2023-03-14 更新
DINO-MC: Self-supervised Contrastive Learning for Remote Sensing Imagery with Multi-sized Local Crops
Authors:Xinye Wanyan, Sachith Seneviratne, Shuchang Shen, Michael Kirley
Due to the costly nature of remote sensing image labeling and the large volume of available unlabeled imagery, self-supervised methods that can learn feature representations without manual annotation have received great attention. While prior works have explored self-supervised learning in remote sensing tasks, pretext tasks based on local-global view alignment remain underexplored. Inspired by DINO, which employs an effective representation learning structure with knowledge distillation based on global-local view alignment, we formulate two pretext tasks for use in self-supervised learning on remote sensing imagery (SSLRS). Using these tasks, we explore the effectiveness of positive temporal contrast as well as multi-sized views on SSLRS. Moreover, we extend DINO and propose DINO-MC which uses local views of various sized crops instead of a single fixed size. Our experiments demonstrate that even when pre-trained on only 10% of the dataset, DINO-MC performs on par or better than existing state of the art SSLRS methods on multiple remote sensing tasks, while using less computational resources. All codes, models and results are available at https://github.com/WennyXY/DINO-MC.
PDF
点此查看论文截图
Robust Contrastive Language-Image Pretraining against Adversarial Attacks
Authors:Wenhan Yang, Baharan Mirzasoleiman
Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive data that powers large multimodal models such as CLIP, makes them extremely vulnerable to various types of adversarial attacks, including targeted and backdoor data poisoning attacks. Despite this vulnerability, robust contrastive vision-language pretraining against adversarial attacks has remained unaddressed. In this work, we propose RoCLIP, the first effective method for robust pretraining {and fine-tuning} multimodal vision-language models. RoCLIP effectively breaks the association between poisoned image-caption pairs by considering a pool of random examples, and (1) matching every image with the text that is most similar to its caption in the pool, and (2) matching every caption with the image that is most similar to its image in the pool. Our extensive experiments show that our method renders state-of-the-art targeted data poisoning and backdoor attacks ineffective during pre-training or fine-tuning of CLIP. In particular, RoCLIP decreases the poison and backdoor attack success rates down to 0\% during pre-training and 1\%-4\% during fine-tuning, and effectively improves the model’s performance.
PDF
点此查看论文截图
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
Authors:Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, Jian Zhao
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance. Previous works explore new optimizing targets and search spaces for NAS ReID, yet they neglect the difference of training schemes between image classification and ReID. In this work, we propose a novel Twins Contrastive Mechanism (TCM) to provide more appropriate supervision for ReID architecture search. TCM reduces the category overlaps between the training and validation data, and assists NAS in simulating real-world ReID training schemes. We then design a Multi-Scale Interaction (MSI) search space to search for rational interaction operations between multi-scale features. In addition, we introduce a Spatial Alignment Module (SAM) to further enhance the attention consistency confronted with images from different sources. Under the proposed NAS scheme, a specific architecture is automatically searched, named as MSINet. Extensive experiments demonstrate that our method surpasses state-of-the-art ReID methods on both in-domain and cross-domain scenarios. Source code available in https://github.com/vimar-gu/MSINet.
PDF Accepted by CVPR2023
点此查看论文截图
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
Authors:Weixiong Lin, Ziheng Zhao, Xiaoman Zhang, Chaoyi Wu, Ya Zhang, Yanfeng Wang, Weidi Xie
Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral’s OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-of-the-art results on various downstream tasks, including image-text retrieval on ROCO, MedMNIST image classification, Medical VQA, i.e. +8.1% R@10 on image-text retrieval, +3.9% accuracy on image classification.
PDF 10 pages, 3 figures
点此查看论文截图
Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos
Authors:David Fan, Deyu Yang, Xinyu Li, Vimal Bhat, Rohith MV
Contrastive learning has recently narrowed the gap between self-supervised and supervised methods in image and video domain. State-of-the-art video contrastive learning methods such as CVRL and $\rho$-MoCo spatiotemporally augment two clips from the same video as positives. By only sampling positive clips locally from a single video, these methods neglect other semantically related videos that can also be useful. To address this limitation, we leverage nearest-neighbor videos from the global space as additional positive pairs, thus improving positive key diversity and introducing a more relaxed notion of similarity that extends beyond video and even class boundaries. Our method, Inter-Intra Video Contrastive Learning (IIVCL), improves performance on a range of video tasks.
PDF Accepted to the ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models
点此查看论文截图
Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning
Authors:Cong Cao, Huanjing Yue, Xin Liu, Jingyu Yang
Capturing high dynamic range (HDR) images (videos) is attractive because it can reveal the details in both dark and bright regions. Since the mainstream screens only support low dynamic range (LDR) content, tone mapping algorithm is required to compress the dynamic range of HDR images (videos). Although image tone mapping has been widely explored, video tone mapping is lagging behind, especially for the deep-learning-based methods, due to the lack of HDR-LDR video pairs. In this work, we propose a unified framework (IVTMNet) for unsupervised image and video tone mapping. To improve unsupervised training, we propose domain and instance based contrastive learning loss. Instead of using a universal feature extractor, such as VGG to extract the features for similarity measurement, we propose a novel latent code, which is an aggregation of the brightness and contrast of extracted features, to measure the similarity of different pairs. We totally construct two negative pairs and three positive pairs to constrain the latent codes of tone mapped results. For video tone mapping, we propose a temporal-feature-replaced (TFR) module to efficiently utilize the temporal correlation and improve the temporal consistency of video tone-mapped results. We construct a large-scale unpaired HDR-LDR video dataset to facilitate the unsupervised training process for video tone mapping. Experimental results demonstrate that our method outperforms state-of-the-art image and video tone mapping methods. Our code and dataset will be released after the acceptance of this work.
PDF 12 pages,5 figures
点此查看论文截图