Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Disaster Image Classification Using Pre-trained Transformer and Contrastive Learning Models
Natural disasters can have devastating consequences for communities, causing loss of life and significant economic damage. To mitigate these impacts, it is crucial to quickly and accurately identify situational awareness and actionable information useful for disaster relief and response organizations. In this paper, we study the use of advanced transformer and contrastive learning models for disaster image classification in a humanitarian context, with focus on state-of-the-art pre-trained vision transformers such as ViT, CSWin and a state-of-the-art pre-trained contrastive learning model, CLIP. We evaluate the performance of these models across various disaster scenarios, including in-domain and cross-domain settings, as well as few- shot learning and zero-shot learning settings. Our results show that the CLIP model outperforms the two transformer models (ViT and CSWin) and also ConvNeXts, a competitive CNN-based model resembling transformers, in all the settings. By improving the performance of disaster image classification, our work can contribute to the goal of reducing the number of deaths and economic losses caused by disasters, as well as helping to decrease the number of people affected by these events.  more » « less
Award ID(s):
1741345
PAR ID:
10472649
Author(s) / Creator(s):
;
Publisher / Repository:
IEEE
Date Published:
Journal Name:
The 10th IEEE International Conference on Data Science and Advanced Analytics (DSAA)
Subject(s) / Keyword(s):
disaster image classification, deep learning, transformers, ViT, CSWin, contrastive learning, CLIP, ConvNeXts
Format(s):
Medium: X
Location:
Thessaloniki, Greece
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers))
    Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP’s contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP’s relative improvement over supervised ReC models trained on real images is 8%. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Hugging Face)
    BioCLIP 2 is a foundation model for biology organismal images. It is trained on TreeOfLife-200M on the basis of a CLIP model (ViT-14/L) pre-trained on LAION-2B. BioCLIP 2 yields state-of-the-art performance in recognizing various species. More importantly, it demonstrates emergent properties beyond species classification after extensive hierarchical contrastive training. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al (, Hugging Face)
    BioCAP is a foundation model for biology organismal images. It is trained on TreeOfLife-10M with synthetic captions (TreeOfLife-10M-Captions) as supervision on the basis of a CLIP model (ViT-B/16) pre-trained by OpenAI. BioCAP achieves state-of-the-art performance on text-image retrieval tasks. 
    more » « less
  4. ; ; (, Advances in Neural Information Processing Systems)
    When learning vision-language models (VLM) for the fashion domain, most existing works design new architectures from vanilla BERT with additional objectives, or perform dense multi-task learning with fashion-specific tasks. Though progress has been made, their architecture or objectives are often intricate and the extendibility is limited.By contrast, with simple architecture (comprising only two unimodal encoders) and just the contrastive objective, popular pre-trained VL models (e.g., CLIP) achieve superior performance in general domains, which are further easily extended to downstream tasks.However, inheriting such benefits of CLIP in the fashion domain is non-trivial in the presence of the notable domain gap. Empirically, we find that directly finetuning on fashion data leads CLIP to frequently ignore minor yet important details such as logos and composition, which are critical in fashion tasks such as retrieval and captioning.In this work, to maintain CLIP's simple architecture and objective while explicitly attending to fashion details, we propose E2 : Easy Regional Contrastive Learning of Expressive Fashion Representations. E2 introduces only a few selection tokens and fusion blocks (just 1.9\% additional parameters in total) with only contrastive losses. Despite lightweight, in our primary focus, cross-modal retrieval, E2 notably outperforms existing fashion VLMs with various fashion-specific objectives.Moreover, thanks to CLIP's widespread use in downstream tasks in general domains (e.g., zero-shot composed image retrieval and image captioning), our model can easily extend these models from general domain to the fashion domain with notable improvement.To conduct a comprehensive evaluation, we further collect data from Amazon Reviews to build a new dataset for cross-modal retrieval in the fashion domain. 
    more » « less
  5. ; ; ; ; ; (, ACM CIKM)
    Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack (i.e., backdoor attack) can manipulate the behavior of machine learning models through contaminating their training dataset, posing significant threat in the real-world application of large pre-trained model, especially for those customized models. Therefore, addressing the unique challenges for exploring vulnerability of pre-trained models is of paramount importance. Through empirical studies on the capability for performing backdoor attack in large pre-trained models (e.g., ViT), we find the following unique challenges of attacking large pre-trained models: 1) the inability to manipulate or even access large training datasets, and 2) the substantial computational resources required for training or fine-tuning these models. To address these challenges, we establish new standards for an effective and feasible backdoor attack in the context of large pre-trained models. In line with these standards, we introduce our EDT model, an Efficient, Data-free, Training-free backdoor attack method. Inspired by model editing techniques, EDT injects an editing-based lightweight codebook into the backdoor of large pre-trained models, which replaces the embedding of the poisoned image with the target image without poisoning the training dataset or training the victim model. Our experiments, conducted across various pre-trained models such as ViT, CLIP, BLIP, and stable diffusion, and on downstream tasks including image classification, image captioning, and image generation, demonstrate the effectiveness of our method. Our code is available at https://github.com/donglgcn/Editing/ 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email