ABC: Achieving Better Control of Multimodal Embeddings using VLMs

• URL: http://arxiv.org/abs/2503.00329v1
• Date: Sat, 01 Mar 2025 03:29:02 GMT
• Title: ABC: Achieving Better Control of Multimodal Embeddings using VLMs
• Authors: Benjamin Schneider, Florian Kerschbaum, Wenhu Chen,
• Abstract summary: Visual embedding models excel at zero-shot tasks like visual retrieval and classification.<n>Existing CLIP-based approaches embed images and text independently, and fuse the result.<n>We introduce ABC, an open-source multimodal embedding model that uses a vision-language model backbone.
• Score: 61.396457715710774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate a multimodal embedding model, which outputs embeddings that combine visual and natural language input. Existing CLIP-based approaches embed images and text independently, and fuse the result. We find that this results in weak interactions between modalities, and poor user control over the representation. We introduce ABC, an open-source multimodal embedding model that uses a vision-language model backbone to deeply integrate image features with natural language instructions. ABC achieves bestfor-size performance on MSCOCO image-to-text retrieval and is the top performing model on classification and VQA tasks in the Massive Multimodal Embedding Benchmark. With a strongly unified vision-language representation, ABC can use natural language to solve subtle and potentially ambiguous visual retrieval problems. To evaluate this capability, we design CtrlBench, a benchmark that requires interleaving textual instructions with image content for correct retrieval. ABC advances the state of multimodal embeddings by offering high-quality representations and flexible natural language control. Our model and datasets are available at our project page.

Related papers

• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images [5.587329786636647]
  Contrastive Language-Image Pretraining (CLIP) is a highly effective method for aligning images and texts in a shared embedding space.<n>CLIP models often struggle with text-only tasks, underperforming compared to specialized text models.<n>In this work, we build upon our previous model, jina-clip-v1, by introducing a refined framework that utilizes multi-task, multi-stage contrastive learning across multiple languages.<n>The resulting model, jina-clip-v2, outperforms its predecessor on text-only and multimodal tasks, while adding multilingual support, better understanding of complex visual documents and efficiency gains.
  arXiv  Detail & Related papers  (2024-12-11T22:28:12Z)
• CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models [58.95889895912716]
  We introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner.
  arXiv  Detail & Related papers  (2024-02-21T08:21:12Z)
• Bootstrapping Vision-Language Learning with Decoupled Language Pre-training [46.570154746311935]
  We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language pre-training. Our approach diverges by concentrating on the language component, specifically identifying the optimal prompts to align with visual features. Our framework is modality-agnostic and flexible in terms of architectural design, as validated by its successful application in a video learning task.
  arXiv  Detail & Related papers  (2023-07-13T21:08:15Z)
• Generating Images with Multimodal Language Models [78.6660334861137]
  We propose a method to fuse frozen text-only large language models with pre-trained image encoder and decoder models. Our model demonstrates a wide suite of multimodal capabilities: image retrieval, novel image generation, and multimodal dialogue.
  arXiv  Detail & Related papers  (2023-05-26T19:22:03Z)
• Multimodal Knowledge Alignment with Reinforcement Learning [103.68816413817372]
  ESPER extends language-only zero-shot models to unseen multimodal tasks, like image and audio captioning. Our key novelty is to use reinforcement learning to align multimodal inputs to language model generations without direct supervision. Experiments demonstrate that ESPER outperforms baselines and prior work on a variety of zero-shot tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:12:17Z)
• On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization [89.94078728495423]
  We show that recent advances in each modality, CLIP image representations and scaling of language models, do not consistently improve multimodal self-rationalization of tasks with multimodal inputs. Our findings call for a backbone modelling approach that can be built on to advance text generation from images and text beyond image captioning.
  arXiv  Detail & Related papers  (2022-05-24T00:52:40Z)

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.