The Neglected Tails in Vision-Language Models

• URL: http://arxiv.org/abs/2401.12425v3
• Date: Wed, 22 May 2024 16:29:58 GMT
• Title: The Neglected Tails in Vision-Language Models
• Authors: Shubham Parashar, Zhiqiu Lin, Tian Liu, Xiangjue Dong, Yanan Li, Deva Ramanan, James Caverlee, Shu Kong,
• Abstract summary: We show that vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. We propose REtrieval-Augmented Learning (REAL) to mitigate the imbalanced performance of zero-shot VLMs.
• Score: 51.79913798808725
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more than ten concepts like night snake, presumably due to their limited presence in the pretraining data. However, measuring the frequency of concepts in VLMs' large-scale datasets is challenging. We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts. Our analysis confirms that popular datasets, such as LAION, exhibit a long-tailed concept distribution, yielding biased performance in VLMs. We also find that downstream applications of VLMs, including visual chatbots (e.g., GPT-4V) and text-to-image models (e.g., Stable Diffusion), often fail to recognize or generate images of rare concepts identified by our method. To mitigate the imbalanced performance of zero-shot VLMs, we propose REtrieval-Augmented Learning (REAL). First, instead of prompting VLMs using the original class names, REAL uses their most frequent synonyms found in pretraining texts. This simple change already outperforms costly human-engineered and LLM-enriched prompts over nine benchmark datasets. Second, REAL trains a linear classifier on a small yet balanced set of pretraining data retrieved using concept synonyms. REAL surpasses the previous zero-shot SOTA, using 400x less storage and 10,000x less training time!

Related papers

• Déjà Vu Memorization in Vision-Language Models [39.51189095703773]
  We propose a new method for measuring memorization in Vision-Language Models (VLMs) We show that the model indeed retains information about individual objects in the training images beyond what can be inferred from correlations or the image caption. We evaluate d'eja vu memorization at both sample and population level, and show that it is significant for OpenCLIP trained on as many as 50M image-caption pairs.
  arXiv  Detail & Related papers  (2024-02-03T09:55:35Z)
• Revisiting Few-Shot Object Detection with Vision-Language Models [49.79495118650838]
  We revisit the task of few-shot object detection (FSOD) in the context of recent foundational vision-language models (VLMs) We propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external data. We discuss our recent CVPR 2024 Foundational FSOD competition and share insights from the community.
  arXiv  Detail & Related papers  (2023-12-22T07:42:00Z)
• VILA: On Pre-training for Visual Language Models [74.08039416548209]
  We study the design options for VLM pre-training through step-by-step controllable comparisons. We build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-12T18:58:18Z)
• 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)
• Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models [13.340759455910721]
  We propose a novel method to prevent zero-shot transfer degradation in the continual learning of vision-language models. Our method outperforms other methods in the traditional class-incremental learning setting.
  arXiv  Detail & Related papers  (2023-03-12T10:28:07Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)
• Generative Negative Text Replay for Continual Vision-Language Pretraining [95.2784858069843]
  Vision-language pre-training has attracted increasing attention recently. Massive data are usually collected in a streaming fashion. We propose a multi-modal knowledge distillation between images and texts to align the instance-wise prediction between old and new models.
  arXiv  Detail & Related papers  (2022-10-31T13:42:21Z)
• Learning Transferable Visual Models From Natural Language Supervision [13.866297967166089]
  Learning directly from raw text about images is a promising alternative. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn. SOTA image representations are learned from scratch on a dataset of 400 million (image, text) pairs collected from the internet.
  arXiv  Detail & Related papers  (2021-02-26T19:04:58Z)
• VisualGPT: Data-efficient Image Captioning by Balancing Visual Input and Linguistic Knowledge from Pretraining [39.24803665848558]
  We propose VisualGPT, a data-efficient image captioning model that leverages the linguistic knowledge from a large pretrained language model (LM) We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder on a small amount of in-domain training data. VisualGPT outperforms the best baseline model by up to 10.8% CIDEr on MS COCO and up to 5.4% CIDEr on Conceptual Captions.
  arXiv  Detail & Related papers  (2021-02-20T18:02:42Z)

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.