Search

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the model to learn to maximize the expected likelihood over all factorization orders and thus effectively improve the model's capability of modeling bidirectional contexts. Importantly, RAR preserves the integrity of the autoregressive modeling framework, ensuring full compatibility with language modeling while significantly improving performance in image generation. On the ImageNet-256 benchmark, RAR achieves an FID score of 1.48, not only surpassing prior state-of-the-art autoregressive image generators but also outperforming leading diffusion-based and masked transformer-based methods. Code and models will be made available at https://github.com/bytedance/1d-tokenizer, Comment: simple method improving autoregressive image generator to SOTA performance; Project page at https://yucornetto.github.io/projects/rar.html

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit tokens - a binary quantized representation of tokens with rich semantics. The first contribution furnishes a transparent, reproducible, and high-performing VQGAN model, enhancing accessibility and matching the performance of current state-of-the-art methods while revealing previously undisclosed details. The second contribution demonstrates that embedding-free image generation using bit tokens achieves a new state-of-the-art FID of 1.52 on the ImageNet 256x256 benchmark, with a compact generator model of mere 305M parameters., Comment: Project page: https://weber-mark.github.io/projects/maskbit.html

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational demands compared to directly processing pixels and enhances the effectiveness and efficiency of the generation process. Prior methods, such as VQGAN, typically utilize 2D latent grids with fixed downsampling factors. However, these 2D tokenizations face challenges in managing the inherent redundancies present in images, where adjacent regions frequently display similarities. To overcome this issue, we introduce Transformer-based 1-Dimensional Tokenizer (TiTok), an innovative approach that tokenizes images into 1D latent sequences. TiTok provides a more compact latent representation, yielding substantially more efficient and effective representations than conventional techniques. For example, a 256 x 256 x 3 image can be reduced to just 32 discrete tokens, a significant reduction from the 256 or 1024 tokens obtained by prior methods. Despite its compact nature, TiTok achieves competitive performance to state-of-the-art approaches. Specifically, using the same generator framework, TiTok attains 1.97 gFID, outperforming MaskGIT baseline significantly by 4.21 at ImageNet 256 x 256 benchmark. The advantages of TiTok become even more significant when it comes to higher resolution. At ImageNet 512 x 512 benchmark, TiTok not only outperforms state-of-the-art diffusion model DiT-XL/2 (gFID 2.74 vs. 3.04), but also reduces the image tokens by 64x, leading to 410x faster generation process. Our best-performing variant can significantly surpasses DiT-XL/2 (gFID 2.13 vs. 3.04) while still generating high-quality samples 74x faster., Comment: A compact 1D Image Tokenization method, leading to SOTA generation performance while being substantially faster. Project page at https://yucornetto.github.io/projects/titok.html

Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geometric fidelity of the output remains an unresolved issue; albeit the rendered 2D views are realistic, the underlying geometry may contain errors such as unreasonable concavities. In this work, we propose CorrespondentDream, an effective method to leverage annotation-free, cross-view correspondences yielded from the diffusion U-Net to provide additional 3D prior to the NeRF optimization process. We find that these correspondences are strongly consistent with human perception, and by adopting it in our loss design, we are able to produce NeRF models with geometries that are more coherent with common sense, e.g., more smoothed object surface, yielding higher 3D fidelity. We demonstrate the efficacy of our approach through various comparative qualitative results and a solid user study., Comment: 25 pages, 22 figures, accepted to CVPR 2024

In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COCO benchmark has propelled the development of modern detection and segmentation systems. However, the COCO segmentation benchmark has seen comparatively slow improvement over the last decade. Originally equipped with coarse polygon annotations for thing instances, it gradually incorporated coarse superpixel annotations for stuff regions, which were subsequently heuristically amalgamated to yield panoptic segmentation annotations. These annotations, executed by different groups of raters, have resulted not only in coarse segmentation masks but also in inconsistencies between segmentation types. In this study, we undertake a comprehensive reevaluation of the COCO segmentation annotations. By enhancing the annotation quality and expanding the dataset to encompass 383K images with more than 5.18M panoptic masks, we introduce COCONut, the COCO Next Universal segmenTation dataset. COCONut harmonizes segmentation annotations across semantic, instance, and panoptic segmentation with meticulously crafted high-quality masks, and establishes a robust benchmark for all segmentation tasks. To our knowledge, COCONut stands as the inaugural large-scale universal segmentation dataset, verified by human raters. We anticipate that the release of COCONut will significantly contribute to the community's ability to assess the progress of novel neural networks., Comment: Accepted at CVPR2024, data available at https://xdeng7.github.io/coconut.github.io/

Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segmentation with high-resolution input features poses significant challenges, often leading to insufficient GPU memory capacity. Consequently, modern video segmenters either extend an image segmenter without incorporating any temporal attention or resort to window space-time attention in a naive manner. In this work, we present Axial-VS, a general and simple framework that enhances video segmenters by tracking objects along axial trajectories. The framework tackles video segmentation through two sub-tasks: short-term within-clip segmentation and long-term cross-clip tracking. In the first step, Axial-VS augments an off-the-shelf clip-level video segmenter with the proposed axial-trajectory attention, sequentially tracking objects along the height- and width-trajectories within a clip, thereby enhancing temporal consistency by capturing motion trajectories. The axial decomposition significantly reduces the computational complexity for dense features, and outperforms the window space-time attention in segmentation quality. In the second step, we further employ axial-trajectory attention to the object queries in clip-level segmenters, which are learned to encode object information, thereby aiding object tracking across different clips and achieving consistent segmentation throughout the video. Without bells and whistles, Axial-VS showcases state-of-the-art results on video segmentation benchmarks, emphasizing its effectiveness in addressing the limitations of modern clip-level video segmenters. Code and models are available at https://github.com/TACJu/Axial-VS., Comment: The paper and model names have been updated to better reflect the methodological contributions

Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/storage of their huge amount of parameters, which becomes increasingly challenging to handle with the growing amount of vision tasks. In this paper, we propose an effective approach to alleviate the issue, namely selective feature adapter (SFA). It achieves state-of-the-art (SoTA) performance under any given budget of trainable parameters, and demonstrates comparable or better performance than fully fine-tuned models across various dense tasks. Specifically, SFA consists of external adapters and internal adapters which are sequentially operated over a transformer model. For external adapters, we properly select the places and amount of additional multilayer perception (MLP). For internal adapters, we transform a few task-important parameters inside the transformer, which are automatically discovered through a simple yet effective lottery ticket algorithm. Our experiments show that the dual adapter module, a.k.a SFA, is essential to achieve the best trade-off on dense vision tasks, such as segmentation, detection and depth-estimation, outperforming other adapters with a single module.

Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from images multiple times, which can be ineffective and inefficient. By contrast, we propose to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off. The proposed FC-CLIP, benefits from the following observations: the frozen CLIP backbone maintains the ability of open-vocabulary classification and can also serve as a strong mask generator, and the convolutional CLIP generalizes well to a larger input resolution than the one used during contrastive image-text pretraining. When training on COCO panoptic data only and testing in a zero-shot manner, FC-CLIP achieve 26.8 PQ, 16.8 AP, and 34.1 mIoU on ADE20K, 18.2 PQ, 27.9 mIoU on Mapillary Vistas, 44.0 PQ, 26.8 AP, 56.2 mIoU on Cityscapes, outperforming the prior art by +4.2 PQ, +2.4 AP, +4.2 mIoU on ADE20K, +4.0 PQ on Mapillary Vistas and +20.1 PQ on Cityscapes, respectively. Additionally, the training and testing time of FC-CLIP is 7.5x and 6.6x significantly faster than the same prior art, while using 5.9x fewer parameters. FC-CLIP also sets a new state-of-the-art performance across various open-vocabulary semantic segmentation datasets. Code at https://github.com/bytedance/fc-clip, Comment: NeurIPS 2023 camera ready. code and model available at https://github.com/bytedance/fc-clip

State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained CLIP from image-text to video-text. Specifically, MV-Adapter utilizes bottleneck structures in both video and text branches, along with two novel components. The first is a Temporal Adaptation Module that is incorporated in the video branch to introduce global and local temporal contexts. We also train weights calibrations to adjust to dynamic variations across frames. The second is Cross Modality Tying that generates weights for video/text branches through sharing cross modality factors, for better aligning between modalities. Thanks to above innovations, MV-Adapter can achieve comparable or better performance than standard full fine-tuning with negligible parameters overhead. Notably, MV-Adapter consistently outperforms various competing methods in V2T/T2V tasks with large margins on five widely used VTR benchmarks (MSR-VTT, MSVD, LSMDC, DiDemo, and ActivityNet).

Geospatial Artificial Intelligence (GeoAI) is an interdisciplinary field enjoying tremendous adoption. However, the efficient design and implementation of GeoAI systems face many open challenges. This is mainly due to the lack of non-standardized approaches to artificial intelligence tool development, inadequate platforms, and a lack of multidisciplinary engagements, which all motivate domain experts to seek a shared stage with scientists and engineers to solve problems of significant impact on society. Since its inception in 2017, the GeoAI series of workshops has been co-located with the Association for Computing Machinery International Conference on Advances in Geographic Information Systems. The workshop series has fostered a nexus for geoscientists, computer scientists, engineers, entrepreneurs, and decision-makers, from academia, industry, and government to engage in artificial intelligence, spatiotemporal data computing, and geospatial data science research, motivated by various challenges. In this article, we revisit and discuss the state of GeoAI open research directions, the recent developments, and an emerging agenda calling for a continued cross-disciplinary community engagement., Comment: 12 pages, 1 figure, 1 table

Recent Knowledge distillation (KD) studies show that different manually designed schemes impact the learned results significantly. Yet, in KD, automatically searching an optimal distillation scheme has not yet been well explored. In this paper, we propose DistPro, a novel framework which searches for an optimal KD process via differentiable meta-learning. Specifically, given a pair of student and teacher networks, DistPro first sets up a rich set of KD connection from the transmitting layers of the teacher to the receiving layers of the student, and in the meanwhile, various transforms are also proposed for comparing feature maps along its pathway for the distillation. Then, each combination of a connection and a transform choice (pathway) is associated with a stochastic weighting process which indicates its importance at every step during the distillation. In the searching stage, the process can be effectively learned through our proposed bi-level meta-optimization strategy. In the distillation stage, DistPro adopts the learned processes for knowledge distillation, which significantly improves the student accuracy especially when faster training is required. Lastly, we find the learned processes can be generalized between similar tasks and networks. In our experiments, DistPro produces state-of-the-art (SoTA) accuracy under varying number of learning epochs on popular datasets, i.e. CIFAR100 and ImageNet, which demonstrate the effectiveness of our framework., Comment: 14 pages, 5 figures

The semantic segmentation of nighttime scenes is a challenging problem that is key to impactful applications like self-driving cars. Yet, it has received little attention compared to its daytime counterpart. In this paper, we propose NightLab, a novel nighttime segmentation framework that leverages multiple deep learning models imbued with night-aware features to yield State-of-The-Art (SoTA) performance on multiple night segmentation benchmarks. Notably, NightLab contains models at two levels of granularity, i.e. image and regional, and each level is composed of light adaptation and segmentation modules. Given a nighttime image, the image level model provides an initial segmentation estimate while, in parallel, a hardness detection module identifies regions and their surrounding context that need further analysis. A regional level model focuses on these difficult regions to provide a significantly improved segmentation. All the models in NightLab are trained end-to-end using a set of proposed night-aware losses without handcrafted heuristics. Extensive experiments on the NightCity and BDD100K datasets show NightLab achieves SoTA performance compared to concurrent methods., Comment: 8pages, 6 figures, accept at CVPR 2022

Neural network-based semantic segmentation has achieved remarkable results when large amounts of annotated data are available, that is, in the supervised case. However, such data is expensive to collect and so methods have been developed to adapt models trained on related, often synthetic data for which labels are readily available. Current adaptation approaches do not consider the dependence of the generalization/transferability of these models on network architecture. In this paper, we perform neural architecture search (NAS) to provide architecture-level perspective and analysis for domain adaptation. We identify the optimization gap that exists when searching architectures for unsupervised domain adaptation which makes this NAS problem uniquely difficult. We propose bridging this gap by using maximum mean discrepancy and regional weighted entropy to estimate the accuracy metric. Experimental results on several widely adopted benchmarks show that our proposed AutoAdapt framework indeed discovers architectures that improve the performance of a number of existing adaptation techniques., Comment: short version has been accepted at 1st NAS workshop co-organized with CVPR 2021

Land-cover classification using remote sensing imagery is an important Earth observation task. Recently, land cover classification has benefited from the development of fully connected neural networks for semantic segmentation. The benchmark datasets available for training deep segmentation models in remote sensing imagery tend to be small, however, often consisting of only a handful of images from a single location with a single scale. This limits the models' ability to generalize to other datasets. Domain adaptation has been proposed to improve the models' generalization but we find these approaches are not effective for dealing with the scale variation commonly found between remote sensing image collections. We therefore propose a scale aware adversarial learning framework to perform joint cross-location and cross-scale land-cover classification. The framework has a dual discriminator architecture with a standard feature discriminator as well as a novel scale discriminator. We also introduce a scale attention module which produces scale-enhanced features. Experimental results show that the proposed framework outperforms state-of-the-art domain adaptation methods by a large margin., Comment: The open-sourced codes are available on Github: https://github.com/xdeng7/scale-aware_da

That most deep learning models are purely data driven is both a strength and a weakness. Given sufficient training data, the optimal model for a particular problem can be learned. However, this is usually not the case and so instead the model is either learned from scratch from a limited amount of training data or pre-trained on a different problem and then fine-tuned. Both of these situations are potentially suboptimal and limit the generalizability of the model. Inspired by this, we investigate methods to inform or guide deep learning models for geospatial image analysis to increase their performance when a limited amount of training data is available or when they are applied to scenarios other than which they were trained on. In particular, we exploit the fact that there are certain fundamental rules as to how things are distributed on the surface of the Earth and these rules do not vary substantially between locations. Based on this, we develop a novel feature pooling method for convolutional neural networks using Getis-Ord Gi* analysis from geostatistics. Experimental results show our proposed pooling function has significantly better generalization performance compared to a standard data-driven approach when applied to overhead image segmentation.

This paper develops a deep-learning framework to synthesize a ground-level view of a location given an overhead image. We propose a novel conditional generative adversarial network (cGAN) in which the trained generator generates realistic looking and representative ground-level images using overhead imagery as auxiliary information. The generator is an encoder-decoder network which allows us to compare low- and high-level features as well as their concatenation for encoding the overhead imagery. We also demonstrate how our framework can be used to perform land cover classification by modifying the trained cGAN to extract features from overhead imagery. This is interesting because, although we are using this modified cGAN as a feature extractor for overhead imagery, it incorporates knowledge of how locations look from the ground., Comment: 5 pages. arXiv admin note: text overlap with arXiv:1806.05129

Conventional remote sensing image retrieval (RSIR) systems usually perform single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. This assumption, however, ignores the complexity of remote sensing images, where an image might have multiple classes (i.e., multiple labels), thus resulting in worse retrieval performance. We therefore propose a novel multi-label RSIR approach with fully convolutional networks (FCN). In our approach, we first train a FCN model using a pixel-wise labeled dataset,and the trained FCN is then used to predict the segmentation maps of each image in the considered archive. We finally extract region convolutional features of each image based on its segmentation map.The region features can be either used to perform region-based retrieval or further post-processed to obtain a feature vector for similarity measure. The experimental results show that our approach achieves state-of-the-art performance in contrast to conventional single-label and recent multi-label RSIR approaches., Comment: 8 pages

This paper investigates conditional generative adversarial networks (cGANs) to overcome a fundamental limitation of using geotagged media for geographic discovery, namely its sparse and uneven spatial distribution. We train a cGAN to generate ground-level views of a location given overhead imagery. We show the "fake" ground-level images are natural looking and are structurally similar to the real images. More significantly, we show the generated images are representative of the locations and that the representations learned by the cGANs are informative. In particular, we show that dense feature maps generated using our framework are more effective for land-cover classification than approaches which spatially interpolate features extracted from sparse ground-level images. To our knowledge, ours is the first work to use cGANs to generate ground-level views given overhead imagery and to explore the benefits of the learned representations., Comment: 10 pages, 5 figures, camera-ready version of ACM SIGSPATIAL 2018 (ORAL)

In recent years, geotagged social media has become popular as a novel source for geographic knowledge discovery. Ground-level images and videos provide a different perspective than overhead imagery and can be applied to a range of applications such as land use mapping, activity detection, pollution mapping, etc. The sparse and uneven distribution of this data presents a problem, however, for generating dense maps. We therefore investigate the problem of spatially interpolating the high-dimensional features extracted from sparse social media to enable dense labeling using standard classifiers. Further, we show how prior knowledge about region boundaries can be used to improve the interpolation through spatial morphing kernel regression. We show that an interpolate-then-classify framework can produce dense maps from sparse observations but that care must be taken in choosing the interpolation method. We also show that the spatial morphing kernel improves the results., Comment: accepted by ICIP 2018

We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of georeferenced, ground-level images suggest an alternate approach to this geographic knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the City of San Francisco. Individual images are classified using a novel convolutional neural network containing two streams, one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geo-visualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level which represents a strong baseline for the challenging 45-way land use classification problem especially given the noisiness of the image data.

This paper performs a quantitative comparison of open-source data available on the Internet for the fine-grain mapping of land use. Three points of interest (POI) data sources--Google Places, Bing Maps, and the Yellow Pages--and one volunteered geographic information data source--Open Street Map (OSM)--are compared with each other at the parcel level for San Francisco with respect to a proposed fine-grain land-use taxonomy. The sources are also compared to coarse-grain authoritative data which we consider to be the ground truth. Results show limited agreement among the data sources as well as limited accuracy with respect to the authoritative data even at coarse class granularity. We conclude that POI and OSM data do not appear to be sufficient alone for fine-grain land-use mapping., Comment: ACM SIGSPATIAL 2017 Workshop on Urban GIS