Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.
We present MMFT-BERT(MultiModal Fusion Transformer with BERT encodings), to solve Visual Question Answering (VQA) ensuring individual and combined processing of multiple input modalities. Our approach benefits from processing multimodal data (video and text) adopting the BERT encodings individually and using a novel transformer-based fusion method to fuse them together. Our method decomposes the different sources of modalities, into different BERT instances with similar architectures, but variable weights. This achieves SOTA results on the TVQA dataset. Additionally, we provide TVQA-Visual, an isolated diagnostic subset of TVQA, which strictly requires the knowledge of visual (V) modality based on a human annotator's judgment. This set of questions helps us to study the model's behavior and the challenges TVQA poses to prevent the achievement of super human performance. Extensive experiments show the effectiveness and superiority of our method.
Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited data. This demonstrates their ability to acquire transferable knowledge, a capability that is central to human learning. However, the existing meta-learning approaches only depend on the current task information during the adaptation, and do not share the meta-knowledge of how a similar task has been adapted before. To address this gap, we propose a 'Path-aware' model-agnostic meta-learning approach. Specifically, our approach not only learns a good initialization for adaptation, it also learns an optimal way to adapt these parameters to a set of task-specific parameters, with learnable update directions, learning rates and, most importantly, the way updates evolve over different time-steps. Compared to the existing meta-learning methods, our approach offers: (a) The ability to learn gradient-preconditioning at different time-steps of the inner-loop, thereby modeling the dynamic learning behavior shared across tasks, and (b) The capability of aggregating the learning context through the provision of direct gradient-skip connections from the old time-steps, thus avoiding overfitting and improving generalization. In essence, our approach not only learns a transferable initialization, but also models the optimal update directions, learning rates, and task-specific learning trends. Specifically, in terms of learning trends, our approach determines the way update directions shape up as the task-specific learning progresses and how the previous update history helps in the current update. Our approach is simple to implement and demonstrates faster convergence. We report significant performance improvements on a number of FSL datasets.
We present a method for image-based crowd counting, one that can predict a crowd density map together with the uncertainty values pertaining to the predicted density map. To obtain prediction uncertainty, we model the crowd density values using Gaussian distributions and develop a convolutional neural network architecture to predict these distributions. A key advantage of our method over existing crowd counting methods is its ability to quantify the uncertainty of its predictions. We illustrate the benefits of knowing the prediction uncertainty by developing a method to reduce the human annotation effort needed to adapt counting networks to a new domain. We present sample selection strategies which make use of the density and uncertainty of predictions from the networks trained on one domain to select the informative images from a target domain of interest to acquire human annotation. We show that our sample selection strategy drastically reduces the amount of labeled data from the target domain needed to adapt a counting network trained on a source domain to the target domain. Empirically, the networks trained on UCF-QNRF dataset can be adapted to surpass the performance of the previous state-of-the-art results on NWPU dataset and Shanghaitech dataset using only 17$\%$ of the labeled training samples from the target domain.
Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. The complexity of the task arises from the commonly-agreed definition of an abnormal event, that is, a rarely occurring event that typically depends on the surrounding context. Following the standard formulation of abnormal event detection as outlier detection, we propose a scene-agnostic framework that learns from training videos containing only normal events. Our framework is composed of an object detector, a set of appearance and motion auto-encoders, and a discriminator. Since our framework only looks at object detections, it can be applied to different scenes, provided that abnormal events are defined identically across scenes. This makes our method scene agnostic, as we rely strictly on objects that can cause anomalies, and not on the background. To overcome the lack of abnormal data during training, we propose an adversarial learning strategy for the auto-encoders. We create a scene-agnostic set of out-of-domain adversarial examples, which are correctly reconstructed by the auto-encoders before applying gradient ascent on the adversarial examples. We further utilize the adversarial examples to serve as abnormal examples when training a binary classifier to discriminate between normal and abnormal latent features and reconstructions. Furthermore, to ensure that the auto-encoders focus only on the main object inside each bounding box image, we introduce a branch that learns to segment the main object. We compare our framework with the state-of-the-art methods on three benchmark data sets, using various evaluation metrics. Compared to existing methods, the empirical results indicate that our approach achieves favorable performance on all data sets.
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects' motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility, and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge, which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script (Code at Dataset <https://github.com/shijieS/OmniMOTDataset>, Dataset Recorder <https://github.com/shijieS/OMOTDRecorder>, Omni-MOT Source <https://github.com/shijieS/DMMN>). We demonstrate the suitability of Omni-MOT for deep learning with DMMNet and also make the source code of our network public.
This paper introduces a new type of image enhancement problem. Compared to traditional image enhancement methods, which mostly deal with pixel-wise modifications of a given photo, our proposed task is to crop an image which is embedded within a photo and enhance the quality of the cropped image. We split our proposed approach into two deep networks: deep photo cropper and deep image enhancer. In the photo cropper network, we employ a spatial transformer to extract the embedded image. In the photo enhancer, we employ super-resolution to increase the number of pixels in the embedded image and reduce the effect of stretching and distortion of pixels. We use cosine distance loss between image features and ground truth for the cropper and the mean square loss for the enhancer. Furthermore, we propose a new dataset to train and test the proposed method. Finally, we analyze the proposed method with respect to qualitative and quantitative evaluations.
Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan behaviors into the models. These malicious behaviors can be triggered at the adversary's will and hence, cause a serious threat to the widespread deployment of deep models. We propose a method to verify if a pre-trained model is Trojaned or benign. Our method captures fingerprints of neural networks in the form of adversarial perturbations learned from the network gradients. Inserting backdoors into a network alters its decision boundaries which are effectively encoded in their adversarial perturbations. We train a two stream network for Trojan detection from its global ($L_\infty$ and $L_2$ bounded) perturbations and the localized region of high energy within each perturbation. The former encodes decision boundaries of the network and latter encodes the unknown trigger shape. We also propose an anomaly detection method to identify the target class in a Trojaned network. Our methods are invariant to the trigger type, trigger size, training data and network architecture. We evaluate our methods on MNIST, NIST-Round0 and NIST-Round1 datasets, with up to 1,000 pre-trained models making this the largest study to date on Trojaned network detection, and achieve over 92\% detection accuracy to set the new state-of-the-art.
Along with the success of deep neural network (DNN) models in solving variousreal world problems, rise the threats to these models that aim to degrade theirintegrity. Trojan attack is one of the recent variant of data poisoning attacks thatinvolves manipulation or modification of the model to act balefully. This can occurwhen an attacker interferes with the training pipeline by inserting triggers into someof the training samples and trains the model to act maliciously only for samplesthat are stamped with trigger. Since the knowledge of such triggers is only privy to the attacker, detection of Trojan behaviour is a challenge task. Unlike any of the existing Trojan detectors, a robust detector should not rely on any assumption about Trojan attack. In this paper, we develop a detector based upon the analysis of intrinsic properties of DNN that could get affected by a Trojan attack. To have a comprehensive study, we propose, Odysseus, the largest Trojan dataset with over 3,000 trained DNN models, both clean and Trojan. It covers a large spectrum of attacks; generated by leveraging the versatility in designing a trigger and mapping (source to target class) type. Our findings reveal that Trojan attacks affect the classifier margin and shape of decision boundary around the manifold of the clean data. Combining these two factors leads to an efficient Trojan detector; operates irrespective of any knowledge of the Trojan attack; that sets the first baseline for this task with accuracy above 83%.