Various types of saliency cues exist, all of which can be instrumental in the foreground extraction. It brings us to an interesting problem of effectively combining them. Note that earlier works either fuse them in the spatial domain or introduce dedicated terms in the energy functions to cater to multiple cues. In contrast, this paper investigates the appearance domain and proposes a novel appearance fusion framework, which we refer to as AppFuse. It is an intuitive framework for fusing candidate appearance models into the desired one for an energy function. Thus, we do not require any alterations in the energy function anymore. Like any fusion strategy, the proposed framework also requires guidance, which we facilitate through reliability and mutual consensus phenomena. To demonstrate the efficacy, we leverage it to solve a foreground extraction problem named video co-localization, where we propose two novel concepts i) hierarchical co-saliency and ii) mask-specific proposals. Our fusion results ensure that similar objects get highlighted sufficiently to ensure localization simply by respecting our framework and different spatiotemporal constraints. Our exhaustive set of experiments using both hand-crafted and learned saliency cues reveal that our approach comfortably outperforms several competing localization methods on standard benchmark datasets.

The primary goal of this paper is to localize objects in a group of semantically similar images jointly, also known as the object co-localization problem. Most related existing works are essentially weakly-supervised, relying prominently on the neighboring images’ weak-supervision. Although weak supervision is beneficial, it is not entirely reliable, for the results are quite sensitive to the neighboring images considered. In this paper, we combine it with a self-awareness phenomenon to mitigate this issue. By self-awareness here, we refer to the solution derived from the image itself in the form of saliency cue, which can also be unreliable if applied alone. Nevertheless, combining these two paradigms together can lead to a better co-localization ability. Specifically, we introduce a dynamic mediator that adaptively strikes a proper balance between the two static solutions to provide an optimal solution. Therefore, we call this method ASOC: Adaptive Self-aware Object Co-localization. We perform exhaustive experiments on several benchmark datasets and validate that weak-supervision supplemented with self-awareness has superior performance outperforming several compared competing methods.

Traditional adversarial attacks rely upon the perturbations generated by gradients from the network which are generally safeguarded by gradient guided search to provide an adversarial counterpart to the network. In this letter, we propose a novel framework to generate adversarial examples where the actual image is not corrupted rather its latent space representation is utilized to tamper the inherent structure of the image while maintaining the perceptual quality intact and to act as legitimate data samples. As opposed to gradient-based attacks, the latent space poisoning exploits the inclination of classifiers to model the independent and identical distribution of the training dataset and tricks it by producing out of distribution samples. We train a disentangled variational autoencoder (β-VAE) to model the data in latent space and then we add noise perturbations using a class-conditioned distribution function to the latent space under the constraint that it is misclassified to the target label. Our empirical results on MNIST, SVHN, and CelebA dataset validate that the generated adversarial examples can easily fool robust l0, l2, l∞norm classifiers designed using provably robust defense mechanisms. The source code is made publicly available at https://github.com/Ujjwal-9/latent-space-poisoning.

In this paper, we propose a novel attention based coupled framework for road and pothole segmentation. In many developing countries as well as in rural areas, the drivable areas are neither well-defined, nor well-maintained. Under such circumstances, an Advance Driver Assistant System (ADAS) is needed to assess the drivable area and alert about the potholes ahead to ensure vehicle safety. Moreover, this information can also be used in structured environments for assessment and maintenance of road health. We demonstrate few-shot learning approach for pothole detection to leverage accuracy even with fewer training samples. We report the exhaustive experimental results for road segmentation on KITTI and IDD datasets. We also present pothole segmentation on IDD.

Online signature verification (OSV) is one of the most challenging tasks in writer identification and digital forensics. Owing to large intra-individual variability, there is a critical requirement to accurately learn the intrapersonal variations of the signature to achieve higher classification accuracy. To achieve this, in this paper, we propose an OSV framework based on deep convolutional Siamese network (DCSN). DCSN automatically extract robust feature descriptions based on metric-based loss function which decreases intra-writer variability (Genuine-Genuine) and increase inter-individual variability (Genuine-Forgery) and guides the DCSN for effective discriminative representation learning for online signatures. Experiments conducted on three widely accepted datasets MCYT-100 (DB1), MCYT-330 (DB2) and SVC-2004-Task2 emphasize the capability of our framework to distinguish the genuine and forgery samples. Experimental results confirm the efficiency of the proposed DCSN in one shot learning by achieving a lower error rate as compared to many recent and state-of-the art OSV models.

In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context. In the proposed method, we construct a Bayesian probabilistic edge map to assign a saliency value to the edgelets by exploiting low level edge features. A Conditional Random Field is then learned to effectively combine these features for edge classification with object/non-object label. We propose an objectness score for the generated windows by analyzing the salient edge density inside the bounding box. Extensive experiments on PASCAL VOC 2007 dataset demonstrate that the proposed method gives competitive performance against 10 popular generic object detection techniques while using fewer number of proposals.

Driver assistance systems, that rely on vehicular sensors such as cameras, LIDAR and other on-board diagnostic sensors, have progressed rapidly in recent years to increase road safety. Road conditions in developing countries like India are chaotic where roads are not well maintained and thus vehicular sensors alone do not suffice in detecting impending collisions. In this paper, we investigate a collaborative driver assistance system "DRIZY: DRIve eaSY" for such scenarios where inference is drawn from on-board camera feed to alert drivers of obstacles ahead and the cloud uses GPS sensor data uploaded by all vehicles to alert drivers of vehicles in potential collision trajectory. Thus, we combine computer vision and vehicle-to-cloud communication to create comprehensive situational awareness. We prototype our system to consider two types of collisions: vehicle-to-vehicle collisions based on uploading GPS sensor data of vehicles to cloud and vehicle-to-pedestrian collisions based on detecting pedestrians from vehicle's dashboard camera feed. Sensor data processing in each vehicle occurs on smartphone for GPS values which are then uploaded to cloud and on raspberry pi3 for video feeds to make a cost-effective solution. Experiments over both 4G and wireless networks in India show that collaborative driver assistance is feasible in low traffic density within acceptable driver reaction time of <5 sec, but can be limited by the time to process compute-intensive video feeds in real-time. We investigate novel ways to optimize the processing to find an acceptable trade-off.

In this paper we present a novel approach for refining segmentation using saliency map. To achieve this, we first develop a new saliency detection method based on cues at various levels. Initially preprocessing step is done using non-linear anisotropic diffusion filtering in order to preserve the edge information in the foreground salient objects and smoothen the background. Then we apply grab cut segmentation using saliency map as the input to get improved segmentation. Repeated application of the scheme is used for multi-object segmentation. The experimental results for the saliency technique show high precision and recall rates against the state-of-the-art methods.