Barking Up The Syntactic Tree: Enhancing VLM Training with Syntactic Losses

• URL: http://arxiv.org/abs/2412.08110v2
• Date: Sat, 29 Mar 2025 19:13:09 GMT
• Title: Barking Up The Syntactic Tree: Enhancing VLM Training with Syntactic Losses
• Authors: Jiayun Luo, Mir Rayat Imtiaz Hossain, Boyang Li, Leonid Sigal,
• Abstract summary: Vision-Language Models implicitly learn to associate image regions with words from large-scale training data.<n>Rich semantic and syntactic structures within the text modality have been overlooked as sources of supervision.<n>Hierarchically STructured Learning (HIST) enhances spatial vision-language alignment without using additional human annotations.
• Score: 31.85977999591524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) implicitly learn to associate image regions with words from large-scale training data, demonstrating an emergent capability for grounding concepts without dense annotations[14,18,51]. However, the coarse-grained supervision from image-caption pairs is often insufficient to resolve ambiguities in object-concept correspondence, even with enormous data volume. Rich semantic and syntactic structures within the text modality have been overlooked as sources of supervision. Starting from contrastive architectures (BLIP and ALBEF) that show strong intrinsic grounding abilities, we propose HIerarchically STructured Learning (HIST). HIST enhances spatial vision-language alignment without using additional human annotations, by hierarchically decomposing captions into the constituent Subjects, Phrases, and Composite Phrases, and enforcing entailment relation between a parent and its children in the hierarchy. Specifically, we introduce two novel loss functions: (1) Subject Loss, which aligns image content with the subject of the corresponding phrase, acting as an entailment of standard contrastive/matching losses at the Phrase level; (2) Composition Loss, to balance attention across multiple objects. HIST is general, and can be applied to any VLM for which attention between vision and language can be computed. Compared to baseline VLMs, HIST achieves up to +9.8% improvement in visual grounding and +6.3% in multi-object referring segmentation. Surprisingly, the improved spatial grounding leads to improvements in other downstream VLM tasks: +1.1% in image-text retrieval, and +0.2% in visual question answering.

Related papers

• COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training [49.2684130383925]
  We propose COSMOS: CrOSs-MOdality Self-distillation for vision-language pre-training.<n>It integrates a novel text-cropping strategy and cross-attention module into a self-supervised learning framework.<n>It consistently outperforms previous strong baselines on various zero-shot downstream tasks.
  arXiv  Detail & Related papers  (2024-12-02T18:56:06Z)
• Instruction Tuning-free Visual Token Complement for Multimodal LLMs [51.138806401996696]
  multimodal large language models (MLLMs) have promised an elegant bridge between vision and language. We propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features. Our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens.
  arXiv  Detail & Related papers  (2024-08-09T12:13:01Z)
• Wings: Learning Multimodal LLMs without Text-only Forgetting [63.56085426442873]
  Wings is a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks.
  arXiv  Detail & Related papers  (2024-06-05T17:59:40Z)
• CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor [18.288738950822342]
  Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. We introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts. Experiments show that our method outperforms not only the training-free counterparts, but also those fine-tuned with millions of data samples.
  arXiv  Detail & Related papers  (2023-12-12T19:00:04Z)
• 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)
• Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models [3.86170450233149]
  We show that large vision-and-language models (VLMs) trained to match images with text lack fine-grained understanding of spatial relations. We propose an alternative fine-grained, compositional approach for recognizing and ranking spatial clauses.
  arXiv  Detail & Related papers  (2023-08-18T18:58:54Z)
• 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)
• Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding [6.798129852396113]
  We introduce a simple and effective method to improve compositional reasoning in Vision-Language Models (VLMs) Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-06-15T03:26:28Z)
• Visually-augmented pretrained language models for NLP tasks without images [77.74849855049523]
  Existing solutions often rely on explicit images for visual knowledge augmentation. We propose a novel textbfVisually-textbfAugmented fine-tuning approach. Our approach can consistently improve the performance of BERT, RoBERTa, BART, and T5 at different scales.
  arXiv  Detail & Related papers  (2022-12-15T16:13:25Z)
• Fine-Grained Semantically Aligned Vision-Language Pre-Training [151.7372197904064]
  Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts. We introduce LO, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions.
  arXiv  Detail & Related papers  (2022-08-04T07:51:48Z)
• BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation [86.4572981982407]
  We propose BLIP, a new vision-language framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. BLIP also demonstrates strong generalization ability when directly transferred to video-language tasks in a zero-shot manner.
  arXiv  Detail & Related papers  (2022-01-28T12:49:48Z)
• Consensus Graph Representation Learning for Better Grounded Image Captioning [48.208119537050166]
  We propose the Consensus Rraph Representation Learning framework (CGRL) for grounded image captioning. We validate the effectiveness of our model, with a significant decline in object hallucination (-9% CHAIRi) on the Flickr30k Entities dataset.
  arXiv  Detail & Related papers  (2021-12-02T04:17:01Z)
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization [81.26077816854449]
  We first explore the use of constituency parse trees for encoding structured input. Second, we augment the structured input with commonsense information and study the impact of this external knowledge on the generation of visual story. Third, we incorporate visual structure via bounding boxes and dense captioning to provide feedback about the characters/objects in generated images.
  arXiv  Detail & Related papers  (2021-10-21T00:16:02Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos [96.85840365678649]
  We tackle the problem of referring expression comprehension in videos with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency. Our model is also applicable to referring expression comprehension in images, illustrated by the improved performance on the RefCOCO dataset.
  arXiv  Detail & Related papers  (2021-03-23T06:42:49Z)
• Image Captioning with Visual Object Representations Grounded in the Textual Modality [14.797241131469486]
  We explore the possibilities of a shared embedding space between textual and visual modality. We propose an approach opposite to the current trend, grounding of the representations in the word embedding space of the captioning system.
  arXiv  Detail & Related papers  (2020-10-19T12:21:38Z)
• Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
  Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference. Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
  arXiv  Detail & Related papers  (2020-07-03T21:53:46Z)

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.