Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are dominated by training models with parallel image-text pairs, which are very costly to collect. In this paper, we make the first attempt to explore TBPS without parallel image-text data ($\mu$-TBPS), in which only non-parallel images and texts, or even image-only data, can be adopted. Towards this end, we propose a two-stage framework, generation-then-retrieval (GTR), to first generate the corresponding pseudo text for each image and then perform the retrieval in a supervised manner. In the generation stage, we propose a fine-grained image captioning strategy to obtain an enriched description of the person image, which firstly utilizes a set of instruction prompts to activate the off-the-shelf pretrained vision-language model to capture and generate fine-grained person attributes, and then converts the extracted attributes into a textual description via the finetuned large language model or the hand-crafted template. In the retrieval stage, considering the noise interference of the generated texts for training model, we develop a confidence score-based training scheme by enabling more reliable texts to contribute more during the training. Experimental results on multiple TBPS benchmarks (i.e., CUHK-PEDES, ICFG-PEDES and RSTPReid) show that the proposed GTR can achieve a promising performance without relying on parallel image-text data.
相關內容
Instruction tuning large language model (LLM) on image-text pairs has achieved unprecedented vision-language multimodal abilities. However, their vision-language alignments are only built on image-level, the lack of region-level alignment limits their advancements to fine-grained multimodal understanding. In this paper, we propose instruction tuning on region-of-interest. The key design is to reformulate the bounding box as the format of spatial instruction. The interleaved sequences of visual features extracted by the spatial instruction and the language embedding are input to LLM, and trained on the transformed region-text data in instruction tuning format. Our region-level vision-language model, termed as GPT4RoI, brings brand new conversational and interactive experience beyond image-level understanding. (1) Controllability: Users can interact with our model by both language and spatial instructions to flexibly adjust the detail level of the question. (2) Capacities: Our model supports not only single-region spatial instruction but also multi-region. This unlocks more region-level multimodal capacities such as detailed region caption and complex region reasoning. (3) Composition: Any off-the-shelf object detector can be a spatial instruction provider so as to mine informative object attributes from our model, like color, shape, material, action, relation to other objects, etc. The code, data, and demo can be found at //github.com/jshilong/GPT4RoI.
Existing efforts on text synthesis for code-switching mostly require training on code-switched texts in the target language pairs, limiting the deployment of the models to cases lacking code-switched data. In this work, we study the problem of synthesizing code-switched texts for language pairs absent from the training data. We introduce GLOSS, a model built on top of a pre-trained multilingual machine translation model (PMMTM) with an additional code-switching module. This module, either an adapter or extra prefixes, learns code-switching patterns from code-switched data during training, while the primary component of GLOSS, i.e., the PMMTM, is frozen. The design of only adjusting the code-switching module prevents our model from overfitting to the constrained training data for code-switching. Hence, GLOSS exhibits the ability to generalize and synthesize code-switched texts across a broader spectrum of language pairs. Additionally, we develop a self-training algorithm on target language pairs further to enhance the reliability of GLOSS. Automatic evaluations on four language pairs show that GLOSS achieves at least 55% relative BLEU and METEOR scores improvements compared to strong baselines. Human evaluations on two language pairs further validate the success of GLOSS.
Hyperspectral images (HSI) with abundant spectral information reflected materials property usually perform low spatial resolution due to the hardware limits. Meanwhile, multispectral images (MSI), e.g., RGB images, have a high spatial resolution but deficient spectral signatures. Hyperspectral and multispectral image fusion can be cost-effective and efficient for acquiring both high spatial resolution and high spectral resolution images. Many of the conventional HSI and MSI fusion algorithms rely on known spatial degradation parameters, i.e., point spread function, spectral degradation parameters, spectral response function, or both of them. Another class of deep learning-based models relies on the ground truth of high spatial resolution HSI and needs large amounts of paired training images when working in a supervised manner. Both of these models are limited in practical fusion scenarios. In this paper, we propose an unsupervised HSI and MSI fusion model based on the cycle consistency, called CycFusion. The CycFusion learns the domain transformation between low spatial resolution HSI (LrHSI) and high spatial resolution MSI (HrMSI), and the desired high spatial resolution HSI (HrHSI) are considered to be intermediate feature maps in the transformation networks. The CycFusion can be trained with the objective functions of marginal matching in single transform and cycle consistency in double transforms. Moreover, the estimated PSF and SRF are embedded in the model as the pre-training weights, which further enhances the practicality of our proposed model. Experiments conducted on several datasets show that our proposed model outperforms all compared unsupervised fusion methods. The codes of this paper will be available at this address: https: //github.com/shuaikaishi/CycFusion for reproducibility.
For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource-limited environments (e.g., smartphones). Moreover, due to the inevitable domain shift between model training (source) and deploying (target) stages, compressing those deep models under cross-domain scenarios becomes more challenging. Although some of existing works have already explored cross-domain knowledge distillation for model compression, they are either biased to source data or heavily tangled between source and target data. To this end, we design a novel end-to-end framework called Universal and joint knowledge distillation (UNI-KD) for cross-domain model compression. In particular, we propose to transfer both the universal feature-level knowledge across source and target domains and the joint logit-level knowledge shared by both domains from the teacher to the student model via an adversarial learning scheme. More specifically, a feature-domain discriminator is employed to align teacher's and student's representations for universal knowledge transfer. A data-domain discriminator is utilized to prioritize the domain-shared samples for joint knowledge transfer. Extensive experimental results on four time series datasets demonstrate the superiority of our proposed method over state-of-the-art (SOTA) benchmarks.
Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution. This paper investigates the distillation of visual representations in large teacher vision-language models into lightweight student models using a small- or mid-scale dataset. Notably, this study focuses on open-vocabulary out-of-distribution (OOD) generalization, a challenging problem that has been overlooked in previous model distillation literature. We propose two principles from vision and language modality perspectives to enhance student's OOD generalization: (1) by better imitating teacher's visual representation space, and carefully promoting better coherence in vision-language alignment with the teacher; (2) by enriching the teacher's language representations with informative and finegrained semantic attributes to effectively distinguish between different labels. We propose several metrics and conduct extensive experiments to investigate their techniques. The results demonstrate significant improvements in zero-shot and few-shot student performance on open-vocabulary out-of-distribution classification, highlighting the effectiveness of our proposed approaches. Our code will be released at //github.com/xuanlinli17/large_vlm_distillation_ood
Limited by imaging systems, the reconstruction of Magnetic Resonance Imaging (MRI) images from partial measurement is essential to medical imaging research. Benefiting from the diverse and complementary information of multi-contrast MR images in different imaging modalities, multi-contrast Super-Resolution (SR) reconstruction is promising to yield SR images with higher quality. In the medical scenario, to fully visualize the lesion, radiologists are accustomed to zooming the MR images at arbitrary scales rather than using a fixed scale, as used by most MRI SR methods. In addition, existing multi-contrast MRI SR methods often require a fixed resolution for the reference image, which makes acquiring reference images difficult and imposes limitations on arbitrary scale SR tasks. To address these issues, we proposed an implicit neural representations based dual-arbitrary multi-contrast MRI super-resolution method, called Dual-ArbNet. First, we decouple the resolution of the target and reference images by a feature encoder, enabling the network to input target and reference images at arbitrary scales. Then, an implicit fusion decoder fuses the multi-contrast features and uses an Implicit Decoding Function~(IDF) to obtain the final MRI SR results. Furthermore, we introduce a curriculum learning strategy to train our network, which improves the generalization and performance of our Dual-ArbNet. Extensive experiments in two public MRI datasets demonstrate that our method outperforms state-of-the-art approaches under different scale factors and has great potential in clinical practice.
Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at //github.com/ttengwang/Caption-Anything.
Existing datasets for manually labelled query-based video summarization are costly and thus small, limiting the performance of supervised deep video summarization models. Self-supervision can address the data sparsity challenge by using a pretext task and defining a method to acquire extra data with pseudo labels to pre-train a supervised deep model. In this work, we introduce segment-level pseudo labels from input videos to properly model both the relationship between a pretext task and a target task, and the implicit relationship between the pseudo label and the human-defined label. The pseudo labels are generated based on existing human-defined frame-level labels. To create more accurate query-dependent video summaries, a semantics booster is proposed to generate context-aware query representations. Furthermore, we propose mutual attention to help capture the interactive information between visual and textual modalities. Three commonly-used video summarization benchmarks are used to thoroughly validate the proposed approach. Experimental results show that the proposed video summarization algorithm achieves state-of-the-art performance.
Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are jointly processed for visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design three pre-training tasks: Masked Language Modeling (MLM), Image-Text Matching (ITM), and Masked Region Modeling (MRM, with three variants). Different from concurrent work on multimodal pre-training that apply joint random masking to both modalities, we use conditioned masking on pre-training tasks (i.e., masked language/region modeling is conditioned on full observation of image/text). Comprehensive analysis shows that conditioned masking yields better performance than unconditioned masking. We also conduct a thorough ablation study to find an optimal setting for the combination of pre-training tasks. Extensive experiments show that UNITER achieves new state of the art across six V+L tasks (over nine datasets), including Visual Question Answering, Image-Text Retrieval, Referring Expression Comprehension, Visual Commonsense Reasoning, Visual Entailment, and NLVR2.
Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction. This emerging technique has reshaped the research landscape of face recognition since 2014, launched by the breakthroughs of Deepface and DeepID methods. Since then, deep face recognition (FR) technique, which leverages the hierarchical architecture to learn discriminative face representation, has dramatically improved the state-of-the-art performance and fostered numerous successful real-world applications. In this paper, we provide a comprehensive survey of the recent developments on deep FR, covering the broad topics on algorithms, data, and scenes. First, we summarize different network architectures and loss functions proposed in the rapid evolution of the deep FR methods. Second, the related face processing methods are categorized into two classes: `one-to-many augmentation' and `many-to-one normalization'. Then, we summarize and compare the commonly used databases for both model training and evaluation. Third, we review miscellaneous scenes in deep FR, such as cross-factor, heterogenous, multiple-media and industry scenes. Finally, potential deficiencies of the current methods and several future directions are highlighted.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191