine-tuning paradigm is a method motivated by the goal of creating adaptable, general-purpose systems for universal language understanding and generation. It involves separating the common components of neural network architectures, such as Transformers, and training them on vast amounts of unlabeled data using self-supervision. The resulting systems, known as foundation models, can be easily adapted for specific downstream applications via fine-tuning or prompting. This paradigm shift has enormously transformed natural language processing, meaning that in many cases, large-scale supervised learning for specific tasks is no longer required.

Learn Before

Related