LARE: Latent Augmentation using Regional Embedding with Vision-Language Model

• URL: http://arxiv.org/abs/2409.12597v1
• Date: Thu, 19 Sep 2024 09:21:42 GMT
• Title: LARE: Latent Augmentation using Regional Embedding with Vision-Language Model
• Authors: Kosuke Sakurai, Tatsuya Ishii, Ryotaro Shimizu, Linxin Song, Masayuki Goto,
• Abstract summary: Vision-language models embed images as a single point in a unified embedding space. Regional Embedding (LARE) embeds the image as a region in the unified embedding space learned by the VLM. LARE achieves robust image classification for domains in and out using augmented image embeddings to fine-tuneVLMs.
• Score: 2.0971479389679337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, considerable research has been conducted on vision-language models that handle both image and text data; these models are being applied to diverse downstream tasks, such as "image-related chat," "image recognition by instruction," and "answering visual questions." Vision-language models (VLMs), such as Contrastive Language-Image Pre-training (CLIP), are also high-performance image classifiers that are being developed into domain adaptation methods that can utilize language information to extend into unseen domains. However, because these VLMs embed images as a single point in a unified embedding space, there is room for improvement in the classification accuracy. Therefore, in this study, we proposed the Latent Augmentation using Regional Embedding (LARE), which embeds the image as a region in the unified embedding space learned by the VLM. By sampling the augmented image embeddings from within this latent region, LARE enables data augmentation to various unseen domains, not just to specific unseen domains. LARE achieves robust image classification for domains in and out using augmented image embeddings to fine-tune VLMs. We demonstrate that LARE outperforms previous fine-tuning models in terms of image classification accuracy on three benchmarks. We also demonstrate that LARE is a more robust and general model that is valid under multiple conditions, such as unseen domains, small amounts of data, and imbalanced data.

Related papers

• Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models [0.6715525121432597]
  This research presents a novel vision language model (VLM) framework to enhance feature extraction, scalability, and efficiency. We evaluate the proposed model on caption generation and Visual Question Answering (VQA) tasks using benchmark datasets with varying levels of Gaussian noise. Our model provides more detailed and contextually relevant responses, particularly for real-world images captured by a RealSense camera mounted on an Unmanned Ground Vehicle (UGV)
  arXiv  Detail & Related papers  (2025-03-08T01:22:10Z)
• SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing [14.007392647145448]
  UDA enables models to learn from unlabeled target domain data while training on labeled source domain data. We propose integrating contrastive learning into UDA, enhancing the model's capacity to capture semantic information. Our SimSeg method outperforms existing approaches, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-17T11:59:39Z)
• Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models [36.59260354292177]
  Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models. We aim to fine-tune vision-language models to a specific classification model without access to any real images. Despite the high fidelity of generated images, we observed a significant performance degradation when fine-tuning the model using the generated datasets.
  arXiv  Detail & Related papers  (2024-06-08T10:43:49Z)
• WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization [63.98650220772378]
  We present WIDIn, Wording Images for Domain-Invariant representation, to disentangle discriminative visual representation. We first estimate the language embedding with fine-grained alignment, which can be used to adaptively identify and then remove domain-specific counterpart. We show that WIDIn can be applied to both pretrained vision-language models like CLIP, and separately trained uni-modal models like MoCo and BERT.
  arXiv  Detail & Related papers  (2024-05-28T17:46:27Z)
• Language Guided Domain Generalized Medical Image Segmentation [68.93124785575739]
  Single source domain generalization holds promise for more reliable and consistent image segmentation across real-world clinical settings. We propose an approach that explicitly leverages textual information by incorporating a contrastive learning mechanism guided by the text encoder features. Our approach achieves favorable performance against existing methods in literature.
  arXiv  Detail & Related papers  (2024-04-01T17:48:15Z)
• VLLaVO: Mitigating Visual Gap through LLMs [7.352822795984628]
  Cross-domain learning aims at extracting domain-invariant knowledge to reduce the domain shift between training and testing data. We propose VLLaVO, combining Vision language models and Large Language models as Visual cross-dOmain learners.
  arXiv  Detail & Related papers  (2024-01-06T16:33:39Z)
• Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models [16.4010094165575]
  We propose a robust phrase grounding model trained with text-conditioned and text-unconditioned data augmentations. Inspired by recent masked signal reconstruction, we propose to use pixel-level masking as a novel form of data augmentation. Our method demonstrates advanced performance over the state-of-the-arts with various metrics.
  arXiv  Detail & Related papers  (2023-11-05T01:14:02Z)
• IFSeg: Image-free Semantic Segmentation via Vision-Language Model [67.62922228676273]
  We introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories. We construct this artificial training data by creating a 2D map of random semantic categories and another map of their corresponding word tokens. Our model not only establishes an effective baseline for this novel task but also demonstrates strong performances compared to existing methods.
  arXiv  Detail & Related papers  (2023-03-25T08:19:31Z)
• Using Language to Extend to Unseen Domains [81.37175826824625]
  It is expensive to collect training data for every possible domain that a vision model may encounter when deployed. We consider how simply verbalizing the training domain as well as domains we want to extend to but do not have data for can improve robustness. Using a multimodal model with a joint image and language embedding space, our method LADS learns a transformation of the image embeddings from the training domain to each unseen test domain.
  arXiv  Detail & Related papers  (2022-10-18T01:14:02Z)
• Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification [50.658613573816254]
  We propose a novel Multi-scale Multi-target Domain Adversarial Network (M2DAN) for angle closure classification. Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains.
  arXiv  Detail & Related papers  (2022-08-25T15:27:55Z)
• Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding [24.64900089320843]
  This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA) In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. We develop a general UDA model to solve the few-shot labeled data per category and the domain adaptation between support and query sets.
  arXiv  Detail & Related papers  (2021-08-06T06:15:02Z)
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets [96.92018649136217]
  We present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains. Our framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.
  arXiv  Detail & Related papers  (2020-10-13T07:28:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.