GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers

• URL: http://arxiv.org/abs/2503.19480v1
• Date: Tue, 25 Mar 2025 09:15:34 GMT
• Title: GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
• Authors: Shijie Ma, Yuying Ge, Teng Wang, Yuxin Guo, Yixiao Ge, Ying Shan,
• Abstract summary: In this work, we empirically found that visually perfect generations are not always optimal for representation enhancement.<n>The essence lies in effectively extracting fine-grained knowledge from generative models while mitigating irrelevant information.<n>We propose a two-stage training strategy to prioritize learning useful visual knowledge.
• Score: 47.92114255322673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The synergy between generative and discriminative models receives growing attention. While discriminative Contrastive Language-Image Pre-Training (CLIP) excels in high-level semantics, it struggles with perceiving fine-grained visual details. Generally, to enhance representations, generative models take CLIP's visual features as conditions for reconstruction. However, the underlying principle remains underexplored. In this work, we empirically found that visually perfect generations are not always optimal for representation enhancement. The essence lies in effectively extracting fine-grained knowledge from generative models while mitigating irrelevant information. To explore critical factors, we delve into three aspects: (1) Conditioning mechanisms: We found that even a small number of local tokens can drastically reduce the difficulty of reconstruction, leading to collapsed training. We thus conclude that utilizing only global visual tokens as conditions is the most effective strategy. (2) Denoising configurations: We observed that end-to-end training introduces extraneous information. To address this, we propose a two-stage training strategy to prioritize learning useful visual knowledge. Additionally, we demonstrate that lightweight denoisers can yield remarkable improvements. (3) Generation paradigms: We explore both continuous and discrete denoisers with desirable outcomes, validating the versatility of our method. Through our in-depth explorations, we have finally arrived at an effective method, namely GenHancer, which consistently outperforms prior arts on the MMVP-VLM benchmark, e.g., 6.0% on OpenAICLIP. The enhanced CLIP can be further plugged into multimodal large language models for better vision-centric performance. All the models and codes are made publicly available.

Related papers

• TULIP: Towards Unified Language-Image Pretraining [60.99500935831526]
  We introduce T, an open-source, drop-in replacement for existing CLIP-like models.<n>Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features.<n>Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across benchmarks.
  arXiv  Detail & Related papers  (2025-03-19T17:58:57Z)
• MetaMorph: Multimodal Understanding and Generation via Instruction Tuning [57.35160715164359]
  Visual-Predictive Instruction Tuning (VPiT) is a simple and effective extension to visual instruction tuning. VPiT teaches an LLM to predict discrete text tokens and continuous visual tokens from any input sequence of image and text data. We train our MetaMorph model and achieve competitive performance on both visual understanding and generation.
  arXiv  Detail & Related papers  (2024-12-18T18:58:50Z)
• POINTS: Improving Your Vision-language Model with Affordable Strategies [28.611705477757454]
  We train a robust baseline model using latest advancements in vision-language models. We filter pre-training data using perplexity, selecting the lowest perplexity data for training. During visual instruction tuning, we used model soup on different datasets when adding more datasets yielded marginal improvements.
  arXiv  Detail & Related papers  (2024-09-07T13:41:37Z)
• Anomaly Detection by Adapting a pre-trained Vision Language Model [48.225404732089515]
  We present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. We introduce the learnable prompt and propose to associate it with abnormal patterns through self-supervised learning. We achieve the state-of-the-art 97.5/55.6 and 89.3/33.1 on MVTec-AD and VisA for anomaly detection and localization.
  arXiv  Detail & Related papers  (2024-03-14T15:35:07Z)
• CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples [34.71588837946776]
  We propose CounterCurate, a framework to improve visio-linguistic compositional reasoning. In particular, we identify two critical under-explored problems: the neglect of the physically grounded reasoning. We first spotlight the near-chance performance of multimodal models like CLIP and LLaVA in physically grounded compositional reasoning. We then apply simple data augmentation using grounded image generation model GLIGEN to generate fine-tuning data, resulting in significant performance improvements.
  arXiv  Detail & Related papers  (2024-02-20T18:59:55Z)
• Aligning Modalities in Vision Large Language Models via Preference Fine-tuning [67.62925151837675]
  In this work, we frame the hallucination problem as an alignment issue, tackle it with preference tuning. Specifically, we propose POVID to generate feedback data with AI models. We use ground-truth instructions as the preferred response and a two-stage approach to generate dispreferred data. In experiments across broad benchmarks, we show that we can not only reduce hallucinations, but improve model performance across standard benchmarks, outperforming prior approaches.
  arXiv  Detail & Related papers  (2024-02-18T00:56:16Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• 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.