v4.23.0: Whisper, Time series, Conditional DETR, MSN, MarkupLM, safetensors
Whisper
The Whisper model was proposed in Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
The abstract from the paper is the following:
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zeroshot transfer setting without the need for any finetuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.
Time series
The Time Series Transformer model is a vanilla encoder-decoder Transformer for time series forecasting.
:warning: This is a recently introduced model and modality, so the API hasn't been tested extensively. There may be some bugs or slight breaking changes to fix it in the future. If you see something strange, file a Github Issue.
Conditional DETR
The Conditional DETR model was proposed in Conditional DETR for Fast Training Convergence by Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang. Conditional DETR presents a conditional cross-attention mechanism for fast DETR training. Conditional DETR converges 6.7× to 10× faster than DETR.
The abstract from the paper is the following:
The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and predicting the box, which increases the need for high-quality content embeddings and thus the training difficulty. Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention. The benefit is that through the conditional spatial query, each cross-attention head is able to attend to a band containing a distinct region, e.g., one object extremity or a region inside the object box. This narrows down the spatial range for localizing the distinct regions for object classification and box regression, thus relaxing the dependence on the content embeddings and easing the training. Empirical results show that conditional DETR converges 6.7× faster for the backbones R50 and R101 and 10× faster for stronger backbones DC5-R50 and DC5-R101.
Masked Siamese Networks
The ViTMSN model was proposed in Masked Siamese Networks for Label-Efficient Learning by Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas. The paper presents a joint-embedding architecture to match the prototypes of masked patches with that of the unmasked patches. With this setup, their method yields excellent performance in the low-shot and extreme low-shot regimes.
The abstract from the paper is the following:
We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the original unmasked image. This self-supervised pre-training strategy is particularly scalable when applied to Vision Transformers since only the unmasked patches are processed by the network. As a result, MSNs improve the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification. For instance, on ImageNet-1K, with only 5,000 annotated images, our base MSN model achieves 72.4% top-1 accuracy, and with 1% of ImageNet-1K labels, we achieve 75.7% top-1 accuracy, setting a new state-of-the-art for self-supervised learning on this benchmark.
MarkupLM
The MarkupLM model was proposed in MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei. MarkupLM is BERT, but applied to HTML pages instead of raw text documents. The model incorporates additional embedding layers to improve performance, similar to LayoutLM.
The model can be used for tasks like question answering on web pages or information extraction from web pages. It obtains state-of-the-art results on 2 important benchmarks:
WebSRC, a dataset for Web-Based Structual Reading Comprehension (a bit like SQuAD but for web pages)
SWDE, a dataset for information extraction from web pages (basically named-entity recogntion on web pages)
The abstract from the paper is the following:
... (truncated)
277 Feb 18, 2021
0 Feb 13, 2022
10 Jan 6, 2023
14 Jul 23, 2022
7 Nov 7, 2022
47 Sep 5, 2022
4 Apr 6, 2022
121 Jan 3, 2023
3.8k Dec 30, 2022
491 Jan 7, 2023
161 Dec 19, 2022
48 Dec 14, 2022
12 Feb 16, 2022
37 Dec 25, 2022
5 Aug 25, 2022
216 Dec 22, 2022
2 Jan 6, 2022
32 Dec 14, 2022