**PipeTransformer** is a method for automated elastic pipelining for efficient distributed training of [Transformer](https://paperswithcode.com/method/transformer) models. In PipeTransformer, an adaptive on the fly freeze algorithm is used that can identify and freeze some layers gradually during training, as well as an elastic pipelining system that can dynamically allocate resources to train the remaining active layers. More specifically, PipeTransformer automatically excludes frozen layers from the pipeline, packs active layers into fewer GPUs, and forks more replicas to increase data-parallel width.

Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework, resulting in impressive results. CLIP imposes a bidirectional constraints on global representation of entire images and sentences. Although IC conducts an unidirectional image-to-text generation on local representation, it lacks any constraint on local text-to-image reconstruction, which limits the ability to understand images at a fine-grained level when aligned with texts. To achieve multimodal alignment from both global and local perspectives, this paper proposes Symmetrizing Contrastive Captioners (SyCoCa), which introduces bidirectional interactions on images and texts across the global and local representation levels. Specifically, we expand a Text-Guided Masked Image Modeling (TG-MIM) head based on ITC and IC heads. The improved SyCoCa can further leverage textual cues to reconstruct contextual images and visual cues to predict textual contents. When implementing bidirectional local interactions, the local contents of images tend to be cluttered or unrelated to their textual descriptions. Thus, we employ an attentive masking strategy to select effective image patches for interaction. Extensive experiments on five vision-language tasks, including image-text retrieval, image-captioning, visual question answering, and zero-shot/finetuned image classification, validate the effectiveness of our proposed method.

SyCoCa

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

PipeTransformer

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers

A novel built-in attention mechanism, that is complementary to all other prior attention mechanisms (e.g. squeeze and excitation, transformers) that are external (i.e., not built-in - please read paper for more details)

Source	PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com