论文检索

Applications/Computer Vision

Antonin Vobecky, Oriane Siméoni, David Hurych, Spyridon Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic

We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries. This is a challenging problem because of the 2D-3D ambiguity and the open-vocabulary nature of the target tasks, where obtaining annotated training data in 3D is difficult. The contributions of this work are three-fold. First, we design a new model architecture for open-vocabulary 3D semantic occupancy prediction. The architecture consists of a 2D-3D encoder together with occupancy prediction and 3D-language heads. The output is a dense voxel map of 3D grounded language embeddings enabling a range of open-vocabulary tasks. Second, we develop a tri-modal self-supervised learning algorithm that leverages three modalities: (i) images, (ii) language and (iii) LiDAR point clouds, and enables training the proposed architecture using a strong pre-trained vision-language model without the need for any 3D manual language annotations. Finally, we demonstrate quantitatively the strengths of the proposed model on several open-vocabulary tasks:Zero-shot 3D semantic segmentation using existing datasets; 3D grounding and retrieval of free-form language queries, using a small dataset that we propose as an extension of nuScenes. You can find the project page here https://vobecant.github.io/POP3D.

Applications/Computer Vision

Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few labeled in-distribution (ID) images. While prompt learning methods such as CoOp have shown effectiveness and efficiency in few-shot ID classification, they still face limitations in OOD detection due to the potential presence of ID-irrelevant information in text embeddings. To address this issue, we introduce a new approach called $\textbf{Lo}$cal regularized $\textbf{Co}$ntext $\textbf{Op}$timization (LoCoOp), which performs OOD regularization that utilizes the portions of CLIP local features as OOD features during training. CLIP's local features have a lot of ID-irrelevant nuisances ($\textit{e.g.}$, backgrounds), and by learning to push them away from the ID class text embeddings, we can remove the nuisances in the ID class text embeddings and enhance the separation between ID and OOD. Experiments on the large-scale ImageNet OOD detection benchmarks demonstrate the superiority of our LoCoOp over zero-shot, fully supervised detection methods and prompt learning methods. Notably, even in a one-shot setting -- just one label per class, LoCoOp outperforms existing zero-shot and fully supervised detection methods. The code is available via https://github.com/AtsuMiyai/LoCoOp.

Applications/Computer Vision

Ruihan Yang, Stephan Mandt

This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional "content" latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining ``texture'' variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with $\mathcal{X}$-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality. Our code is available at: https://github.com/buggyyang/CDC_compression

Applications/Computer Vision

Lujun Li, Peijie Dong, Anggeng Li, Zimian Wei, Ya Yang

Knowledge distillation (KD) has emerged as an effective technique for compressing models that can enhance the lightweight model. Conventional KD methods propose various designs to allow student model to imitate the teacher better. However, these handcrafted KD designs heavily rely on expert knowledge and may be sub-optimal for various teacher-student pairs. In this paper, we present a novel framework, KD-Zero, which utilizes evolutionary search to automatically discover promising distiller from scratch for any teacher-student architectures. Specifically, we first decompose the generalized distiller into knowledge transformations, distance functions, and loss weights. Then, we construct our distiller search space by selecting advanced operations for these three components. With sharpness and represent gap as fitting objectives, we evolve candidate populations and generate better distillers by crossover and mutation. To ensure efficient searching, we employ the loss-rejection protocol, search space shrinkage, and proxy settings during the search process. In this manner, the discovered distiller can address the capacity gap and cross-architecture challenges for any teacher-student pairs in the final distillation stage. Comprehensive experiments reveal that KD-Zero consistently outperforms other state-of-the-art methods across diverse architectures on classification, detection, and segmentation tasks. Noticeably, we provide some practical insights in designing the distiller by analyzing the distiller discovered. Codes are available in supplementary materials.

Applications/Computer Vision

Wenlong Zhang, Xiaohui Li, Guangyuan SHI, Xiangyu Chen, Yu Qiao, Xiaoyun Zhang, Xiao-Ming Wu, Chao Dong

In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-task learning perspective. We demonstrate that the conventional formulation of real-SR can be viewed as solving multiple distinct degradation tasks using a single shared model. This poses a challenge known as task competition or task conflict in multi-task learning, where certain tasks dominate the learning process, resulting in poor performance on other tasks. This problem is exacerbated in the case of real-SR, due to the involvement of numerous degradation tasks. To address the issue of task competition in real-SR, we propose a task grouping approach. Our approach efficiently identifies the degradation tasks where a real-SR model falls short and groups these unsatisfactory tasks into multiple task groups. We then utilize the task groups to fine-tune the real-SR model in a simple way, which effectively mitigates task competition and facilitates knowledge transfer. Extensive experiments demonstrate our method achieves significantly enhanced performance across a wide range of degradation scenarios.

Applications/Computer Vision

Lingchen Meng, Xiyang Dai, Jianwei Yang, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Yi-Ling Chen, Zuxuan Wu, Lu Yuan, Yu-Gang Jiang

Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces limited results due to (1) semantic ambiguity---an image-level label only captures a salient part of the image, ignoring the remaining rich semantics within the image; and (2) location sensitivity---the label highly depends on the locations and crops of the original image, which may change after data transformations like random cropping.To remedy this, we propose RichSem, a simple but effective method, which is robust to learn rich semantics from coarse locations without the need of accurate bounding boxes. RichSem leverages rich semantics from images, which are then served as additional ``soft supervision'' for training detectors. Specifically, we add a semantic branch to our detector to learn these soft semantics and enhance feature representations for long-tailed object detection. The semantic branch is only used for training and is removed during inference. RichSem achieves consistent improvements on both overall and rare-category of LVIS under different backbones and detectors. Our method achieves state-of-the-art performance without requiring complex training and testing procedures. Moreover, we show the effectiveness of our method on other long-tailed datasets with additional experiments.

Applications/Computer Vision

Yi Yu, Xue Yang, Qingyun Li, Yue Zhou, Feipeng Da, Junchi Yan

With the rapidly increasing demand for oriented object detection, e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving weakly-supervised detector H2RBox for learning rotated box (RBox) from the more readily-available horizontal box (HBox) has shown promise. This paper presents H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection. Specifically, we propose to leverage the reflection symmetry via flip and rotate consistencies, using a weakly-supervised network branch similar to H2RBox, together with a novel self-supervised branch that learns orientations from the symmetry inherent in visual objects. The detector is further stabilized and enhanced by practical techniques to cope with peripheral issues e.g. angular periodicity. To our best knowledge, H2RBox-v2 is the first symmetry-aware self-supervised paradigm for oriented object detection. In particular, our method shows less susceptibility to low-quality annotation and insufficient training data compared to H2RBox. Specifically, H2RBox-v2 achieves very close performance to a rotation annotation trained counterpart -- Rotated FCOS: 1) DOTA-v1.0/1.5/2.0: 72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%; 2) HRSC: 89.66% vs. 88.99%; 3) FAIR1M: 42.27% vs. 41.25%.

Applications/Computer Vision

Qihang Fang, Yafei Song, Keqiang Li, Liefeng Bo

A neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly. To deal with this issue, existing works have incorporated prior knowledge to provide an independent supervision signal for the density field, including total variation loss, sparsity loss, distortion loss, etc. These losses are based on general assumptions about the density field, e.g., it should be smooth, sparse, or compact, which are not adaptive to a specific scene. In this paper, we propose a more adaptive method to reduce the shape-radiance ambiguity. The key is a rendering method that is only based on the density field. Specifically, we first estimate the color field based on the density field and posed images in a closed form. Then NeRF's rendering process can proceed. We address the problems in estimating the color field, including occlusion and non-uniformly distributed views. Afterwards, it is applied to regularize NeRF's density field. As our regularization is guided by photometric loss, it is more adaptive compared to existing ones. Experimental results show that our method improves the density field of NeRF both qualitatively and quantitatively. Our code is available at https://github.com/qihangGH/Closed-form-color-field.

Applications/Computer Vision

DONGXU LI, Junnan Li, Steven Hoi

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text.Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications. Implementations are available at: https://github.com/salesforce/LAVIS/tree/main/projects/blip-diffusion.

Applications/Computer Vision

Yunhao Ge, Hong-Xing Yu, Cheng Zhao, Yuliang Guo, Xinyu Huang, Liu Ren, Laurent Itti, Jiajun Wu

A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets. While augmenting real scenes with virtual objects holds promise to improve both the diversity and quantity of the objects, it remains elusive due to the lack of an effective 3D object insertion method in complex real captured scenes. In this work, we study augmenting complex real indoor scenes with virtual objects for monocular 3D object detection. The main challenge is to automatically identify plausible physical properties for virtual assets (e.g., locations, appearances, sizes, etc.) in cluttered real scenes. To address this challenge, we propose a physically plausible indoor 3D object insertion approach to automatically copy virtual objects and paste them into real scenes. The resulting objects in scenes have 3D bounding boxes with plausible physical locations and appearances. In particular, our method first identifies physically feasible locations and poses for the inserted objects to prevent collisions with the existing room layout. Subsequently, it estimates spatially-varying illumination for the insertion location, enabling the immersive blending of the virtual objects into the original scene with plausible appearances and cast shadows. We show that our augmentation method significantly improves existing monocular 3D object models and achieves state-of-the-art performance. For the first time, we demonstrate that a physically plausible 3D object insertion, serving as a generative data augmentation technique, can lead to significant improvements for discriminative downstream tasks such as monocular 3D object detection. Project website: https://gyhandy.github.io/3D-Copy-Paste/.

Applications/Computer Vision

Weikang Bian, Zhaoyang Huang, Xiaoyu Shi, Yitong Dong, Yijin Li, Hongsheng Li

We tackle the problem of Persistent Independent Particles (PIPs), also called Tracking Any Point (TAP), in videos, which specifically aims at estimating persistent long-term trajectories of query points in videos. Previous methods attempted to estimate these trajectories independently to incorporate longer image sequences, therefore, ignoring the potential benefits of incorporating spatial context features. We argue that independent video point tracking also demands spatial context features. To this end, we propose a novel framework Context-PIPs, which effectively improves point trajectory accuracy by aggregating spatial context features in videos. Context-PIPs contains two main modules: 1) a SOurse Feature Enhancement (SOFE) module, and 2) a TArget Feature Aggregation (TAFA) module. Context-PIPs significantly improves PIPs all-sided, reducing 11.4\% Average Trajectory Error of Occluded Points (ATE-Occ) on CroHD and increasing 11.8\% Average Percentage of Correct Keypoint (A-PCK) on TAP-Vid-Kinetics. Demos are available at \url{https://wkbian.github.io/Projects/Context-PIPs/}.

Applications/Computer Vision

Zheng Chen, Yulun Zhang, Ding Liu, bin xia, Jinjin Gu, Linghe Kong, Xin Yuan

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consumes massive computational resources. Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process. The deblurring process is implemented by a regression-based method to obtain better distortion accuracy. Meanwhile, the highly compact latent space ensures the efficiency of the DM. Furthermore, we design the hierarchical integration module to fuse the prior into the regression-based model from multiple scales, enabling better generalization in complex blurry scenarios. Comprehensive experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods. Code and trained models are available at https://github.com/zhengchen1999/HI-Diff.

Applications/Computer Vision

Jiacheng Chen, Ruizhi Deng, Yasutaka Furukawa

This paper presents \textit{PolyDiffuse}, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating reconstruction as a generation process conditioned on sensor data. The task of structured reconstruction poses two fundamental challenges to DM: 1) A structured geometry is a ''set'' (e.g., a set of polygons for a floorplan geometry), where a sample of $N$ elements has $N!$ different but equivalent representations, making the denoising highly ambiguous; and 2) A ''reconstruction'' task has a single solution, where an initial noise needs to be chosen carefully, while any initial noise works for a generation task.Our technical contribution is the introduction of a Guided Set Diffusion Model where 1) the forward diffusion process learns \textit{guidance networks} to control noise injection so that one representation of a sample remains distinct from its other permutation variants, thus resolving denoising ambiguity; and 2) the reverse denoising process reconstructs polygonal shapes, initialized and directed by the guidance networks, as a conditional generation process subject to the sensor data.We have evaluated our approach for reconstructing two types of polygonal shapes: floorplan as a set of polygons and HD map for autonomous cars as a set of polylines.Through extensive experiments on standard benchmarks, we demonstrate that PolyDiffuse significantly advances the current state of the art and enables broader practical applications. The code and data are available on our project page: https://poly-diffuse.github.io.

Applications/Computer Vision

Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim Alabdulmohsin 等

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT) offer flexible sequence-based modeling, and hence varying input sequence lengths. We take advantage of this with NaViT (Native Resolution ViT) which uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios. Alongside flexible model usage, we demonstrate improved training efficiency for large-scale supervised and contrastive image-text pretraining.NaViT can be efficiently transferred to standard tasks such as image and video classification, object detection, and semantic segmentation and leads to improved results on robustness and fairness benchmarks. At inference time, the input resolution flexibility can be used to smoothly navigate the test-time cost-performance trade-off. We believe that NaViTmarks a departure from the standard, CNN-designed, input and modelling pipeline used by most computer vision models, and represents a promising direction for ViTs.

Applications/Computer Vision

Quang Nguyen, Truong Vu, Anh Tran, Khoi Nguyen

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category labels, we propose a novel method for generating pixel-level semantic segmentation labels using the text-to-image generative model Stable Diffusion (SD). By utilizing the text prompts, cross-attention, and self-attention of SD, we introduce three new techniques: class-prompt appending, class-prompt cross-attention, and self-attention exponentiation. These techniques enable us to generate segmentation maps corresponding to synthetic images. These maps serve as pseudo-labels for training semantic segmenters, eliminating the need for labor-intensive pixel-wise annotation. To account for the imperfections in our pseudo-labels, we incorporate uncertainty regions into the segmentation, allowing us to disregard loss from those regions. We conduct evaluations on two datasets, PASCAL VOC and MSCOCO, and our approach significantly outperforms concurrent work. Our benchmarks and code will be released at https://github.com/VinAIResearch/Dataset-Diffusion.

Applications/Computer Vision

Peiyan Dong, LEI LU, Chao Wu, Cheng Lyu, Geng Yuan, Hao Tang, Yanzhi Wang

While Vision Transformers (ViTs) have undoubtedly made impressive strides in computer vision (CV), their intricate network structures necessitate substantial computation and memory resources. A decision-making process for CV tasks typically entails performing computations with low latency, which is a tricky problem for ViT models.Model quantization is a widely-used technique to optimize the hardware efficiency of deep neural networks.Full quantization under Sub-8-bit precision, in particular, is a promising solution to reduce inference latency significantly. Unfortunately, current commodity hardware, such as CPUs and GPUs, still struggles to efficiently execute these sub-8-bit quantized networks, as their SIMD instructions only support a granularity of 8 bits or wider.Also, there is a scarcity of literature that presents a full quantization paradigm for ViTs.In this paper, we propose an activation-aware fully sub-8-bit quantization-aware training (QAT) framework called PackQViT for efficient yet accurate ViT acceleration on mobile devices to facilitate real-time AI-powered decision-making.Specifically, in revisiting data activation within the ViT dataflow, two characteristics are relevant to quantization strategy and precision: the long-tailed distribution and systematic channel-wise outliers.In response, we employ either log2 quantization or clipping to address the long-tailed distribution and incorporate outlier-aware training for residual link quantization to regulate the various channel-wise outliers more consistently.Notably, due to the systematic fixed pattern, outlier-aware training approach can predict the channel indices and regularized scales of outliers in advance, thus avoiding the runtime data-adaptive selection during inference.Furthermore, we employ Int-$2^{n}$-Softmax, Int-LayerNorm, and Integer GELU to enable integer-only computation flow. Finally, we develop a SIMD-based 4-bit packed multiplier to achieve end-to-end ViT acceleration on mobile phones.Compared to prior studies on ViT quantization using 8-bit precision, PackQViT surpasses other works by an improved accuracy ranging from 0.4\% to 17.9\% for various widely used ViTs on ImageNet dataset; under 4-bit precision, PackQViT demonstrates 0.4%$\sim$2.8% higher accuracy. Compared to the baseline multiplier, our implementations on the Realme GT Android smartphone with Snapdragon 870 SoC CPU achieve 2.6x$\sim$3.7x speedup under 8-bit scenario and 3.8x$\sim$5.9x speedup under 4-bit which ensures practical real-time performance.

Applications/Computer Vision

Enneng Yang, Li Shen, Zhenyi Wang, Tongliang Liu, Guibing Guo

Dataset condensation (DC) distills a large real-world dataset into a small synthetic dataset, with the goal of training a network from scratch on the latter that performs similarly to the former. State-of-the-art (SOTA) DC methods have achieved satisfactory results through techniques such as accuracy, gradient, training trajectory, or distribution matching. However, these works all perform matching in the high-dimension pixel spaces, ignoring that natural images are usually locally connected and have lower intrinsic dimensions, resulting in low condensation efficiency. In this work, we propose a simple-yet-efficient dataset condensation plugin that matches the raw and synthetic datasets in a low-dimensional manifold. Specifically, our plugin condenses raw images into two low-rank matrices instead of parameterized image matrices. Our plugin can be easily incorporated into existing DC methods, thereby containing richer raw dataset information at limited storage costs to improve the downstream applications' performance. We verify on multiple public datasets that when the proposed plugin is combined with SOTA DC methods, the performance of the network trained on synthetic data is significantly improved compared to traditional DC methods. Moreover, when applying the DC methods as a plugin to continual learning tasks, we observed that our approach effectively mitigates catastrophic forgetting of old tasks under limited memory buffer constraints and avoids the problem of raw data privacy leakage.

Applications/Computer Vision

Xiang Li, Chung-Ching Lin, Yinpeng Chen, Zicheng Liu, Jinglu Wang, Rita Singh, Bhiksha Raj

The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which creates a contrast between the original image and a painted image in which a masked area is painted using off-the-shelf generative models. During the painting process, inpainting and outpainting are alternated, with the former masking the foreground and filling in the background, and the latter masking the background while recovering the missing part of the foreground object. Inpainting and outpainting, also referred to as I-step and O-step, allow our method to gradually advance the target segmentation mask toward the ground truth without supervision or training. PaintSeg can be configured to work with a variety of prompts, e.g. coarse masks, boxes, scribbles, and points. Our experimental results demonstrate that PaintSeg outperforms existing approaches in coarse mask-prompt, box-prompt, and point-prompt segmentation tasks, providing a training-free solution suitable for unsupervised segmentation. Code: https://github.com/lxa9867/PaintSeg.

Applications/Computer Vision

Michael Tschannen, Manoj Kumar, Andreas Steiner, Xiaohua Zhai, Neil Houlsby, Lucas Beyer

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this type of data is commonly considered an inferior pretraining strategy. In this paper, we perform a fair comparison of these two pretraining strategies, carefully matching training data, compute, and model capacity. Using a standard encoder-decoder transformer, we find that captioning alone is surprisingly effective: on classification tasks, captioning produces vision encoders competitive with contrastively pretrained encoders, while surpassing them on vision & language tasks. We further analyze the effect of the model architecture and scale, as well as the pretraining data on the representation quality, and find that captioning exhibits the same or better scaling behavior along these axes. Overall our results show that plain image captioning is a more powerful pretraining strategy than was previously believed. Code is available at [https://github.com/google-research/big_vision](https://github.com/google-research/big_vision).

Applications/Computer Vision

Michael Tschannen, Manoj Kumar, Andreas Steiner, Xiaohua Zhai, Neil Houlsby, Lucas Beyer

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this type of data is commonly considered an inferior pretraining strategy. In this paper, we perform a fair comparison of these two pretraining strategies, carefully matching training data, compute, and model capacity. Using a standard encoder-decoder transformer, we find that captioning alone is surprisingly effective: on classification tasks, captioning produces vision encoders competitive with contrastively pretrained encoders, while surpassing them on vision & language tasks. We further analyze the effect of the model architecture and scale, as well as the pretraining data on the representation quality, and find that captioning exhibits the same or better scaling behavior along these axes. Overall our results show that plain image captioning is a more powerful pretraining strategy than was previously believed. Code is available at [https://github.com/google-research/big_vision](https://github.com/google-research/big_vision).