I0T: Embedding Standardization Method Towards Zero Modality Gap

• URL: http://arxiv.org/abs/2412.14384v1
• Date: Wed, 18 Dec 2024 22:35:01 GMT
• Title: I0T: Embedding Standardization Method Towards Zero Modality Gap
• Abstract summary: Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification.<n>Recent works extending CLIP suffer from the issue of modality gap.<n>We propose two methods to address the modality gap.
• Score: 18.032635790176464
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP suffer from the issue of modality gap, which arises when the image and text embeddings are projected to disparate manifolds, deviating from the intended objective of image-text contrastive learning. We discover that this phenomenon is linked to the modality-specific characteristic that each image/text encoder independently possesses and propose two methods to address the modality gap: (1) a post-hoc embedding standardization method, $\text{I0T}_{\text{post}}$ that reduces the modality gap approximately to zero and (2) a trainable method, $\text{I0T}_{\text{async}}$, to alleviate the modality gap problem by adding two normalization layers for each encoder. Our I0T framework can significantly reduce the modality gap while preserving the original embedding representations of trained models with their locked parameters. In practice, $\text{I0T}_{\text{post}}$ can serve as an alternative explainable automatic evaluation metric of widely used CLIPScore (CLIP-S).

Related papers

• STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation [60.597357847359255]
  Video segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries.<n>Existing methods address this through token compression, yet typically operate on features lacking temporal context.<n>State-space models resolve this constraint, as their linear recurrence selectively conditions each token on temporal context at $mathcalO(T)$ cost compression to reduce.
  arXiv  Detail & Related papers  (2026-07-03T03:28:25Z)
• CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization [122.88484422855934]
  We present CaTok, a 1D causal image tokenizer with a MeanFlow decoder.<n>By selecting tokens over time intervals, CaTok learns causal 1D representations that support both fast one-step generation and high-fidelity multi-step sampling.<n> Experiments demonstrate that CaTok achieves state-of-the-art results on ImageNet reconstruction, reaching 0.75 FID, 22.53 PSNR and 0.674 SSIM.
  arXiv  Detail & Related papers  (2026-03-06T16:39:17Z)
• $β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment [53.42377319350806]
  $$-CLIP is a multi-granular text-conditioned contrastive learning framework.<n>$$-CAL addresses the semantic overlap inherent in this hierarchy.<n>$$-CLIP establishes a robust, adaptive baseline for dense vision-language correspondence.
  arXiv  Detail & Related papers  (2025-12-14T13:03:20Z)
• Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection [58.927873049646024]
  We show that fake images cannot be properly aligned with corresponding captions compared to real images.<n>We propose a simple yet effective ITEM by leveraging the image-text misalignment in a joint visual-language space as discriminative clues.
  arXiv  Detail & Related papers  (2025-11-01T06:51:14Z)
• Enhancing CLIP Robustness via Cross-Modality Alignment [54.01929554563447]
  We propose Cross-modality Alignment, an optimal transport-based framework for vision-language models.<n> COLA restores global image-text alignment and local structural consistency in the feature space.<n> COLA is training-free and compatible with existing fine-tuned models.
  arXiv  Detail & Related papers  (2025-10-28T03:47:44Z)
• SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP [6.427791334895624]
  We introduce SeMoBridge, a lightweight yet powerful approach that directly addresses the misalignment.<n>Our method maps images into the text modality, while keeping their semantic content intact through what we call a Semantic Modality Bridge.<n> Experiments show that the trained version, SeMoBridge-T, requires only a fraction of the training time while overall outperforming other methods.
  arXiv  Detail & Related papers  (2025-09-30T10:12:15Z)
• MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval [32.33545237942899]
  Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a reference image and a modification text.<n>We propose Chain-of-Thought with re-ranking (MCoT-RE) as a training-free zero-shot CIR framework.
  arXiv  Detail & Related papers  (2025-07-17T06:22:49Z)
• Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning [69.33115351856785]
  We present a novel method, called T2I-PAL, to tackle the modality gap issue when using only text captions for PEFT.<n>The core design of T2I-PAL is to leverage pre-trained text-to-image generation models to generate photo-realistic and diverse images from text captions.<n>Extensive experiments on multiple benchmarks, including MS-COCO, VOC2007, and NUS-WIDE, show that our T2I-PAL can boost recognition performance by 3.47% in average.
  arXiv  Detail & Related papers  (2025-06-12T11:09:49Z)
• Post-pre-training for Modality Alignment in Vision-Language Foundation Models [12.110530026601968]
  This paper presents CLIP-Refine, a post-pre-training method for CLIP models at a phase between pre-training and fine-tuning. It aims to align the feature space with 1 epoch training on small image-text datasets without zero-shot performance degradations.
  arXiv  Detail & Related papers  (2025-04-17T07:46:19Z)
• Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning [70.98890307376548]
  We propose a novel Patch-wise Cross-modal feature Mix-up (PCM) mechanism to adaptively mitigate the unfaithful contents during training. Our PCM-Net ranks first in both in-domain and cross-domain zero-shot image captioning.
  arXiv  Detail & Related papers  (2024-12-31T13:39:08Z)
• $\texttt{BATCLIP}$: Bimodal Online Test-Time Adaptation for CLIP [18.278043899825267]
  We show that zero-shot CLIP lacks robustness to common image corruptions during test-time. We propose $textttBATCLIP$, a bimodal $textbfonline$ TTA method designed to improve CLIP's robustness to common image corruptions.
  arXiv  Detail & Related papers  (2024-12-03T21:02:14Z)
• Adapt CLIP as Aggregation Instructor for Image Dehazing [17.29370328189668]
  Most dehazing methods suffer from limited receptive field and do not explore the rich semantic prior encapsulated in vision-language models. We introduce CLIPHaze, a pioneering hybrid framework that synergizes the efficient global modeling of Mamba with the prior knowledge and zero-shot capabilities of CLIP. Our method employs parallel state space model and window-based self-attention to obtain global contextual dependency and local fine-grained perception.
  arXiv  Detail & Related papers  (2024-08-22T11:51:50Z)
• Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning [53.766434746801366]
  Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. Hackers may unauthorizedly exploit image-text data for model training, potentially including personal and privacy-sensitive information. Recent works propose generating unlearnable examples by adding imperceptible perturbations to training images to build shortcuts for protection. We propose Multi-step Error Minimization (MEM), a novel optimization process for generating multimodal unlearnable examples.
  arXiv  Detail & Related papers  (2024-07-23T09:00:52Z)
• A Simple Framework for Open-Vocabulary Zero-Shot Segmentation [50.58626342189163]
  SimZSS is a framework for open-vocabulary Zero-Shot segmentation.<n>It exploits the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions.<n>SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.
  arXiv  Detail & Related papers  (2024-06-23T11:57:08Z)
• Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification [54.96876797812238]
  We present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. Experiment results across various datasets and models confirm CODER's effectiveness.
  arXiv  Detail & Related papers  (2024-04-27T02:04:36Z)
• Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training [14.340740609933437]
  We propose a novel zero-shot image captioning framework with text-only training to reduce the modality gap. In particular, we introduce a subregion feature aggregation to leverage local region information. We extend our framework to build a zero-shot VQA pipeline, demonstrating its generality.
  arXiv  Detail & Related papers  (2024-01-04T16:43:46Z)
• Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization [63.61093388441298]
  Contrastive Language-Image Pre-training models have shown promising performance on zero-shot visual recognition tasks. In this work, we propose AnoCLIP for zero-shot anomaly localization.
  arXiv  Detail & Related papers  (2023-08-30T10:35:36Z)
• Zero-Shot Video Captioning with Evolving Pseudo-Tokens [79.16706829968673]
  We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge.
  arXiv  Detail & Related papers  (2022-07-22T14:19:31Z)
• CyCLIP: Cyclic Contrastive Language-Image Pretraining [34.588147979731374]
  Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. We demonstrate that the image and text representations learned via a standard contrastive objective are not interchangeable and can lead to inconsistent downstream predictions. We propose CyCLIP, a framework for contrastive representation learning that explicitly optimize for the learned representations to be geometrically consistent in the image and text space.
  arXiv  Detail & Related papers  (2022-05-28T15:31:17Z)
• No Token Left Behind: Explainability-Aided Image Classification and Generation [79.4957965474334]
  We present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input. Our method yields an improvement in the recognition rate, without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2022-04-11T07:16:39Z)
• Semantically Grounded Visual Embeddings for Zero-Shot Learning [17.86691047421871]
  We propose to learn semantically grounded and enriched visual information by computing a joint image and text model with a two-stream network on a proxy task. Our method, dubbed joint embeddings for zero-shot learning is evaluated on several benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-03T10:43:15Z)
• Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning [116.91819311885166]
  We propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to textbfCross-samples and Multi-level representation. Our method, termed as CsMl, has the ability to integrate multi-level visual representations across samples in a robust way.
  arXiv  Detail & Related papers  (2020-12-04T17:26:24Z)
• Boosting Continuous Sign Language Recognition via Cross Modality Augmentation [135.30357113518127]
  Continuous sign language recognition deals with unaligned video-text pair. We propose a novel architecture with cross modality augmentation. The proposed framework can be easily extended to other existing CTC based continuous SLR architectures.
  arXiv  Detail & Related papers  (2020-10-11T15:07:50Z)

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.