Discriminative Fine-tuning of LVLMs

• URL: http://arxiv.org/abs/2412.04378v2
• Date: Sun, 08 Dec 2024 20:58:42 GMT
• Title: Discriminative Fine-tuning of LVLMs
• Authors: Yassine Ouali, Adrian Bulat, Alexandros Xenos, Anestis Zaganidis, Ioannis Maniadis Metaxas, Brais Martinez, Georgios Tzimiropoulos,
• Abstract summary: 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.
• Score: 67.14293827774827
• License:
• Abstract: Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks. In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding. Our contributions include: (1) A carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework's components. (2) A parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters. (3) Significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.

Related papers

• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model [27.56988000960972]
  We introduce a new framework based on a dual context of both domain-shared and class-specific contexts. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in Large Language Models. We also formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens.
  arXiv  Detail & Related papers  (2024-07-05T13:15:29Z)
• APoLLo: Unified Adapter and Prompt Learning for Vision Language Models [58.9772868980283]
  We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for Vision-Language models. APoLLo achieves a relative gain up to 6.03% over MaPLe (SOTA) on novel classes for 10 diverse image recognition datasets.
  arXiv  Detail & Related papers  (2023-12-04T01:42:09Z)
• LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions [13.546494268784757]
  We propose a framework that integrates large language models (LLMs) and vision-language models (VLMs) to find the optimal class descriptors. Our training-free approach develops an LLM-based agent with an evolutionary optimization strategy to iteratively refine class descriptors.
  arXiv  Detail & Related papers  (2023-11-20T16:37:45Z)
• Planting a SEED of Vision in Large Language Model [73.17530130368053]
  We present SEED, an elaborate image tokenizer that empowers Large Language Models (LLMs) with the ability to SEE and Draw at the same time. This version of SEED was trained in 5.7 days using only 64 V100 GPUs and 5M publicly available image-text pairs.
  arXiv  Detail & Related papers  (2023-07-16T13:41:39Z)
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification [84.05253637260743]
  We propose a new framework, named Semantic-guided Visual Adapting (SgVA), to extend vision-language pre-trained models. SgVA produces discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
  arXiv  Detail & Related papers  (2022-11-28T14:58:15Z)
• MaPLe: Multi-modal Prompt Learning [54.96069171726668]
  We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
  arXiv  Detail & Related papers  (2022-10-06T17:59:56Z)
• DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning [37.48292304239107]
  We present a transformer-based end-to-end ZSL method named DUET. We develop a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images. We find that DUET can often achieve state-of-the-art performance, its components are effective and its predictions are interpretable.
  arXiv  Detail & Related papers  (2022-07-04T11:12:12Z)

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.