We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for multimodal fusion has a noticeable performance gap compared to transformers; (ii) However, VL pre-training can help close the performance gap; (iii) Instead of heavy multi-head attention, adding tiny one-head attention to MLPs is sufficient to achieve comparable performance to transformers. Moreover, we also find that the performance gap between MLPs and transformers is not widened when being evaluated on the harder robust VQA benchmarks, suggesting using MLPs for VL fusion can generalize roughly to a similar degree as using transformers. These results hint that MLPs can effectively learn to align vision and text features extracted from lower-level encoders without heavy reliance on self-attention. Based on this, we ask an even bolder question: can we have an all-MLP architecture for VL modeling, where both VL fusion and the vision encoder are replaced with MLPs? Our result shows that an all-MLP VL model is sub-optimal compared to state-of-the-art full-featured VL models when both of them get pre-trained. However, pre-training an all-MLP can surprisingly achieve a better average score than full-featured transformer models without pre-training. This indicates the potential of large-scale pre-training of MLP-like architectures for VL modeling and inspires the future research direction on simplifying well-established VL modeling with less inductive design bias. Our code is publicly available at: https://github.com/easonnie/mlp-vil
Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledge External Attention for Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\% in comparison to the human accuracy of 88.9\%.
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be more efficient than previous region-feature-based methods, their performance on downstream tasks often degrades significantly. In this paper, we present METER, a Multimodal End-to-end TransformER framework, through which we investigate how to design and pre-train a fully transformer-based VL model in an end-to-end manner. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIPViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion module (e.g., merged attention vs. co-attention), architectural design (e.g., encoder-only vs. encoder-decoder), and pre-training objectives (e.g., masked image modeling). We conduct comprehensive experiments and provide insights on how to train a performant VL transformer while maintaining fast inference speed. Notably, our best model achieves an accuracy of 77.64% on the VQAv2 test-std set using only 4M images for pre-training, surpassing the state-of-the-art region-feature-based model by 1.04%, and outperforming the previous best fully transformer-based model by 1.6%. Code and models are released at https://github.com/zdou0830/METER.
Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications. While existing vision foundation models such as CLIP, ALIGN, and Wu Dao 2.0 focus mainly on mapping images and textual representations to a cross-modal shared representation, we introduce a new computer vision foundation model, Florence, to expand the representations from coarse (scene) to fine (object), from static (images) to dynamic (videos), and from RGB to multiple modalities (caption, depth). By incorporating universal visual-language representations from Web-scale image-text data, our Florence model can be easily adapted for various computer vision tasks, such as classification, retrieval, object detection, VQA, image caption, video retrieval and action recognition. Moreover, Florence demonstrates outstanding performance in many types of transfer learning: fully sampled fine-tuning, linear probing, few-shot transfer and zero-shot transfer for novel images and objects. All of these properties are critical for our vision foundation model to serve general purpose vision tasks. Florence achieves new state-of-the-art results in majority of 44 representative benchmarks, e.g., ImageNet-1K zero-shot classification with top-1 accuracy of 83.74 and the top-5 accuracy of 97.18, 62.4 mAP on COCO fine tuning, 80.36 on VQA, and 87.8 on Kinetics-600.
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. In this paper, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM is built based on the HuBERT framework, with an emphasis on both spoken content modeling and speaker identity preservation. We first equip the Transformer structure with gated relative position bias to improve its capability on recognition tasks. For better speaker discrimination, we propose an utterance mixing training strategy, where additional overlapped utterances are created unsupervisely and incorporated during model training. Lastly, we scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks. The code and pretrained models are available at https://aka.ms/wavlm.
The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text latent spaces. The embedding aligner is a shared linear projection between text encoder and speech encoder trained by masked language modeling (MLM) loss and connectionist temporal classification (CTC), respectively. The modality switch training randomly swaps speech and text embeddings based on the forced alignment result to learn a joint representation space. Experimental results show that our proposed approach achieves a relative 14% to 19% word error rate (WER) reduction on Librispeech ASR task. We further verify its effectiveness on spoken language understanding (SLU), i.e., an absolute 2.5% to 2.8% F1 score improvement on SNIPS slot filling task.
Recently, a trend is emerging toward human-servicing autonomous mobile robots, with diverse applications including delivery of supplies in hospitals, hotels, or labs where personnel are scarce, or reacting to indoor emergencies. However, existing autonomous mobile robot (AMR) motion is slow and inefficient, a foundational barrier to proliferation of human-servicing applications. This research has developed a motion control architecture that demonstrates the potential of several algorithms for increasing speed and efficiency. These include a novel PI(t)D(t) controller that sets integral and derivative gains as functions of time, and motion-profiling applied for holonomic motion. Resulting performance indicates potential for faster, more efficient AMRs, that maintain high levels of accuracy and repeatability. The hope is that this research can serve as a proof of concept for faster motion-control, to remove a key barrier to further use of human-servicing mobile robots.
Commonsense reasoning (CSR) requires the model to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are in few popular languages, especially English. Thus, it remains unclear how to effectively conduct multilingual commonsense reasoning (XCSR) for various languages. In this work, we propose to utilize English knowledge sources via a translate-retrieve-translate (TRT) strategy. For multilingual commonsense questions and choices, we collect related knowledge via translation and retrieval from the knowledge sources. The retrieved knowledge is then translated into the target language and integrated into a pre-trained multilingual language model via visible knowledge attention. Then we utilize a diverse of 4 English knowledge sources to provide more comprehensive coverage of knowledge in different formats. Extensive results on the XCSR benchmark demonstrate that TRT with external knowledge can significantly improve multilingual commonsense reasoning in both zero-shot and translate-train settings, outperforming 3.3 and 3.6 points over the previous state-of-the-art on XCSR benchmark datasets (X-CSQA and X-CODAH).
In this paper, we bring a new way of digesting news content by introducing the task of segmenting a news article into multiple sections and generating the corresponding summary to each section. We make two contributions towards this new task. First, we create and make available a dataset, SegNews, consisting of 27k news articles with sections and aligned heading-style section summaries. Second, we propose a novel segmentation-based language generation model adapted from pre-trained language models that can jointly segment a document and produce the summary for each section. Experimental results on SegNews demonstrate that our model can outperform several state-of-the-art sequence-to-sequence generation models for this new task.