Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

• URL: http://arxiv.org/abs/2401.02460v2
• Date: Wed, 3 Apr 2024 22:23:25 GMT
• Title: Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions
• Authors: Oindrila Saha, Grant Van Horn, Subhransu Maji,
• Abstract summary: We develop methods to train vision-language models (VLMs) with "bag-level" image-text supervision. We use descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance.
• Score: 24.596929878045568
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of information -- descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets -- to improve the zero-shot classification performance of VLMs across fine-grained domains. On the technical side, we develop methods to train VLMs with this "bag-level" image-text supervision. We find that simply using these attributes at test-time does not improve performance, but our training strategy, for example, on the iNaturalist dataset, leads to an average improvement of 4-5% in zero-shot classification accuracy for novel categories of birds and flowers. Similar improvements are observed in domains where a subset of the categories was used to fine-tune the model. By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories. We systematically evaluate their ability to improve zero-shot categorization in natural domains. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance. Our method also outperforms prior work on prompt-based tuning of VLMs. We release the benchmark, consisting of 14 datasets at https://github.com/cvl-umass/AdaptCLIPZS , which will contribute to future research in zero-shot recognition.

Related papers

• Retrieval-enriched zero-shot image classification in low-resource domains [23.529317590033845]
  Low-resource domains present significant challenges for language and visual understanding tasks. Recent advancements in Vision-Language Models (VLM) have shown promising results in high-resource domains but fall short in low-resource concepts that are under-represented. We tackle the challenging task of zero-shot low-resource image classification from a novel perspective.
  arXiv  Detail & Related papers  (2024-11-01T19:24:55Z)
• Why are Visually-Grounded Language Models Bad at Image Classification? [39.76294811955341]
  We revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs significantly underperform CLIP on standard image classification benchmarks like ImageNet. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data.
  arXiv  Detail & Related papers  (2024-05-28T17:57:06Z)
• 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)
• TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification [28.72126911321771]
  Vision and Language Models (VLMs) have enabled visual recognition of a potentially unlimited set of categories described by text prompts. For the best visual recognition performance, these models still require tuning to better fit the data distributions of the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-13T08:59:54Z)
• Text Descriptions are Compressive and Invariant Representations for Visual Learning [63.3464863723631]
  We show that an alternative approach, in line with humans' understanding of multiple visual features per class, can provide compelling performance in the robust few-shot learning setting. In particular, we introduce a novel method, textit SLR-AVD (Sparse Logistic Regression using Augmented Visual Descriptors). This method first automatically generates multiple visual descriptions of each class via a large language model (LLM), then uses a VLM to translate these descriptions to a set of visual feature embeddings of each image, and finally uses sparse logistic regression to select a relevant subset of these features to classify
  arXiv  Detail & Related papers  (2023-07-10T03:06:45Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)
• Novel Class Discovery in Semantic Segmentation [104.30729847367104]
  We introduce a new setting of Novel Class Discovery in Semantic (NCDSS) It aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image. We propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels.
  arXiv  Detail & Related papers  (2021-12-03T13:31:59Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption [72.35532598131176]
  We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features. We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
  arXiv  Detail & Related papers  (2021-06-29T08:08:33Z)
• Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning [0.5156484100374058]
  Few-shot learning aims to learn novel visual categories from very few samples. We propose a Self-Attention Based Complementary Module (SAC Module) to fulfill the weakly-supervised object localization. We also produce the activated masks for selecting discriminative deep descriptors for few-shot classification.
  arXiv  Detail & Related papers  (2020-03-02T14:07:05Z)

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.