Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data

• URL: http://arxiv.org/abs/2305.05208v3
• Date: Tue, 04 Feb 2025 02:54:38 GMT
• Title: Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
• Authors: Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi,
• Abstract summary: Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning.<n>We introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training.
• Score: 122.282521548393
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning. Improving CLIP typically requires additional data and retraining with new loss functions, but these demands raise resource and time costs, limiting practical use. In this work, we introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training. This eliminates the need for additional data or extensive retraining. Moreover, HELIP integrates effortlessly into current training pipelines with minimal code modifications, allowing for quick and seamless implementation. On comprehensive benchmarks, HELIP consistently boosts existing models. In particular, within just two epochs of training, it improves zero-shot classification accuracy on ImageNet for SLIP models pre-trained on CC3M, CC12M, and YFCC15M datasets by 3.05%, 4.47%, and 10.1% , respectively. In addition, on fine-grained classification datasets, HELIP improves the zero-shot performance of CLIP and SLIP by an average of 8.4% and 18.6%, and their linear probe performance by an average of 9.5% and 3.0%. The code is publicly available at: https://github.com/haonan3/HELIP-NACCL-2025.git.

Related papers

• TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification [12.558701595138928]
  Contrastive Language-Image Pretraining has shown impressive zero-shot performance on image classification. State-of-the-art methods often rely on fine-tuning techniques like prompt learning and adapter-based tuning to optimize CLIP's performance. We introduce training-free approaches, Single-stage LMM Augmented CLIP (SLAC) and Two-stage LMM Augmented CLIP (TLAC) Our models achieved superior accuracy on 9 of 11 base-to-novel datasets, including ImageNet, SUN397, and Caltech101.
  arXiv  Detail & Related papers  (2025-03-15T17:11:41Z)
• Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity [11.414069074535007]
  Contrastive Language-Image Pre-training on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. Small subsets of training data that provably generalize the best has remained an open question. We show that subsets that closely preserve the cross-covariance of the images and captions of the full data provably achieve a superior generalization performance.
  arXiv  Detail & Related papers  (2024-03-18T21:32:58Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Effective pruning of web-scale datasets based on complexity of concept clusters [48.125618324485195]
  We present a method for pruning large-scale multimodal datasets for training CLIP-style models on ImageNet. We find that training on a smaller set of high-quality data can lead to higher performance with significantly lower training costs. We achieve a new state-of-the-art Imagehttps://info.arxiv.org/help/prep#commentsNet zero-shot accuracy and a competitive average zero-shot accuracy on 38 evaluation tasks.
  arXiv  Detail & Related papers  (2024-01-09T14:32:24Z)
• MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training [17.158498267947877]
  We introduce MobileCLIP, a new family of efficient image-text models optimized for runtime performance. MobileCLIP uses knowledge transfer from an image captioning model and an ensemble of strong CLIP encoders to improve the accuracy of efficient models. Our approach avoids train-time compute overhead by storing the additional knowledge in a reinforced dataset.
  arXiv  Detail & Related papers  (2023-11-28T18:55:42Z)
• VeCLIP: Improving CLIP Training via Visual-enriched Captions [63.547204530720705]
  This study introduces a scalable pipeline for noisy caption rewriting. We emphasize the incorporation of visual concepts into captions, termed as Visual-enriched Captions (VeCap) We showcase the adaptation of this method for training CLIP on large-scale web-crawled datasets, termed VeCLIP.
  arXiv  Detail & Related papers  (2023-10-11T17:49:13Z)
• Demystifying CLIP Data [86.34045746910114]
  Contrastive Language-Image Pre-training (CLIP) has advanced research and applications in computer vision. We introduce Metadata-Curated Language-Image Pre-training (MetaCLIP) MetaCLIP takes a raw data pool and metadata (derived from CLIP's concepts) and yields a balanced subset over the metadata distribution.
  arXiv  Detail & Related papers  (2023-09-28T17:59:56Z)
• No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets [0.0]
  We study alternative regularization strategies to push the limits of supervised learning on small image classification datasets. In particular, we employ a agnostic to select (semi) optimal learning rate and weight decay couples via the norm of model parameters. We reach a test accuracy of 66.5%, on par with the best state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-04T16:13:59Z)
• 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)
• UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks [60.46473247205654]
  Using large-scale unsupervised unimodal models as pre-training can enhance the zero-shot performance of image-text pair models. Our experiments show that unimodal pre-training outperforms state-of-the-art CLIP-based models.
  arXiv  Detail & Related papers  (2023-06-07T18:26:22Z)
• Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement [24.108008515395458]
  We propose APE, an Adaptive Prior rEfinement method for CLIP's pre-trained knowledge, which achieves superior accuracy with high computational efficiency. For the average accuracy over 11 benchmarks, both APE and APE-T attain state-of-the-art and respectively outperform the second-best by +1.59% and +1.99% under 16 shots with x30 less learnable parameters.
  arXiv  Detail & Related papers  (2023-04-03T17:58:54Z)
• Learning Customized Visual Models with Retrieval-Augmented Knowledge [104.05456849611895]
  We propose REACT, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs from the web-scale database as external knowledge, and propose to customize the model by only training new modualized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings.
  arXiv  Detail & Related papers  (2023-01-17T18:59:06Z)
• CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention [31.84299688413136]
  Contrastive Language-Image Pre-training has been shown to learn visual representations with great transferability. Existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. We introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a parameter-free Attention module.
  arXiv  Detail & Related papers  (2022-09-28T15:22:11Z)
• Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification [58.06983806317233]
  Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. To enhance CLIP's adaption capability, existing methods proposed to fine-tune additional learnable modules. We propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter.
  arXiv  Detail & Related papers  (2022-07-19T19:12:11Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)

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.