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
This content will become publicly available on October 9, 2024
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
- NSF-PAR ID:
- 10472649
- 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
-
-
more » « less
Abstract Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.
-
Ruiz, Francisco ; Dy, Jennifer ; van de Meent, Jan-Willem (Ed.)We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimization of its contrastive learning objective. We accomplish this by taking advantage of an information efficient lower-bound to maximize the mutual information between the two input modalities. This allows CLIP-Lite to be trained with significantly reduced amounts of data and batch sizes while obtaining better performance than CLIP at the same scale. We evaluate CLIP-Lite by pretraining on the COCO-Captions dataset and testing transfer learning to other datasets. CLIP-Lite obtains a +14.0 mAP absolute gain in performance on Pascal VOC classification, and a +22.1 top-1 accuracy gain on ImageNet, while being comparable or superior to other, more complex, text-supervised models. CLIP-Lite is also superior to CLIP on image and text retrieval, zero-shot classification, and visual grounding. Finally, we show that CLIP-Lite can leverage language semantics to encourage bias-free visual representations that can be used in downstream tasks. Implementation: https://github.com/4m4n5/CLIP-Litemore » « less
-
Effectively filtering and categorizing the large volume of user-generated content on social media during disaster events can help emergency management and disaster response prioritize their resources. Deep learning approaches, including recurrent neural networks and transformer-based models, have been previously used for this purpose. Capsule Neural Networks (CapsNets), initially proposed for image classification, have been proven to be useful for text analysis as well. However, to the best of our knowledge, CapsNets have not been used for classifying crisis-related messages, and have not been extensively compared with state-of-the-art transformer-based models, such as BERT. Therefore, in this study, we performed a thorough comparison between CapsNet models, state-of-the-art BERT models and two popular recurrent neural network models that have been successfully used for tweet classification, specifically, LSTM and Bi-LSTM models, on the task of classifying crisis tweets both in terms of their informativeness (binary classification), as well as their humanitarian content (multi-class classification). For this purpose, we used several benchmark datasets for crisis tweet classification, namely CrisisBench, CrisisNLP and CrisisLex. Experimental results show that the performance of the CapsNet models is on a par with that of LSTM and Bi-LSTM models for all metrics considered, while the performance obtained with BERT models have surpassed the performance of the other three models across different datasets and classes for both classification tasks, and thus BERT could be considered the best overall model for classifying crisis tweets.more » « less
-
Aliannejadi, M ; Faggioli, G ; Ferro, N ; Vlachos, M. (Ed.)This work discusses the participation of CS_Morgan in the Concept Detection and Caption Prediction tasks of the ImageCLEFmedical 2023 Caption benchmark evaluation campaign. The goal of this task is to automatically identify relevant concepts and their locations in images, as well as generate coherent captions for the images. The dataset used for this task is a subset of the extended Radiology Objects in Context (ROCO) dataset. The implementation approach employed by us involved the use of pre-trained Convolutional Neural Networks (CNNs), Vision Transformer (ViT), and Text-to-Text Transfer Transformer (T5) architectures. These models were leveraged to handle the different aspects of the tasks, such as concept detection and caption generation. In the Concept Detection task, the objective was to classify multiple concepts associated with each image. We utilized several deep learning architectures with ‘sigmoid’ activation to enable multilabel classification using the Keras framework. We submitted a total of five (5) runs for this task, and the best run achieved an F1 score of 0.4834, indicating its effectiveness in detecting relevant concepts in the images. For the Caption Prediction task, we successfully submitted eight (8) runs. Our approach involved combining the ViT and T5 models to generate captions for the images. For the caption prediction task, the ranking is based on the BERTScore, and our best run achieved a score of 0.5819 based on generating captions using the fine-tuned T5 model from keywords generated using the pretrained ViT as the encoder.more » « less
