Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly. Generally, pipeline models outperform end-to-end models, but the intermediate transcription necessarily discards some potentially useful non-textual information. In addition to textual information, speech can convey details such as accent, mood, and and emphasis, which should be effectively captured in the encoded representation. In this paper, we investigate whether non-textual information, which is overlooked by pipeline-based models, can be leveraged to improve speech-image matching performance. We thoroughly analyze and compare End-to-End models, pipeline models, and our proposed dual-channel model for robust audio-image retrieval on a variety of datasets. Our approach achieves a substantial performance gain over the previous state-of-the-art by leveraging strong pretrained models, a prompting mechanism and a bifurcated design.
The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility modeling is essential. Traditional methods, often based on Bayesian Personalized Ranking (BPR), have shown limited performance. Recent efforts have explored using generative models in compatibility modeling and item retrieval, where generated images serve as additional inputs. However, these approaches often overlook the quality of generated images, which could be crucial for model performance. Additionally, generative models typically require large datasets, posing challenges when such data is scarce. To address these issues, we introduce the Generative Compatibility Model (GeCo), a two-stage approach that improves fashion image retrieval through paired image-to-image translation. First, the Complementary Item Generation Model (CIGM), built on Conditional Generative Adversarial Networks (GANs), generates target item images (e.g., bottoms) from seed items (e.g., tops), offering conditioning signals for retrieval. These generated samples are then integrated into GeCo, enhancing compatibility modeling and retrieval accuracy. Evaluations on three datasets show that GeCo outperforms state-of-the-art baselines. Key contributions include: (i) the GeCo model utilizing paired image-to-image translation within the Composed Image Retrieval framework, (ii) comprehensive evaluations on benchmark datasets, and (iii) the release of a new Fashion Taobao dataset designed for top-bottom retrieval, promoting further research.
In this study, we aim to develop a domestic service robot (DSR) that, guided by open-vocabulary instructions, can carry everyday objects to the specified pieces of furniture. Few existing methods handle mobile manipulation tasks with open-vocabulary instructions in the image retrieval setting, and most do not identify both the target objects and the receptacles. We propose the Dual-Mode Multimodal Ranking model (DM2RM), which enables images of both the target objects and receptacles to be retrieved using a single model based on multimodal foundation models. We introduce a switching mechanism that leverages a mode token and phrase identification via a large language model to switch the embedding space based on the prediction target. To evaluate the DM2RM, we construct a novel dataset including real-world images collected from hundreds of building-scale environments and crowd-sourced instructions with referring expressions. The evaluation results show that the proposed DM2RM outperforms previous approaches in terms of standard metrics in image retrieval settings. Furthermore, we demonstrate the application of the DM2RM on a standardized real-world DSR platform including fetch-and-carry actions, where it achieves a task success rate of 82% despite the zero-shot transfer setting. Demonstration videos, code, and more materials are available at https://kkrr10.github.io/dm2rm/.
The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2) requiring tuning by additional data or training. In this paper, we rethink and analyze the existing model merging paradigm. We discover that using a single model's weights can hardly simulate all the models' performance. To tackle this issue, we propose Elect, Mask & Rescale-Merging (EMR-Merging). We first (a) elect a unified model from all the model weights and then (b) generate extremely lightweight task-specific modulators, including masks and rescalers, to align the direction and magnitude between the unified model and each specific model, respectively. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance. We find that EMR-Merging shows outstanding performance compared to existing merging methods under different classical and newly-established settings, including merging different numbers of vision models (up to 30), NLP models, PEFT models, and multi-modal models.
Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to the drastic appearance and geometry differences between views. In this paper, we propose a new approach for cross-view image geo-localization, i.e., the Panorama-BEV Co-Retrieval Network. Specifically, by utilizing the ground plane assumption and geometric relations, we convert street view panorama images into the BEV view, reducing the gap between street panoramas and satellite imagery. In the existing retrieval of street view panorama images and satellite images, we introduce BEV and satellite image retrieval branches for collaborative retrieval. By retaining the original street view retrieval branch, we overcome the limited perception range issue of BEV representation. Our network enables comprehensive perception of both the global layout and local details around the street view capture locations. Additionally, we introduce CVGlobal, a global cross-view dataset that is closer to real-world scenarios. This dataset adopts a more realistic setup, with street view directions not aligned with satellite images. CVGlobal also includes cross-regional, cross-temporal, and street view to map retrieval tests, enabling a comprehensive evaluation of algorithm performance. Our method excels in multiple tests on common cross-view datasets such as CVUSA, CVACT, VIGOR, and our newly introduced CVGlobal, surpassing the current state-of-the-art approaches. The code and datasets can be found at \url{https://github.com/yejy53/EP-BEV}.
This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance enhancements, this work prioritizes the crucial trade-off between performance and memory requirements. The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors. A distinctive property of the model is the capability for asymmetric similarity estimation. Database images are represented with a smaller number of descriptors compared to query images, enabling performance improvements without increasing memory consumption. To ensure adaptability across different applications, a universal model is introduced that adjusts to a varying number of local descriptors during the testing phase. Results on standard benchmarks demonstrate the superiority of our approach over both hand-crafted and learned models. In particular, compared with current state-of-the-art methods that overlook their memory footprint, our approach not only attains superior performance but does so with a significantly reduced memory footprint. The code and pretrained models are publicly available at: https://github.com/pavelsuma/ames
Medical images play a crucial role in modern healthcare by providing vital information for diagnosis, treatment planning, and disease monitoring. Fields such as radiology and pathology rely heavily on accurate image interpretation, with radiologists examining X-rays, CT scans, and MRIs to diagnose conditions from fractures to cancer, while pathologists use microscopy and digital images to detect cellular abnormalities for diagnosing cancers and infections. The technological advancements have exponentially increased the volume and complexity of medical images, necessitating efficient tools for management and retrieval. Content-Based Image Retrieval (CBIR) systems address this need by searching and retrieving images based on visual content, enhancing diagnostic accuracy by allowing clinicians to find similar cases and compare pathological patterns. Comprehensive validation of image search engines in medical applications involves evaluating performance metrics like accuracy, indexing, and search times, and storage overhead, ensuring reliable and efficient retrieval of accurate results, as demonstrated by recent validations in histopathology.
This paper introduces a novel approach to improving the training stability of self-supervised learning (SSL) methods by leveraging a non-parametric memory of seen concepts. The proposed method involves augmenting a neural network with a memory component to stochastically compare current image views with previously encountered concepts. Additionally, we introduce stochastic memory blocks to regularize training and enforce consistency between image views. We extensively benchmark our method on many vision tasks, such as linear probing, transfer learning, low-shot classification, and image retrieval on many datasets. The experimental results consolidate the effectiveness of the proposed approach in achieving stable SSL training without additional regularizers while learning highly transferable representations and requiring less computing time and resources.
Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and image via the cross-attention mechanism (one-tower framework) or in a common embedding space (two-tower framework). Recently, generative cross-modal retrieval has emerged as a new research line, which assigns images with unique string identifiers and generates the target identifier as the retrieval target. Despite its great potential, existing generative approaches are limited due to the following issues: insufficient visual information in identifiers, misalignment with high-level semantics, and learning gap towards the retrieval target. To address the above issues, we propose an autoregressive voken generation method, named AVG. AVG tokenizes images into vokens, i.e., visual tokens, and innovatively formulates the text-to-image retrieval task as a token-to-voken generation problem. AVG discretizes an image into a sequence of vokens as the identifier of the image, while maintaining the alignment with both the visual information and high-level semantics of the image. Additionally, to bridge the learning gap between generative training and the retrieval target, we incorporate discriminative training to modify the learning direction during token-to-voken training. Extensive experiments demonstrate that AVG achieves superior results in both effectiveness and efficiency.
Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to process a large number of visual tokens does not guarantee effective retrieval and reasoning for multi-image question answering (MIQA), especially in real-world applications like photo album searches or satellite imagery analysis. In this work, we first assess the limitations of current benchmarks for long-context LMMs. We address these limitations by introducing a new vision-centric, long-context benchmark, "Visual Haystacks (VHs)". We comprehensively evaluate both open-source and proprietary models on VHs, and demonstrate that these models struggle when reasoning across potentially unrelated images, perform poorly on cross-image reasoning, as well as exhibit biases based on the placement of key information within the context window. Towards a solution, we introduce MIRAGE (Multi-Image Retrieval Augmented Generation), an open-source, lightweight visual-RAG framework that processes up to 10k images on a single 40G A100 GPU -- far surpassing the 1k-image limit of contemporary models. MIRAGE demonstrates up to 13% performance improvement over existing open-source LMMs on VHs, sets a new state-of-the-art on the RetVQA multi-image QA benchmark, and achieves competitive performance on single-image QA with state-of-the-art LMMs.
Determining the necessity of resecting malignant polyps during colonoscopy screen is crucial for patient outcomes, yet challenging due to the time-consuming and costly nature of histopathology examination. While deep learning-based classification models have shown promise in achieving optical biopsy with endoscopic images, they often suffer from a lack of explainability. To overcome this limitation, we introduce EndoFinder, a content-based image retrieval framework to find the 'digital twin' polyp in the reference database given a newly detected polyp. The clinical semantics of the new polyp can be inferred referring to the matched ones. EndoFinder pioneers a polyp-aware image encoder that is pre-trained on a large polyp dataset in a self-supervised way, merging masked image modeling with contrastive learning. This results in a generic embedding space ready for different downstream clinical tasks based on image retrieval. We validate the framework on polyp re-identification and optical biopsy tasks, with extensive experiments demonstrating that EndoFinder not only achieves explainable diagnostics but also matches the performance of supervised classification models. EndoFinder's reliance on image retrieval has the potential to support diverse downstream decision-making tasks during real-time colonoscopy procedures.
Zero-Shot Composed Image Retrieval (ZS-CIR) has garnered increasing interest in recent years, which aims to retrieve a target image based on a query composed of a reference image and a modification text without training samples. Specifically, the modification text describes the distinction between the two images. To conduct ZS-CIR, the prevailing methods employ pre-trained image-to-text models to transform the query image and text into a single text, which is then projected into the common feature space by CLIP to retrieve the target image. However, these methods neglect that ZS-CIR is a typical fuzzy retrieval task, where the semantics of the target image are not strictly defined by the query image and text. To overcome this limitation, this paper proposes a training-free LLM-based Divergent Reasoning and Ensemble (LDRE) method for ZS-CIR to capture diverse possible semantics of the composed result. Firstly, we employ a pre-trained captioning model to generate dense captions for the reference image, focusing on different semantic perspectives of the reference image. Then, we prompt Large Language Models (LLMs) to conduct divergent compositional reasoning based on the dense captions and modification text, deriving divergent edited captions that cover the possible semantics of the composed target. Finally, we design a divergent caption ensemble to obtain the ensemble caption feature weighted by semantic relevance scores, which is subsequently utilized to retrieve the target image in the CLIP feature space. Extensive experiments on three public datasets demonstrate that our proposed LDRE achieves the new state-of-the-art performance.
This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These gradients are projected to a lower dimension and then concatenated with the model's output embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification, clustering and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training.
Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accurately reflect the factual information and common sense conveyed by the input text prompts. We refer to this issue as Image hallucination. Drawing from studies on hallucinations in language models, we classify this problem into three types and propose a methodology that uses factual images retrieved from external sources to generate realistic images. Depending on the nature of the hallucination, we employ off-the-shelf image editing tools, either InstructPix2Pix or IP-Adapter, to leverage factual information from the retrieved image. This approach enables the generation of images that accurately reflect the facts and common sense.
The objective of this paper is to address the localization problem using omnidirectional images captured by a catadioptric vision system mounted on the robot. For this purpose, we explore the potential of Siamese Neural Networks for modeling indoor environments using panoramic images as the unique source of information. Siamese Neural Networks are characterized by their ability to generate a similarity function between two input data, in this case, between two panoramic images. In this study, Siamese Neural Networks composed of two Convolutional Neural Networks (CNNs) are used. The output of each CNN is a descriptor which is used to characterize each image. The dissimilarity of the images is computed by measuring the distance between these descriptors. This fact makes Siamese Neural Networks particularly suitable to perform image retrieval tasks. First, we evaluate an initial task strongly related to localization that consists in detecting whether two images have been captured in the same or in different rooms. Next, we assess Siamese Neural Networks in the context of a global localization problem. The results outperform previous techniques for solving the localization task using the COLD-Freiburg dataset, in a variety of lighting conditions, specially when using images captured in cloudy and night conditions.
Image retrieval plays a pivotal role in applications from wildlife conservation to healthcare, for finding individual animals or relevant images to aid diagnosis. Although deep learning techniques for image retrieval have advanced significantly, their imperfect real-world performance often necessitates including human expertise. Human-in-the-loop approaches typically rely on humans completing the task independently and then combining their opinions with an AI model in various ways, as these models offer very little interpretability or \textit{correctability}. To allow humans to intervene in the AI model instead, thereby saving human time and effort, we adapt the Concept Bottleneck Model (CBM) and propose \texttt{CHAIR}. \texttt{CHAIR} (a) enables humans to correct intermediate concepts, which helps \textit{improve} embeddings generated, and (b) allows for flexible levels of intervention that accommodate varying levels of human expertise for better retrieval. To show the efficacy of \texttt{CHAIR}, we demonstrate that our method performs better than similar models on image retrieval metrics without any external intervention. Furthermore, we also showcase how human intervention helps further improve retrieval performance, thereby achieving human-AI complementarity.
Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical practice, the continuously expanding size of WSI databases limits the practical application of the current CBHIR methods. In this paper, we propose a Lifelong Whole Slide Retrieval (LWSR) framework to address the challenges of catastrophic forgetting by progressive model updating on continuously growing retrieval database. Our framework aims to achieve the balance between stability and plasticity during continuous learning. To preserve system plasticity, we utilize local memory bank with reservoir sampling method to save instances, which can comprehensively encompass the feature spaces of both old and new tasks. Furthermore, A distance consistency rehearsal (DCR) module is designed to ensure the retrieval queue's consistency for previous tasks, which is regarded as stability within a lifelong CBHIR system. We evaluated the proposed method on four public WSI datasets from TCGA projects. The experimental results have demonstrated the proposed method is effective and is superior to the state-of-the-art methods.
Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity. We introduce Multi-Group Proportional Representation (MPR), a novel metric that measures representation across intersectional groups. We develop practical methods for estimating MPR, provide theoretical guarantees, and propose optimization algorithms to ensure MPR in retrieval. We demonstrate that existing methods optimizing for equal and proportional representation metrics may fail to promote MPR. Crucially, our work shows that optimizing MPR yields more proportional representation across multiple intersectional groups specified by a rich function class, often with minimal compromise in retrieval accuracy.
We present CEIA, an effective framework for open-world event-based understanding. Currently training a large event-text model still poses a huge challenge due to the shortage of paired event-text data. In response to this challenge, CEIA learns to align event and image data as an alternative instead of directly aligning event and text data. Specifically, we leverage the rich event-image datasets to learn an event embedding space aligned with the image space of CLIP through contrastive learning. In this way, event and text data are naturally aligned via using image data as a bridge. Particularly, CEIA offers two distinct advantages. First, it allows us to take full advantage of the existing event-image datasets to make up the shortage of large-scale event-text datasets. Second, leveraging more training data, it also exhibits the flexibility to boost performance, ensuring scalable capability. In highlighting the versatility of our framework, we make extensive evaluations through a diverse range of event-based multi-modal applications, such as object recognition, event-image retrieval, event-text retrieval, and domain adaptation. The outcomes demonstrate CEIA's distinct zero-shot superiority over existing methods on these applications.
Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms all fail to strike a good trade-off between the model's generalization ability and retrieval performance, recent researchers have introduced the task of few-shot CIR (FS-CIR) and proposed a textual inversion-based network based on pretrained CLIP model to realize it. Despite its promising performance, the approach encounters two key limitations: simply relying on the few annotated samples for CIR model training and indiscriminately selecting training triplets for CIR model fine-tuning. To address these two limitations, we propose a novel two-stage pseudo triplet guided few-shot CIR scheme, dubbed PTG-FSCIR. In the first stage, we propose an attentive masking and captioning-based pseudo triplet generation method, to construct pseudo triplets from pure image data and use them to fulfill the CIR-task specific pertaining. In the second stage, we propose a challenging triplet-based CIR fine-tuning method, where we design a pseudo modification text-based sample challenging score estimation strategy and a robust top range-based random sampling strategy for sampling robust challenging triplets to promote the model fine-tuning. Notably, our scheme is plug-and-play and compatible with any existing supervised CIR models. We test our scheme across two backbones on three public datasets (i.e., FashionIQ, CIRR, and Birds-to-Words), achieving maximum improvements of 13.3%, 22.2%, and 17.4% respectively, demonstrating our scheme's efficacy.