No abstract

Self-attention based transformer models have been dominating many computer vision tasks in the past few years. Their superb model qualities heavily depend on the excessively large labeled image datasets. In order to reduce the reliance on large labeled datasets, reconstruction based masked autoencoders are gaining popularity, which learn high quality transferable representations from unlabeled images. For the same purpose, recent weakly supervised image pretraining methods explore language supervision from text captions accompanying the images. In this work, we propose masked image pretraining on language assisted representation, dubbed as MILAN. Instead of predicting raw pixels or low level features, our pretraining objective is to reconstruct the image features with substantial semantic signals that are obtained using caption supervision. Moreover, to accommodate our reconstruction target, we propose a more efficient prompting decoder architecture and a semantic aware mask sampling mechanism, which further advance the transfer performance of the pretrained model. Experimental results demonstrate that MILAN delivers higher accuracy than the previous works. When the masked autoencoder is pretrained and finetuned on ImageNet-1K dataset with an input resolution of 224×224, MILAN achieves a top-1 accuracy of 85.4% on ViT-B/16, surpassing previous state-of-the-arts by 1%. In the downstream semantic segmentation task, MILAN achieves 52.7 mIoU using ViT-B/16 backbone on ADE20K dataset, outperforming previous masked pretraining results by 4 points 1 .

No abstract

Large pretrained language models (PLMs) are often domain- or task-adapted via finetuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and few examples but limits performance. Instead, we prepare PLMs for data- and parameter-efficient adaptation by learning to learn the difference between general and adapted PLMs. This difference is expressed in terms of model weights and sublayer structure through our proposed dynamic low-rank reparameterization and learned architecture controller. Experiments on few-shot dialogue completion, low-resource abstractive summarization, and multi-domain language modeling show improvements in adaptation time and performance over direct finetuning or preparation via domain-adaptive pretraining. Ablations show our task-adaptive reparameterization (TARP) and model search (TAMS) components individually improve on other parameter-efficient transfer like adapters and structure-learning methods like learned sparsification.

Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long training and inference time. Model sparsification can reduce the computation and memory cost while maintaining model quality. Most existing sparsification algorithms unidirectionally remove weights, while others randomly or greedily explore a small subset of weights in each layer for pruning. The limitations of these algorithms reduce the level of sparsity. In addition, many algorithms still require pre-trained dense models and thus suffer from large memory footprint. In this paper, we propose a novel scheduled grow-and-prune (GaP) methodology without having to pre-train a dense model. It addresses the shortcomings of the previous work by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks, such as image classification, objective detection, 3D object part segmentation, and translation. They also outperform other state-of-the-art (SOTA) methods for model sparsification. As an example, a 90% sparse ResNet-50 obtained via GaP achieves 77.9% top-1 accuracy on ImageNet, improving the SOTA results of sparsification algorithms by 1.5%.Early works on weight pruning generally follow a prune-from-dense methodology [2,3,4,5,6,7,8,9], which usually requires 3 phases of training: pre-train a dense model, prune it to sparse, and fine-tune it. In such methodologies, however, the pre-trained dense models consume large memory space and may lead to long training time. In addition, one-shot or iteratively pruning from a well-trained DNN can only remove weights, which lacks the flexibility of growing back weights that are considered unimportant early in the training process but showed to be significant later in training. † Equal contribution.