DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in the presence of a predefined trigger pattern, which can be easily realized via poisoning a small amount of data. In general, adversarial training is believed to defend against backdoor attacks since it helps models to keep their prediction unchanged even if we perturb the input image (as long as within a feasible range). Unfortunately, few previous studies succeed in doing so. To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters. For instance, adversarial training with spatial adversarial examples provides notable robustness against commonly-used patch-based backdoor attacks. We further propose a hybrid strategy which provides satisfactory robustness across different backdoor attacks.
In image processing, classical methods minimize a suitable functional that balances between computational feasibility (convexity of the functional is ideal) and suitable penalties reflecting the desired image decomposition. The fact that algorithms derived from such minimization problems can be used to construct (deep) learning architectures has spurred the development of algorithms that can be trained for a specifically desired image decomposition, e.g. into cartoon and texture. While many such methods are very successful, theoretical guarantees are only scarcely available. To this end, in this contribution, we formalize a general class of intersection point problems encompassing a wide range of (learned) image decomposition models, and we give an existence result for a large subclass of such problems, i.e. giving the existence of a fixpoint of the corresponding algorithm. This class generalizes classical model-based variational problems, such as the TV-l2 -model or the more general TV-Hilbert model. To illustrate the potential for learned algorithms, novel (non learned) choices within our class show comparable results in denoising and texture removal.
Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural Networks (DNNs) still raises concerns in the practical operational environment, which calls for systematic testing, especially in safety-critical scenarios. Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs. However, due to the blackbox nature of DNN, the existing structural coverage criteria are difficult to interpret, making it hard to understand the underlying principles of these criteria. The relationship between the structural coverage and the decision logic of DNNs is unknown. Moreover, recent studies have further revealed the non-existence of correlation between the structural coverage and DNN defect detection, which further posts concerns on what a suitable DNN testing criterion should be. In this paper, we propose the interpretable coverage criteria through constructing the decision structure of a DNN. Mirroring the control flow graph of the traditional program, we first extract a decision graph from a DNN based on its interpretation, where a path of the decision graph represents a decision logic of the DNN. Based on the control flow and data flow of the decision graph, we propose two variants of path coverage to measure the adequacy of the test cases in exercising the decision logic. The higher the path coverage, the more diverse decision logic the DNN is expected to be explored. Our large-scale evaluation results demonstrate that: the path in the decision graph is effective in characterizing the decision of the DNN, and the proposed coverage criteria are also sensitive with errors including natural errors and adversarial examples, and strongly correlated with the output impartiality.
We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for each class. Motivated by the binary relevance method for multi-label classification, we propose to inversely learn the mapping between an image and a semantic classifier. Given an input image, the proposed Image-Guided Semantic Classification (IGSC) method creates a label classifier, being applied to all label embeddings to determine whether a label belongs to the input image. Therefore, semantic classifiers are image-adaptive and are generated during inference. IGSC is conceptually simple and can be realized by a slight enhancement of an existing deep architecture for classification; yet it is effective and outperforms state-of-the-art embedding-based generalized ZSL approaches on standard benchmarks.
The volume of available data has grown dramatically in recent years in many applications. Furthermore, the age of networks that used multiple modalities separately has practically ended. Therefore, enabling bidirectional cross-modality data retrieval capable of processing has become a requirement for many domains and disciplines of research. This is especially true in the medical field, as data comes in a multitude of types, including various types of images and reports as well as molecular data. Most contemporary works apply cross attention to highlight the essential elements of an image or text in relation to the other modalities and try to match them together. However, regardless of their importance in their own modality, these approaches usually consider features of each modality equally. In this study, self-attention as an additional loss term will be proposed to enrich the internal representation provided into the cross attention module. This work suggests a novel architecture with a new loss term to help represent images and texts in the joint latent space. Experiment results on two benchmark datasets, i.e. MS-COCO and ARCH, show the effectiveness of the proposed method.
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths, or require a heavy fine-tuning process to recover the performance. To our knowledge, this vulnerability to low precisions relies on two statistical observations of feature map values. First, distribution of feature map values varies significantly per channel and per input image. Second, feature maps have outliers that can dominate the quantization error. Based on these observations, we propose a novel distribution-aware quantization scheme (DAQ) which facilitates accurate training-free quantization in ultra-low precision. A simple function of DAQ determines dynamic range of feature maps and weights with low computational burden. Furthermore, our method enables mixed-precision quantization by calculating the relative sensitivity of each channel, without any training process involved. Nonetheless, quantization-aware training is also applicable for auxiliary performance gain. Our new method outperforms recent training-free and even training-based quantization methods to the state-of-the-art image super-resolution networks in ultra-low precision.
Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition. Many recent studies leverage the pre-trained CLIP models for image-level classification and manipulation. In this paper, we further explore the potentials of CLIP for pixel-level dense prediction, specifically in semantic segmentation. Our method, DenseCLIP, in the absence of annotations and fine-tuning, yields reasonable segmentation results on open concepts across various datasets. By adding pseudo labeling and self-training, DenseCLIP+ surpasses SOTA transductive zero-shot semantic segmentation methods by large margins, e.g., mIoUs of unseen classes on PASCAL VOC/PASCAL Context/COCO Stuff are improved from 35.6/20.7/30.3 to 86.1/66.7/54.7. We also test the robustness of DenseCLIP under input corruption and evaluate its capability in discriminating fine-grained objects and novel concepts. Our finding suggests that DenseCLIP can serve as a new reliable source of supervision for dense prediction tasks to achieve annotation-free segmentation.
The Multimedia and Computer Vision Lab of the University of Augsburg participated in the VTT task only. We use the VATEX and TRECVID-VTT datasets for training our VTT models. We base our model on the Transformer approach for both of our submitted runs. For our second model, we adapt the X-Linear Attention Networks for Image Captioning which does not yield the desired bump in scores. For both models, we train on the complete VATEX dataset and 90% of the TRECVID-VTT dataset for pretraining while using the remaining 10% for validation. We finetune both models with self-critical sequence training, which boosts the validation performance significantly. Overall, we find that training a Video-to-Text system on traditional Image Captioning pipelines delivers very poor performance. When switching to a Transformer-based architecture our results greatly improve and the generated captions match better with the corresponding video.
The COVID-19 (coronavirus) is an ongoing pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The virus was first identified in mid-December 2019 in the Hubei province of Wuhan, China and by now has spread throughout the planet with more than 75.5 million confirmed cases and more than 1.67 million deaths. With limited number of COVID-19 test kits available in medical facilities, it is important to develop and implement an automatic detection system as an alternative diagnosis option for COVID-19 detection that can used on a commercial scale. Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Computer vision and deep learning techniques can help in determining COVID-19 virus with Chest X-ray Images. Due to the high availability of large-scale annotated image datasets, great success has been achieved using convolutional neural network for image analysis and classification. In this research, we have proposed a deep convolutional neural network trained on five open access datasets with binary output: Normal and Covid. The performance of the model is compared with four pre-trained convolutional neural network-based models (COVID-Net, ResNet18, ResNet and MobileNet-V2) and it has been seen that the proposed model provides better accuracy on the validation set as compared to the other four pre-trained models. This research work provides promising results which can be further improvise and implement on a commercial scale.
Generative adversarial networks (GANs) are unsupervised Deep Learning approach in the computer vision community which has gained significant attention from the last few years in identifying the internal structure of multimodal medical imaging data. The adversarial network simultaneously generates realistic medical images and corresponding annotations, which proven to be useful in many cases such as image augmentation, image registration, medical image generation, image reconstruction, and image-to-image translation. These properties bring the attention of the researcher in the field of medical image analysis and we are witness of rapid adaption in many novel and traditional applications. This chapter provides state-of-the-art progress in GANs-based clinical application in medical image generation, and cross-modality synthesis. The various framework of GANs which gained popularity in the interpretation of medical images, such as Deep Convolutional GAN (DCGAN), Laplacian GAN (LAPGAN), pix2pix, CycleGAN, and unsupervised image-to-image translation model (UNIT), continue to improve their performance by incorporating additional hybrid architecture, has been discussed. Further, some of the recent applications of these frameworks for image reconstruction, and synthesis, and future research directions in the area have been covered.