What If We Recaption Billions of Web Images with LLaMA-3?

Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance model training across various vision-language tasks, particularly text-to-image generation. However, large-scale investigations in this area remain predominantly closed-source. Our paper aims to bridge this community effort, leveraging the powerful and \textit{open-sourced} LLaMA-3, a GPT-4 level LLM. Our recaptioning pipeline is simple: first, we fine-tune a LLaMA-3-8B powered LLaVA-1.5 and then employ it to recaption 1.3 billion images from the DataComp-1B dataset. Our empirical results confirm that this enhanced dataset, Recap-DataComp-1B, offers substantial benefits in training advanced vision-language models. For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks. For generative models like text-to-image Diffusion Transformers, the generated images exhibit a significant improvement in alignment with users' text instructions, especially in following complex queries. Our project page is https://www.haqtu.me/Recap-Datacomp-1B/

Autoregressive Pretraining with Mamba in Vision

The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-wise, the autoregressive nature can well capitalize on the Mamba's unidirectional recurrent structure, enabling faster overall training speed compared to other training strategies like mask modeling. Performance-wise, autoregressive pretraining equips the Mamba architecture with markedly higher accuracy over its supervised-trained counterparts and, more importantly, successfully unlocks its scaling potential to large and even huge model sizes. For example, with autoregressive pretraining, a base-size Mamba attains 83.2\% ImageNet accuracy, outperforming its supervised counterpart by 2.0\%; our huge-size Mamba, the largest Vision Mamba to date, attains 85.0\% ImageNet accuracy (85.5\% when finetuned with $384\times384$ inputs), notably surpassing all other Mamba variants in vision. The code is available at \url{https://github.com/OliverRensu/ARM}.

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context

This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different modalities and datasets. To capitalize on both local and global context, we design a hybrid method combining masked image modeling with autoregressive training for conditional image generation. This hybrid approach yields the most robust performance across all involved medical imaging tasks. To rigorously evaluate MVG's capabilities, we curated the first comprehensive generalist medical vision benchmark, comprising 13 datasets and spanning four imaging modalities (CT, MRI, X-ray, and micro-ultrasound). Our results consistently establish MVG's superior performance, outperforming existing vision generalists, such as Painter and LVM. Furthermore, MVG exhibits strong scalability, with its performance demonstrably improving when trained on a more diverse set of tasks, and can be effectively adapted to unseen datasets with only minimal task-specific samples. The code is available at \url{https://github.com/OliverRensu/MVG}.

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning

This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive video tokens into clusters that span both spatially and temporally, thereby enabling a richer aggregation of contextual information compared to the standard spatial-only or temporal-only clusters. Second, we adopt a randomized spatiotemporal prediction order to facilitate learning from multi-dimensional data, addressing the limitations of a handcrafted spatial-first or temporal-first sequence order. Extensive experiments establish ARVideo as an effective paradigm for self-supervised video representation learning. For example, when trained with the ViT-B backbone, ARVideo competitively attains 81.2% on Kinetics-400 and 70.9% on Something-Something V2, which are on par with the strong benchmark set by VideoMAE. Importantly, ARVideo also demonstrates higher training efficiency, i.e., it trains 14% faster and requires 58% less GPU memory compared to VideoMAE.

Mamba-R: Vision Mamba ALSO Needs Registers

Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much more severe in Vision Mamba -- they exist prevalently even with the tiny-sized model and activate extensively across background regions. To mitigate this issue, we follow the prior solution of introducing register tokens into Vision Mamba. To better cope with Mamba blocks' uni-directional inference paradigm, two key modifications are introduced: 1) evenly inserting registers throughout the input token sequence, and 2) recycling registers for final decision predictions. We term this new architecture Mamba-R. Qualitative observations suggest, compared to vanilla Vision Mamba, Mamba-R's feature maps appear cleaner and more focused on semantically meaningful regions. Quantitatively, Mamba-R attains stronger performance and scales better. For example, on the ImageNet benchmark, our base-size Mamba-R attains 82.9% accuracy, significantly outperforming Vim-B's 81.8%; furthermore, we provide the first successful scaling to the large model size (i.e., with 341M parameters), attaining a competitive accuracy of 83.2% (84.5% if finetuned with 384x384 inputs). Additional validation on the downstream semantic segmentation task also supports Mamba-R's efficacy.

Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation

Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the spurious features. Various domain augmentation have been proposed but largely rely on interpolating existing domains and frequently face difficulties in creating truly "novel" domains. Humans, on the other hand, can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalization? We introduce a novel approach to domain extrapolation that leverages reasoning ability and the extensive knowledge encapsulated within large language models (LLMs) to synthesize entirely new domains. Starting with the class of interest, we query the LLMs to extract relevant knowledge for these novel domains. We then bridge the gap between the text-centric knowledge derived from LLMs and the pixel input space of the model using text-to-image generation techniques. By augmenting the training set of domain generalization datasets with high-fidelity, photo-realistic images of these new domains, we achieve significant improvements over all existing methods, as demonstrated in both single and multi-domain generalization across various benchmarks. With the ability to extrapolate any domains for any class, our method has the potential to learn a generalized model for any task without any data. To illustrate, we put forth a much more difficult setting termed, data-free domain generalization, that aims to learn a generalized model in the absence of any collected data. Our empirical findings support the above argument and our methods exhibit commendable performance in this setting, even surpassing the supervised setting by approximately 1-2\% on datasets such as VLCS.

Compress & Align: Curating Image-Text Data with Human Knowledge

The massive growth of image-text data through web crawling inherently presents the challenge of variability in data quality. This paper introduces a novel algorithm, rooted in human knowledge, to compress this vast corpus of web-crawled image-text datasets to a compact and high-quality form. Our method unfolds in three major steps. First, we collect an image-text dataset, wherein each image is associated with multiple captions sourced from diverse origins. Then, to systemically capture human preferences regarding the best caption paired with each image, we establish a comprehensive set of both subjective and objective criteria for critically guiding the alignment assessment from labelers. Lastly, we train a reward model on the annotated dataset to internalize the nuanced human understanding of image-text alignment. The resulting reward model thus can act as a human-like referee to filter misaligned/low-quality image-text pairs. Extensive experiments demonstrate that we are able to secure (or even improve) model performance by compressing the image-text datasets up to ~90%. An impressive example is that, by aggressively reducing the total training sample from 130M to 15.5M (e.g., ~9x smaller), our BLIP-B/16 models still consistently show superior performance compared with the full-size-dataset counterpart on image-text retrieval (Flickr30K, COCO) by ~2.5% in Recall@1, and on image-captioning (Nocaps, COCO) by ~10.0% in CIDEr and ~2.7% in SPICE.

Rejuvenating image-GPT as Strong Visual Representation Learners

This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the prediction target from raw pixels to semantic tokens, enabling a higher-level understanding of visual content. Second, we supplement the autoregressive modeling by instructing the model to predict not only the next tokens but also the visible tokens. This pipeline is particularly effective when semantic tokens are encoded by discriminatively trained models, such as CLIP. We introduce this novel approach as D-iGPT. Extensive experiments showcase that D-iGPT excels as a strong learner of visual representations: A notable achievement of D-iGPT is its compelling performance on the ImageNet-1K dataset -- by training on publicly available datasets, D-iGPT achieves 89.5\% top-1 accuracy with a vanilla ViT-Large model. This model also shows strong generalization on the downstream task and robustness on out-of-distribution samples. Code is avaiable at \href{https://github.com/OliverRensu/D-iGPT}{https://github.com/OliverRensu/D-iGPT}.

SG-Former: Self-guided Transformer with Evolving Token Reallocation

Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature maps. To alleviate the computation cost, previous works rely on either fine-grained self-attentions restricted to local small regions, or global self-attentions but to shorten the sequence length resulting in coarse granularity. In this paper, we propose a novel model, termed as Self-guided Transformer~(SG-Former), towards effective global self-attention with adaptive fine granularity. At the heart of our approach is to utilize a significance map, which is estimated through hybrid-scale self-attention and evolves itself during training, to reallocate tokens based on the significance of each region. Intuitively, we assign more tokens to the salient regions for achieving fine-grained attention, while allocating fewer tokens to the minor regions in exchange for efficiency and global receptive fields. The proposed SG-Former achieves performance superior to state of the art: our base size model achieves \textbf{84.7\%} Top-1 accuracy on ImageNet-1K, \textbf{51.2mAP} bbAP on CoCo, \textbf{52.7mIoU} on ADE20K surpassing the Swin Transformer by \textbf{+1.3\% / +2.7 mAP/ +3 mIoU}, with lower computation costs and fewer parameters. The code is available at \href{https://github.com/OliverRensu/SG-Former}{https://github.com/OliverRensu/SG-Former}

NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos

Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies. This work aims to take a step forward to understand how humans perceive non-photorealistic videos with eye fixation (\ie, saliency detection), which is critical for enhancing media production, artistic design, and game user experience. To fill in the gap of missing a suitable dataset for this research line, we present NPF-200, the first large-scale multi-modal dataset of purely non-photorealistic videos with eye fixations. Our dataset has three characteristics: 1) it contains soundtracks that are essential according to vision and psychological studies; 2) it includes diverse semantic content and videos are of high-quality; 3) it has rich motions across and within videos. We conduct a series of analyses to gain deeper insights into this task and compare several state-of-the-art methods to explore the gap between natural images and non-photorealistic data. Additionally, as the human attention system tends to extract visual and audio features with different frequencies, we propose a universal frequency-aware multi-modal non-photorealistic saliency detection model called NPSNet, demonstrating the state-of-the-art performance of our task. The results uncover strengths and weaknesses of multi-modal network design and multi-domain training, opening up promising directions for future works. {Our dataset and code can be found at \url{https://github.com/Yangziyu/NPF200}}.