Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
- URL: http://arxiv.org/abs/2410.05210v1
- Date: Mon, 7 Oct 2024 17:16:20 GMT
- Title: Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
- Authors: Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Junmo Kim,
- Abstract summary: Fine-grained Selective Calibrated CLIP integrates local hard negative loss and selective calibrated regularization.
Our evaluations show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities.
- Score: 69.76121008898677
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve compositional reasoning at the cost of degrading multi-modal capabilities, primarily due to the use of global hard negative (HN) loss, which contrasts global representations of images and texts. This global HN loss pushes HN texts that are highly similar to the original ones, damaging the model's multi-modal representations. To overcome this limitation, we propose Fine-grained Selective Calibrated CLIP (FSC-CLIP), which integrates local hard negative loss and selective calibrated regularization. These innovations provide fine-grained negative supervision while preserving the model's representational integrity. Our extensive evaluations across diverse benchmarks for both compositionality and multi-modal tasks show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities. Code is available at: https://github.com/ytaek-oh/fsc-clip.
Related papers
- Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models [58.936893810674896]
Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems.
We introduce a multimodal large language model framework for FAS, termed Interpretable Face Anti-Spoofing (I-FAS)
We propose a Spoof-aware Captioning and Filtering (SCF) strategy to generate high-quality captions for FAS images.
arXiv Detail & Related papers (2025-01-03T09:25:04Z) - Discriminative Fine-tuning of LVLMs [67.14293827774827]
Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.
We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
arXiv Detail & Related papers (2024-12-05T17:54:27Z) - MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection [64.29452783056253]
The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia.
Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored.
We propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities.
arXiv Detail & Related papers (2024-09-15T13:08:59Z) - LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification [5.8754760054410955]
We introduce textttHi-CoDecomposition, a novel framework designed to enhance model interpretability through structured concept analysis.
Our approach not only aligns with the performance of state-of-the-art models but also advances transparency by providing clear insights into the decision-making process.
arXiv Detail & Related papers (2024-05-29T00:36:56Z) - Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models [0.0]
This paper introduces CascadeVLM, an innovative framework that overcomes the constraints of previous CLIP-based methods.
Experiments across various fine-grained image datasets demonstrate that CascadeVLM significantly outperforms existing models.
arXiv Detail & Related papers (2024-05-18T14:12:04Z) - Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning [45.25602203155762]
Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data.
A major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression.
We propose a novel model-agnostic Multistage Contrastive Learning framework.
arXiv Detail & Related papers (2024-02-19T04:13:33Z) - Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion
Models [58.46926334842161]
This work illuminates the fundamental reasons for such misalignment, pinpointing issues related to low attention activation scores and mask overlaps.
We propose two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores.
Our method diverges from conventional test-time-adaptation techniques, focusing on finetuning critical parameters, which enhances scalability and generalizability.
arXiv Detail & Related papers (2023-12-10T22:07:42Z) - Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models [55.5610165938949]
Fine-tuning vision-language models (VLMs) has gained increasing popularity due to its practical value.
This paper explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model.
We introduce three customized ensemble strategies, each tailored to one specific scenario.
The proposed ensemble strategies are evaluated on zero-shot, base-to-new, and cross-dataset generalization, achieving new state-of-the-art performance.
arXiv Detail & Related papers (2023-11-28T05:17:25Z)
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.