Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant limitation of CLIP lies in the inadequate length of text input. The length of the text token is restricted to 77, and an empirical study shows the actual effective length is even less than 20. This prevents CLIP from handling detailed descriptions, limiting its applications for image retrieval and text-to-image generation with extensive prerequisites. To this end, we propose Long-CLIP as a plug-and-play alternative to CLIP that supports long-text input, retains or even surpasses its zero-shot generalizability, and aligns the CLIP latent space, making it readily replace CLIP without any further adaptation in downstream frameworks. Nevertheless, achieving this goal is far from straightforward, as simplistic fine-tuning can result in a significant degradation of CLIP's performance. Moreover, substituting the text encoder with a language model supporting longer contexts necessitates pretraining with vast amounts of data, incurring significant expenses. Accordingly, Long-CLIP introduces an efficient fine-tuning solution on CLIP with two novel strategies designed to maintain the original capabilities, including (1) a knowledge-preserved stretching of positional embedding and (2) a primary component matching of CLIP features. With leveraging just one million extra long text-image pairs, Long-CLIP has shown the superiority to CLIP for about 20% in long caption text-image retrieval and 6% in traditional text-image retrieval tasks, e.g., COCO and Flickr30k. Furthermore, Long-CLIP offers enhanced capabilities for generating images from detailed text descriptions by replacing CLIP in a plug-and-play manner.
In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes. To broaden the applicability of image retrieval methods for diverse purposes and uncover more general patterns, we innovatively introduce a crucial factor from computational aesthetics, namely image composition, into this topic. By explicitly integrating composition-related information extracted by CNN into the designed retrieval model, our method considers both the image's composition rules and semantic information. Qualitative and quantitative experiments demonstrate that the image retrieval network guided by composition information outperforms those relying solely on content information, facilitating the identification of images in databases closer to the target image in human perception. Please visit https://github.com/linty5/CCBIR to try our codes.
Classical structural-based visual localization methods offer high accuracy but face trade-offs in terms of storage, speed, and privacy. A recent innovation, keypoint scene coordinate regression (KSCR) named D2S addresses these issues by leveraging graph attention networks to enhance keypoint relationships and predict their 3D coordinates using a simple multilayer perceptron (MLP). Camera pose is then determined via PnP+RANSAC, using established 2D-3D correspondences. While KSCR achieves competitive results, rivaling state-of-the-art image-retrieval methods like HLoc across multiple benchmarks, its performance is hindered when data samples are limited due to the deep learning model's reliance on extensive data. This paper proposes a solution to this challenge by introducing a pipeline for keypoint descriptor synthesis using Neural Radiance Field (NeRF). By generating novel poses and feeding them into a trained NeRF model to create new views, our approach enhances the KSCR's generalization capabilities in data-scarce environments. The proposed system could significantly improve localization accuracy by up to 50% and cost only a fraction of time for data synthesis. Furthermore, its modular design allows for the integration of multiple NeRFs, offering a versatile and efficient solution for visual localization. The implementation is publicly available at: https://github.com/ais-lab/DescriptorSynthesis4Feat2Map.
We present PAPERCLIP (Proposal Abstracts Provide an Effective Representation for Contrastive Language-Image Pre-training), a method which associates astronomical observations imaged by telescopes with natural language using a neural network model. The model is fine-tuned from a pre-trained Contrastive Language-Image Pre-training (CLIP) model using successful observing proposal abstracts and corresponding downstream observations, with the abstracts optionally summarized via guided generation using large language models (LLMs). Using observations from the Hubble Space Telescope (HST) as an example, we show that the fine-tuned model embodies a meaningful joint representation between observations and natural language through tests targeting image retrieval (i.e., finding the most relevant observations using natural language queries) and description retrieval (i.e., querying for astrophysical object classes and use cases most relevant to a given observation). Our study demonstrates the potential for using generalist foundation models rather than task-specific models for interacting with astronomical data by leveraging text as an interface.
This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to the commitment of "what you sketch is what you get". A pilot study underscores the necessity, revealing that deformities in existing models stem from spatial-conditioning. To rectify this, we propose an abstraction-aware framework, utilising a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association. Our approach operates seamlessly during inference without the need for textual prompts; a simple, rough sketch akin to what you and I can create suffices! We welcome everyone to examine results presented in the paper and its supplementary. Contributions include democratising sketch control, introducing an abstraction-aware framework, and leveraging discriminative guidance, validated through extensive experiments.
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://github.com/hly1998/BRCD.
Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response. Despite its significance, accurately localizing the geographical extent of these images, crucial for effective utilization, poses substantial challenges. Current manual localization efforts are time-consuming, motivating the need for automated solutions. We propose a novel approach - leveraging image retrieval - to address this challenge efficiently. We introduce innovative training techniques, including Year-Wise Data Augmentation and a Neutral-Aware Multi-Similarity Loss, which contribute to the development of a high-performance model, EarthLoc. We develop six evaluation datasets and perform a comprehensive benchmark comparing EarthLoc to existing methods, showcasing its superior efficiency and accuracy. Our approach marks a significant advancement in automating the localization of astronaut photography, which will help bridge a critical gap in Earth observations data. Code and datasets are available at https://github.com/gmberton/EarthLoc
Content-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. Current CBIR systems face limitations due to their specialization to certain pathologies, limiting their utility. In response, we propose using vision foundation models as powerful and versatile off-the-shelf feature extractors for content-based medical image retrieval. By benchmarking these models on a comprehensive dataset of 1.6 million 2D radiological images spanning four modalities and 161 pathologies, we identify weakly-supervised models as superior, achieving a P@1 of up to 0.594. This performance not only competes with a specialized model but does so without the need for fine-tuning. Our analysis further explores the challenges in retrieving pathological versus anatomical structures, indicating that accurate retrieval of pathological features presents greater difficulty. Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning.
Asymmetric image retrieval is a task that seeks to balance retrieval accuracy and efficiency by leveraging lightweight and large models for the query and gallery sides, respectively. The key to asymmetric image retrieval is realizing feature compatibility between different models. Despite the great progress, most existing approaches either rely on classifiers inherited from gallery models or simply impose constraints at the instance level, ignoring the structure of embedding space. In this work, we propose a simple yet effective structure similarity preserving method to achieve feature compatibility between query and gallery models. Specifically, we first train a product quantizer offline with the image features embedded by the gallery model. The centroid vectors in the quantizer serve as anchor points in the embedding space of the gallery model to characterize its structure. During the training of the query model, anchor points are shared by the query and gallery models. The relationships between image features and centroid vectors are considered as structure similarities and constrained to be consistent. Moreover, our approach makes no assumption about the existence of any labeled training data and thus can be extended to an unlimited amount of data. Comprehensive experiments on large-scale landmark retrieval demonstrate the effectiveness of our approach. Our code is released at: https://github.com/MCC-WH/SSP.
In the domain of image layout representation learning, the critical process of translating image layouts into succinct vector forms is increasingly significant across diverse applications, such as image retrieval, manipulation, and generation. Most approaches in this area heavily rely on costly labeled datasets and notably lack in adapting their modeling and learning methods to the specific nuances of photographic image layouts. This shortfall makes the learning process for photographic image layouts suboptimal. In our research, we directly address these challenges. We innovate by defining basic layout primitives that encapsulate various levels of layout information and by mapping these, along with their interconnections, onto a heterogeneous graph structure. This graph is meticulously engineered to capture the intricate layout information within the pixel domain explicitly. Advancing further, we introduce novel pretext tasks coupled with customized loss functions, strategically designed for effective self-supervised learning of these layout graphs. Building on this foundation, we develop an autoencoder-based network architecture skilled in compressing these heterogeneous layout graphs into precise, dimensionally-reduced layout representations. Additionally, we introduce the LODB dataset, which features a broader range of layout categories and richer semantics, serving as a comprehensive benchmark for evaluating the effectiveness of layout representation learning methods. Our extensive experimentation on this dataset demonstrates the superior performance of our approach in the realm of photographic image layout representation learning.
Image retrieval enables an efficient search through vast amounts of satellite imagery and returns similar images to a query. Deep learning models can identify images across various semantic concepts without the need for annotations. This work proposes to use Geospatial Foundation Models, like Prithvi, for remote sensing image retrieval with multiple benefits: i) the models encode multi-spectral satellite data and ii) generalize without further fine-tuning. We introduce two datasets to the retrieval task and observe a strong performance: Prithvi processes six bands and achieves a mean Average Precision of 97.62% on BigEarthNet-43 and 44.51% on ForestNet-12, outperforming other RGB-based models. Further, we evaluate three compression methods with binarized embeddings balancing retrieval speed and accuracy. They match the retrieval speed of much shorter hash codes while maintaining the same accuracy as floating-point embeddings but with a 32-fold compression. The code is available at https://github.com/IBM/remote-sensing-image-retrieval.
Learned sparse retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors that can be indexed and retrieved efficiently with an inverted index. We explore the application of LSR to the multi-modal domain, with a focus on text-image retrieval. While LSR has seen success in text retrieval, its application in multimodal retrieval remains underexplored. Current approaches like LexLIP and STAIR require complex multi-step training on massive datasets. Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors. We address issues of high dimension co-activation and semantic deviation through a new training algorithm, using Bernoulli random variables to control query expansion. Experiments with two dense models (BLIP, ALBEF) and two datasets (MSCOCO, Flickr30k) show that our proposed algorithm effectively reduces co-activation and semantic deviation. Our best-performing sparsified model outperforms state-of-the-art text-image LSR models with a shorter training time and lower GPU memory requirements. Our approach offers an effective solution for training LSR retrieval models in multimodal settings. Our code and model checkpoints are available at github.com/thongnt99/lsr-multimodal
Effectively and efficiently retrieving images from remote sensing databases is a critical challenge in the realm of remote sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages, yet the potential of multi-level feature integration from sketches remains underexplored, leading to suboptimal retrieval performance. To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update. This approach employs only vision information and does not require semantic knowledge concerning the sketch and image. It starts by employing multi-level self-attention guided feature extraction to tokenize the query sketches, as well as self-attention feature extraction to tokenize the candidate images. It then employs cross-attention mechanisms to establish token correspondence between these two modalities, facilitating the computation of sketch-to-image similarity. Our method significantly outperforms existing sketch-based remote sensing image retrieval techniques, as evidenced by tests on multiple datasets. Notably, it also exhibits robust zero-shot learning capabilities and strong generalizability in handling unseen categories and novel remote sensing data. The method's scalability can be further enhanced by the pre-calculation of retrieval tokens for all candidate images in a database. This research underscores the significant potential of multi-level, attention-guided tokenization in cross-modal remote sensing image retrieval. For broader accessibility and research facilitation, we have made the code and dataset used in this study publicly available online. Code and dataset are available at https://github.com/Snowstormfly/Cross-modal-retrieval-MLAGT.
We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.
Deep Metric Learning (DML) has long attracted the attention of the machine learning community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained models on conventional image datasets. As a result of the success of recent pre-trained models trained from larger-scale datasets, it is challenging to adapt the model to the DML tasks in the local data domain while retaining the previously gained knowledge. In this paper, we investigate parameter-efficient methods for fine-tuning the pre-trained model for DML tasks. In particular, we propose a novel and effective framework based on learning Visual Prompts (VPT) in the pre-trained Vision Transformers (ViT). Based on the conventional proxy-based DML paradigm, we augment the proxy by incorporating the semantic information from the input image and the ViT, in which we optimize the visual prompts for each class. We demonstrate that our new approximations with semantic information are superior to representative capabilities, thereby improving metric learning performance. We conduct extensive experiments to demonstrate that our proposed framework is effective and efficient by evaluating popular DML benchmarks. In particular, we demonstrate that our fine-tuning method achieves comparable or even better performance than recent state-of-the-art full fine-tuning works of DML while tuning only a small percentage of total parameters.
We define and investigate the problem of $\textit{c-approximate window search}$: approximate nearest neighbor search where each point in the dataset has a numeric label, and the goal is to find nearest neighbors to queries within arbitrary label ranges. Many semantic search problems, such as image and document search with timestamp filters, or product search with cost filters, are natural examples of this problem. We propose and theoretically analyze a modular tree-based framework for transforming an index that solves the traditional c-approximate nearest neighbor problem into a data structure that solves window search. On standard nearest neighbor benchmark datasets equipped with random label values, adversarially constructed embeddings, and image search embeddings with real timestamps, we obtain up to a $75\times$ speedup over existing solutions at the same level of recall.
Local feature matching enjoys wide-ranging applications in the realm of computer vision, encompassing domains such as image retrieval, 3D reconstruction, and object recognition. However, challenges persist in improving the accuracy and robustness of matching due to factors like viewpoint and lighting variations. In recent years, the introduction of deep learning models has sparked widespread exploration into local feature matching techniques. The objective of this endeavor is to furnish a comprehensive overview of local feature matching methods. These methods are categorized into two key segments based on the presence of detectors. The Detector-based category encompasses models inclusive of Detect-then-Describe, Joint Detection and Description, Describe-then-Detect, as well as Graph Based techniques. In contrast, the Detector-free category comprises CNN Based, Transformer Based, and Patch Based methods. Our study extends beyond methodological analysis, incorporating evaluations of prevalent datasets and metrics to facilitate a quantitative comparison of state-of-the-art techniques. The paper also explores the practical application of local feature matching in diverse domains such as Structure from Motion, Remote Sensing Image Registration, and Medical Image Registration, underscoring its versatility and significance across various fields. Ultimately, we endeavor to outline the current challenges faced in this domain and furnish future research directions, thereby serving as a reference for researchers involved in local feature matching and its interconnected domains. A comprehensive list of studies in this survey is available at https://github.com/vignywang/Awesome-Local-Feature-Matching .
Vision-Language Models pre-trained on large-scale image-text datasets have shown superior performance in downstream tasks such as image retrieval. Most of the images for pre-training are presented in the form of open domain common-sense visual elements. Differently, video covers in short video search scenarios are presented as user-originated contents that provide important visual summaries of videos. In addition, a portion of the video covers come with manually designed cover texts that provide semantic complements. In order to fill in the gaps in short video cover data, we establish the first large-scale cover-text benchmark for Chinese short video search scenarios. Specifically, we release two large-scale datasets CBVS-5M/10M to provide short video covers, and the manual fine-labeling dataset CBVS-20K to provide real user queries, which serves as an image-text benchmark test in the Chinese short video search field. To integrate the semantics of cover text in the case of modality missing, we propose UniCLIP where cover texts play a guiding role during training, however are not relied upon by inference. Extensive evaluation on CBVS-20K demonstrates the excellent performance of our proposal. UniCLIP has been deployed to Tencent's online video search systems with hundreds of millions of visits and achieved significant gains. The dataset and code are available at https://github.com/QQBrowserVideoSearch/CBVS-UniCLIP.
Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between images are overlooked. Moreover, these methods predominantly focus on the Euclidean space for computational convenience, compromising their ability to map the multi-level semantic relationships between images effectively. To mitigate these shortcomings, we propose a novel unsupervised product quantization method dubbed \textbf{Hi}erarchical \textbf{H}yperbolic \textbf{P}roduct \textbf{Q}uantization (HiHPQ), which learns quantized representations by incorporating hierarchical semantic similarity within hyperbolic geometry. Specifically, we propose a hyperbolic product quantizer, where the hyperbolic codebook attention mechanism and the quantized contrastive learning on the hyperbolic product manifold are introduced to expedite quantization. Furthermore, we propose a hierarchical semantics learning module, designed to enhance the distinction between similar and non-matching images for a query by utilizing the extracted hierarchical semantics as an additional training supervision. Experiments on benchmarks show that our proposed method outperforms state-of-the-art baselines.
Self-supervised learning through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) image representation learning, and thus embodies a significant potential for content-based image retrieval (CBIR) from ever-growing RS image archives. However, the existing MAE based CBIR studies in RS assume that the considered RS images are acquired by a single image sensor, and thus are only suitable for uni-modal CBIR problems. The effectiveness of MAEs for cross-sensor CBIR, which aims to search semantically similar images across different image modalities, has not been explored yet. In this paper, we take the first step to explore the effectiveness of MAEs for sensor-agnostic CBIR in RS. To this end, we present a systematic overview on the possible adaptations of the vanilla MAE to exploit masked image modeling on multi-sensor RS image archives (denoted as cross-sensor masked autoencoders [CSMAEs]) in the context of CBIR. Based on different adjustments applied to the vanilla MAE, we introduce different CSMAE models. We also provide an extensive experimental analysis of these CSMAE models. We finally derive a guideline to exploit masked image modeling for uni-modal and cross-modal CBIR problems in RS. The code of this work is publicly available at https://github.com/jakhac/CSMAE.