LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
- URL: http://arxiv.org/abs/2503.13794v1
- Date: Tue, 18 Mar 2025 00:50:40 GMT
- Title: LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
- Authors: Yang Zhou, Shiyu Zhao, Yuxiao Chen, Zhenting Wang, Dimitris N. Metaxas,
- Abstract summary: This paper presents a systematic method to enhance visual grounding by utilizing decoder layers of the Large Language Models (LLMs)<n>We demonstrate that intermediate hidden states from early LLM layers retain strong spatial-semantic correlations that are beneficial to grounding tasks.<n> Experiments show that our adaptation strategy significantly enhances the performance on complex free-form text queries.
- Score: 41.97593224447291
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large foundation models trained on large-scale visual-text data can significantly enhance Open Vocabulary Object Detection (OVD) through data generation. However, this may lead to biased synthetic data and overfitting to specific configurations. It can sidestep biases of manually curated data generation by directly leveraging hidden states of Large Language Models (LLMs), which is surprisingly rarely explored. This paper presents a systematic method to enhance visual grounding by utilizing decoder layers of the LLM of a MLLM. We introduce a zero-initialized cross-attention adapter to enable efficient knowledge transfer from LLMs to object detectors, an new approach called LED (LLM Enhanced Open-Vocabulary Object Detection). We demonstrate that intermediate hidden states from early LLM layers retain strong spatial-semantic correlations that are beneficial to grounding tasks. Experiments show that our adaptation strategy significantly enhances the performance on complex free-form text queries while remaining the same on plain categories. With our adaptation, Qwen2-0.5B with Swin-T as the vision encoder improves GroundingDINO by 2.33% on Omnilabel, at the overhead of 8.7% more GFLOPs. Qwen2-0.5B with a larger vision encoder can further boost the performance by 6.22%. We further validate our design by ablating on varied adapter architectures, sizes of LLMs, and which layers to add adaptation.
Related papers
- AU-LLM: Micro-Expression Action Unit Detection via Enhanced LLM-Based Feature Fusion [26.058143518505805]
This paper introduces textbfAU-LLM, a novel framework that uses Large Language Models to detect micro-expression Action Units (AUs) in micro-expression datasets with subtle intensities and the scarcity of data.<n>We specifically address the critical vision-language semantic gap, the textbfEnhanced Fusion Projector (EFP). The EFP employs a Multi-Layer Perceptron (MLP) to intelligently fuse mid-level (local texture) and high-level (global semantics) visual features from a specialized 3D-CNN backbone into a single, information-dense token.
arXiv Detail & Related papers (2025-07-29T13:01:59Z) - Training-Free Reasoning and Reflection in MLLMs [45.134271969594614]
This paper introduces FRANK Model, a training-FRee ANd r1-liKe MLLM that imbues off-the-shelf MLLMs with reasoning and reflection abilities.<n>Our key insight is to decouple perception and reasoning across MLLM decoder layers.<n>To this end, we propose a layer-wise, Taylor-derived closed-form fusion mechanism that integrates reasoning capacity into deep decoder layers.
arXiv Detail & Related papers (2025-05-22T02:51:12Z) - Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction [52.09472099976885]
IAR is an Improved AutoRegressive Visual Generation Method that enhances the training efficiency and generation quality of LLM-based visual generation models.<n>Our method consistently enhances the model training efficiency and performance from 100M to 1.4B, reducing the training time by half while achieving the same FID.
arXiv Detail & Related papers (2025-01-01T15:58:51Z) - Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation [43.630437906898635]
We propose a novel two-stage fine-tuning architecture called Invar-RAG.
In the retrieval stage, an LLM-based retriever is constructed by integrating LoRA-based representation learning.
In the generation stage, a refined fine-tuning method is employed to improve LLM accuracy in generating answers based on retrieved information.
arXiv Detail & Related papers (2024-11-11T14:25:37Z) - SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models [34.3296459569307]
Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect.<n>We introduce Self Logits Evolution Decoding (SLED), a novel decoding framework that enhances the truthfulness of LLMs.<n>We show that SLED consistently improves factual accuracy by up to 20% compared to existing decoding methods.
arXiv Detail & Related papers (2024-11-01T17:33:34Z) - SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration [10.970637831760136]
Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality.<n>We introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference.<n>Our experiments demonstrate that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text.
arXiv Detail & Related papers (2024-10-09T14:15:30Z) - Intent Detection in the Age of LLMs [3.755082744150185]
Intent detection is a critical component of task-oriented dialogue systems (TODS)
Traditional approaches relied on computationally efficient supervised sentence transformer encoder models.
The emergence of generative large language models (LLMs) with intrinsic world knowledge presents new opportunities to address these challenges.
arXiv Detail & Related papers (2024-10-02T15:01:55Z) - All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks [51.19110891434727]
Large Language Models (LLMs) with pretrained knowledge and powerful semantic comprehension abilities have recently shown a remarkable ability to benefit applications using vision and text data.
E-LLaGNN is a framework with an on-demand LLM service that enriches message passing procedure of graph learning by enhancing a limited fraction of nodes from the graph.
arXiv Detail & Related papers (2024-07-20T22:09:42Z) - GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval [80.96706764868898]
We present a new Low-light Image Enhancement (LLIE) network via Generative LAtent feature based codebook REtrieval (GLARE)
We develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook.
Experiments confirm the superior performance of GLARE on various benchmark datasets and real-world data.
arXiv Detail & Related papers (2024-07-17T09:40:15Z) - Large Language Models Understand Layout [6.732578061359833]
Large language models (LLMs) demonstrate extraordinary abilities in a wide range of natural language processing (NLP) tasks.
We show that, beyond text understanding capability, LLMs are capable of processing text layouts denoted by spatial markers.
We show that layout understanding ability is beneficial for building efficient visual question-answering (VQA) systems.
arXiv Detail & Related papers (2024-07-08T09:03:12Z) - Dense Connector for MLLMs [89.50595155217108]
We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs.
Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens.
Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
arXiv Detail & Related papers (2024-05-22T16:25:03Z) - Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance [51.30560006045442]
Image-gRounded guIdaNcE (MARINE) is a framework that is both training-free and API-free.<n>MARINE effectively and efficiently reduces object hallucinations during inference by introducing image-grounded guidance to LVLMs.<n>Our framework's flexibility further allows for the integration of multiple vision models, enabling more reliable and robust object-level guidance.
arXiv Detail & Related papers (2024-02-13T18:59:05Z) - DeepSeek LLM: Scaling Open-Source Language Models with Longtermism [76.90033862238728]
We present our findings that facilitate scaling of large scale models in two commonly used open-source configurations, 7B and 67B.
Guided by the scaling laws, we introduce DeepSeek LLM, a project dedicated to advancing open-source language models with a long-term perspective.
arXiv Detail & Related papers (2024-01-05T18:59:13Z) - Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN)
At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself.
This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
arXiv Detail & Related papers (2024-01-02T18:53:13Z) - Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes [57.62036621319563]
We introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the low-data regime.
We demonstrate the superior performance of CLLM in the low-data regime compared to conventional generators.
arXiv Detail & Related papers (2023-12-19T12:34:46Z) - Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models [30.20915403608803]
Griffon is a language-prompted localization dataset for large vision language models.
It is trained end-to-end through a well-designed pipeline.
It achieves state-of-the-art performance on the fine-grained RefCOCO series and Flickr30K Entities.
arXiv Detail & Related papers (2023-11-24T15:35:07Z) - Exploring the Potential of Large Language Models (LLMs) in Learning on
Graphs [59.74814230246034]
Large Language Models (LLMs) have been proven to possess extensive common knowledge and powerful semantic comprehension abilities.
We investigate two possible pipelines: LLMs-as-Enhancers and LLMs-as-Predictors.
arXiv Detail & Related papers (2023-07-07T05:31:31Z)
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.