Cross-Domain Video Anomaly Detection without Target Domain Adaptation

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious model-tuning by the end-user who may prefer to have a system that works ``out-of-the-box." To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new `Zero-shot Cross-domain Video Anomaly Detection (zxvad)' framework that includes a future-frame prediction generative model setup. Different from prior future-frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different ``relatively" to features in pseudo-abnormal examples. A novel Untrained Convolutional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxvad generalizes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxvad outperforms the state-of-the-art (SOTA), regardless of whether task-relevant (i.e., VAD) source training data are available or not. Lastly, zxvad also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.

Cross-Modal Knowledge Transfer Without Task-Relevant Source Data

Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality, and have some advantages over RGB in domains like autonomous navigation and remote sensing. As such, building computer vision and deep learning systems for depth and infrared data are crucial. However, large labeled datasets for these modalities are still lacking. In such cases, transferring knowledge from a neural network trained on a well-labeled large dataset in the source modality (RGB) to a neural network that works on a target modality (depth, infrared, etc.) is of great value. For reasons like memory and privacy, it may not be possible to access the source data, and knowledge transfer needs to work with only the source models. We describe an effective solution, SOCKET: SOurce-free Cross-modal KnowledgE Transfer for this challenging task of transferring knowledge from one source modality to a different target modality without access to task-relevant source data. The framework reduces the modality gap using paired task-irrelevant data, as well as by matching the mean and variance of the target features with the batch-norm statistics that are present in the source models. We show through extensive experiments that our method significantly outperforms existing source-free methods for classification tasks which do not account for the modality gap.

Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition

Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition. Most existing approaches do not explicitly embed the high-order spatio-temporal importance to joints' spatial connection topology and intensity, and they do not have direct objectives on their attention module to jointly learn when and where to focus on in the action sequence. To address these problems, we propose the To-a-T Spatio-Temporal Focus (STF), a skeleton-based action recognition framework that utilizes the spatio-temporal gradient to focus on relevant spatio-temporal features. We first propose the STF modules with learnable gradient-enforced and instance-dependent adjacency matrices to model the high-order spatio-temporal dynamics. Second, we propose three loss terms defined on the gradient-based spatio-temporal focus to explicitly guide the classifier when and where to look at, distinguish confusing classes, and optimize the stacked STF modules. STF outperforms the state-of-the-art methods on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets in all 15 settings over different views, subjects, setups, and input modalities, and STF also shows better accuracy on scarce data and dataset shifting settings.

Iterative Self Knowledge Distillation -- From Pothole Classification to Fine-Grained and COVID Recognition

Pothole classification has become an important task for road inspection vehicles to save drivers from potential car accidents and repair bills. Given the limited computational power and fixed number of training epochs, we propose iterative self knowledge distillation (ISKD) to train lightweight pothole classifiers. Designed to improve both the teacher and student models over time in knowledge distillation, ISKD outperforms the state-of-the-art self knowledge distillation method on three pothole classification datasets across four lightweight network architectures, which supports that self knowledge distillation should be done iteratively instead of just once. The accuracy relation between the teacher and student models shows that the student model can still benefit from a moderately trained teacher model. Implying that better teacher models generally produce better student models, our results justify the design of ISKD. In addition to pothole classification, we also demonstrate the efficacy of ISKD on six additional datasets associated with generic classification, fine-grained classification, and medical imaging application, which supports that ISKD can serve as a general-purpose performance booster without the need of a given teacher model and extra trainable parameters.

ViewSynth: Learning Local Features from Depth using View Synthesis

We address the problem of jointly detecting keypoints and learning descriptors in depth data with challenging viewpoint changes. Despite great improvements in recent RGB based local feature learning methods, we show that these methods cannot be directly transferred to the depth image modality. These methods also do not utilize the 2.5D information present in depth images. We propose a framework ViewSynth, designed to jointly learn 3D structure aware depth image representation, and local features from that representation. ViewSynth consists of `View Synthesis Network' (VSN), trained to synthesize depth image views given a depth image representation and query viewpoints. ViewSynth framework includes joint learning of keypoints and feature descriptor, paired with our view synthesis loss, which guides the model to propose keypoints robust to viewpoint changes. We demonstrate the effectiveness of our formulation on several depth image datasets, where learned local features using our proposed ViewSynth framework outperforms the state-of-the-art methods in keypoint matching and camera localization tasks.

Attention Guided Anomaly Detection and Localization in Images

Anomaly detection and localization is a popular computer vision problem involving detecting anomalous images and localizing anomalies within them. However, this task is challenging due to the small sample size and pixel coverage of the anomaly in real-world scenarios. Prior works need to use anomalous training images to compute a threshold to detect and localize anomalies. To remove this need, we propose Convolutional Adversarial Variational autoencoder with Guided Attention (CAVGA), which localizes the anomaly with a convolutional latent variable to preserve the spatial information. In the unsupervised setting, we propose an attention expansion loss, where we encourage CAVGA to focus on all normal regions in the image without using any anomalous training image. Furthermore, using only 2% anomalous images in the weakly supervised setting we propose a complementary guided attention loss, where we encourage the normal attention to focus on all normal regions while minimizing the regions covered by the anomalous attention in the normal image. CAVGA outperforms the state-of-the-art (SOTA) anomaly detection methods on the MNIST, CIFAR-10, Fashion-MNIST, MVTec Anomaly Detection (MVTAD), and modified ShanghaiTech Campus (mSTC) datasets. CAVGA also outperforms the SOTA anomaly localization methods on the MVTAD and mSTC datasets.

Learning without Memorizing

Incremental learning (IL) is an important task aimed to increase the capability of a trained model, in terms of the number of classes recognizable by the model. The key problem in this task is the requirement of storing data (e.g. images) associated with existing classes, while training the classifier to learn new classes. However, this is impractical as it increases the memory requirement at every incremental step, which makes it impossible to implement IL algorithms on the edge devices with limited memory. Hence, we propose a novel approach, called "Learning without Memorizing (LwM)", to preserve the information with respect to existing (base) classes, without storing any of their data, while making the classifier progressively learn the new classes. In LwM, we present an information preserving penalty: Attention Distillation Loss, and demonstrate that penalizing the changes in classifiers' attention maps helps to retain information of the base classes, as new classes are added. We show that adding Attention Distillation Loss to the distillation loss which is an existing information preserving loss consistently outperforms the state-of-the-art performance in the iILSVRC-small and iCIFAR-100 datasets in terms of the overall accuracy of base and incrementally learned classes.

Reducing Visual Confusion with Discriminative Attention

Recent developments in gradient-based attention modeling have led to improved model interpretability by means of class-specific attention maps. A key limitation, however, of these approaches is that the resulting attention maps, while being well localized, are not class discriminative. In this paper, we address this limitation with a new learning framework that makes class-discriminative attention and cross-layer attention consistency a principled and explicit part of the learning process. Furthermore, our framework provides attention guidance to the model in an end-to-end fashion, resulting in better discriminability and reduced visual confusion. We conduct extensive experiments on various image classification benchmarks with our proposed framework and demonstrate its efficacy by means of improved classification accuracy including CIFAR-100 (+3.46%), Caltech-256 (+1.64%), ImageNet (+0.92%), CUB-200-2011 (+4.8%) and PASCAL VOC2012 (+5.78%).

Zero-Shot Deep Domain Adaptation

Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during training. We demonstrate how to perform domain adaptation when no such task-relevant target-domain data is available. To tackle this issue, we propose zero-shot deep domain adaptation (ZDDA), which uses privileged information from task-irrelevant dual-domain pairs. ZDDA learns a source-domain representation which is not only tailored for the task of interest but also close to the target-domain representation. Therefore, the source-domain task of interest solution (e.g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations. Using the MNIST, Fashion-MNIST, NIST, EMNIST, and SUN RGB-D datasets, we show that ZDDA can perform domain adaptation in classification tasks without access to task-relevant target-domain training data. We also extend ZDDA to perform sensor fusion in the SUN RGB-D scene classification task by simulating task-relevant target-domain representations with task-relevant source-domain data. To the best of our knowledge, ZDDA is the first domain adaptation and sensor fusion method which requires no task-relevant target-domain data. The underlying principle is not particular to computer vision data, but should be extensible to other domains.

Learning Compositional Visual Concepts with Mutual Consistency

Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data. For instance, we may learn concepts of changing illumination, geometry or albedo of a scene, and try to recombine them to generate physically meaningful, but unseen data for training and testing. In practice however we often do not have samples from the joint concept space available: We may have data on illumination change in one data set and on geometric change in another one without complete overlap. We pose the following question: How can we learn two or more concepts jointly from different data sets with mutual consistency where we do not have samples from the full joint space? We present a novel answer in this paper based on cyclic consistency over multiple concepts, represented individually by generative adversarial networks (GANs). Our method, ConceptGAN, can be understood as a drop in for data augmentation to improve resilience for real world applications. Qualitative and quantitative evaluations demonstrate its efficacy in generating semantically meaningful images, as well as one shot face verification as an example application.