Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of the model parameters for any given input token. As such, sparse MoEs have enabled unprecedented scalability, resulting in tremendous successes across domains such as natural language processing and computer vision. In this work, we instead explore the use of sparse MoEs to scale-down Vision Transformers (ViTs) to make them more attractive for resource-constrained vision applications. To this end, we propose a simplified and mobile-friendly MoE design where entire images rather than individual patches are routed to the experts. We also propose a stable MoE training procedure that uses super-class information to guide the router. We empirically show that our sparse Mobile Vision MoEs (V-MoEs) can achieve a better trade-off between performance and efficiency than the corresponding dense ViTs. For example, for the ViT-Tiny model, our Mobile V-MoE outperforms its dense counterpart by 3.39% on ImageNet-1k. For an even smaller ViT variant with only 54M FLOPs inference cost, our MoE achieves an improvement of 4.66%.
We present MOFI, a new vision foundation model designed to learn image representations from noisy entity annotated images. MOFI differs from previous work in two key aspects: ($i$) pre-training data, and ($ii$) training recipe. Regarding data, we introduce a new approach to automatically assign entity labels to images from noisy image-text pairs. Our approach involves employing a named entity recognition model to extract entities from the alt-text, and then using a CLIP model to select the correct entities as labels of the paired image. The approach is simple, does not require costly human annotation, and can be readily scaled up to billions of image-text pairs mined from the web. Through this method, we have created Image-to-Entities (I2E), a new large-scale dataset with 1 billion images and 2 million distinct entities, covering rich visual concepts in the wild. Building upon the I2E dataset, we study different training recipes, including supervised pre-training, contrastive pre-training, and multi-task learning. For constrastive pre-training, we treat entity names as free-form text, and further enrich them with entity descriptions. Experiments show that supervised pre-training with large-scale fine-grained entity labels is highly effective for image retrieval tasks, and multi-task training further improves the performance. The final MOFI model achieves 86.66% mAP on the challenging GPR1200 dataset, surpassing the previous state-of-the-art performance of 72.19% from OpenAI's CLIP model. Further experiments on zero-shot and linear probe image classification also show that MOFI outperforms a CLIP model trained on the original image-text data, demonstrating the effectiveness of the I2E dataset in learning strong image representations.
The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive. Furthermore, the conventional CLIP model doesn't differentiate between the visual semantics and meaning of text regions embedded in images. This can lead to non-robustness when the text in the embedded region doesn't match the image's visual appearance. In this paper, we discuss two effective approaches to improve the efficiency and robustness of CLIP training: (1) augmenting the training dataset while maintaining the same number of optimization steps, and (2) filtering out samples that contain text regions in the image. By doing so, we significantly improve the classification and retrieval accuracy on public benchmarks like ImageNet and CoCo. Filtering out images with text regions also protects the model from typographic attacks. To verify this, we build a new dataset named ImageNet with Adversarial Text Regions (ImageNet-Attr). Our filter-based CLIP model demonstrates a top-1 accuracy of 68.78\%, outperforming previous models whose accuracy was all below 50\%.
Multimodal learning is defined as learning over multiple heterogeneous input modalities such as video, audio, and text. In this work, we are concerned with understanding how models behave as the type of modalities differ between training and deployment, a situation that naturally arises in many applications of multimodal learning to hardware platforms. We present a multimodal robustness framework to provide a systematic analysis of common multimodal representation learning methods. Further, we identify robustness short-comings of these approaches and propose two intervention techniques leading to $1.5\times$-$4\times$ robustness improvements on three datasets, AudioSet, Kinetics-400 and ImageNet-Captions. Finally, we demonstrate that these interventions better utilize additional modalities, if present, to achieve competitive results of $44.2$ mAP on AudioSet 20K.
Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate the similarity in the dense embedding space as the matching score. On the other hand, sparse semantic features like bag-of-words models are more interpretable, but believed to suffer from inferior accuracy than dense representations. In this work, we show that it is possible to build a sparse semantic representation that is as powerful as, or even better than, dense presentations. We extend the CLIP model and build a sparse text and image representation (STAIR), where the image and text are mapped to a sparse token space. Each token in the space is a (sub-)word in the vocabulary, which is not only interpretable but also easy to integrate with existing information retrieval systems. STAIR model significantly outperforms a CLIP model with +$4.9\%$ and +$4.3\%$ absolute Recall@1 improvement on COCO-5k text$\rightarrow$image and image$\rightarrow$text retrieval respectively. It also achieved better performance on both of ImageNet zero-shot and linear probing compared to CLIP.
Self supervision and natural language supervision have emerged as two exciting ways to train general purpose image encoders which excel at a variety of downstream tasks. Recent works such as M3AE and SLIP have suggested that these approaches can be effectively combined, but most notably their results use small pre-training datasets (<50M samples) and don't effectively reflect the large-scale regime (>100M examples) that is commonly used for these approaches. Here we investigate whether a similar approach can be effective when trained with a much larger amount of data. We find that a combination of two state of the art approaches: masked auto-encoders, MAE and contrastive language image pre-training, CLIP provides a benefit over CLIP when trained on a corpus of 11.3M image-text pairs, but little to no benefit (as evaluated on a suite of common vision tasks) over CLIP when trained on a large corpus of 1.4B images. Our work provides some much needed clarity into the effectiveness (or lack thereof) of self supervision for large-scale image-text training.
Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding an image, however, is not just about understanding what content resides within an image, but importantly, where that content resides. In this work we examine how well vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We demonstrate how contemporary vision and language representation learning models based on contrastive losses and large web-based data capture limited object localization information. We propose a minimal set of modifications that results in models that uniquely learn both semantic and spatial information. We measure this performance in terms of zero-shot image recognition, unsupervised bottom-up and top-down semantic segmentations, as well as robustness analyses. We find that the resulting model achieves state-of-the-art results in terms of unsupervised segmentation, and demonstrate that the learned representations are uniquely robust to spurious correlations in datasets designed to probe the causal behavior of vision models.
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards intelligent agents or robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pre-training on large text and image-text datasets from the web has been extensively explored but the improvements are limited. To address the scarcity of in-domain instruction data, we investigate large-scale augmentation with synthetic instructions. We take 500+ indoor environments captured in densely-sampled 360 deg panoramas, construct navigation trajectories through these panoramas, and generate a visually-grounded instruction for each trajectory using Marky (Wang et al., 2022), a high-quality multilingual navigation instruction generator. To further increase the variability of the trajectories, we also synthesize image observations from novel viewpoints using an image-to-image GAN. The resulting dataset of 4.2M instruction-trajectory pairs is two orders of magnitude larger than existing human-annotated datasets, and contains a wider variety of environments and viewpoints. To efficiently leverage data at this scale, we train a transformer agent with imitation learning for over 700M steps of experience. On the challenging Room-across-Room dataset, our approach outperforms all existing RL agents, improving the state-of-the-art NDTW from 71.1 to 79.1 in seen environments, and from 64.6 to 66.8 in unseen test environments. Our work points to a new path to improving instruction-following agents, emphasizing large-scale imitation learning and the development of synthetic instruction generation capabilities.