Saket Anand

Ashima Garg, Depanshu Sani, Saket Anand

Label hierarchies are often available apriori as part of biological taxonomy or language datasets WordNet. Several works exploit these to learn hierarchy aware features in order to improve the classifier to make semantically meaningful mistakes while maintaining or reducing the overall error. In this paper, we propose a novel approach for learning Hierarchy Aware Features (HAF) that leverages classifiers at each level of the hierarchy that are constrained to generate predictions consistent with the label hierarchy. The classifiers are trained by minimizing a Jensen-Shannon Divergence with target soft labels obtained from the fine-grained classifiers. Additionally, we employ a simple geometric loss that constrains the feature space geometry to capture the semantic structure of the label space. HAF is a training time approach that improves the mistakes while maintaining top-1 error, thereby, addressing the problem of cross-entropy loss that treats all mistakes as equal. We evaluate HAF on three hierarchical datasets and achieve state-of-the-art results on the iNaturalist-19 and CIFAR-100 datasets. The source code is available at https://github.com/07Agarg/HAF

Sharat Agarwal, Saket Anand, Chetan Arora

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between supervised and unsupervised DA techniques, ADA allows for an excellent trade-off between annotation cost and performance. Prior art makes use of measures of uncertainty or disagreement of models to identify `regions' to be annotated by the human oracle. However, these regions frequently comprise of pixels at object boundaries which are hard and tedious to annotate. Hence, even if the fraction of image pixels annotated reduces, the overall annotation time and the resulting cost still remain high. In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame. We show that these set of `hard' classes are context-dependent and typically vary across frames, and when annotated help the model generalize better. We propose two ADA techniques: the Anchor-based and Augmentation-based approaches to select complementary and diverse regions in the context of the current training set. Our approach achieves 66.6 mIoU on GTA to Cityscapes dataset with an annotation budget of 4.7% in comparison to 64.9 mIoU by MADA using 5% of annotations. Our technique can also be used as a decorator for any existing frame-based AL technique, e.g., we report 1.5% performance improvement for CDAL on Cityscapes using our approach.

Akshit Jindal, Vikram Goyal, Saket Anand et al.

Machine Learning (ML) models become vulnerable to Model Stealing Attacks (MSA) when they are deployed as a service. In such attacks, the deployed model is queried repeatedly to build a labelled dataset. This dataset allows the attacker to train a thief model that mimics the original model. To maximize query efficiency, the attacker has to select the most informative subset of data points from the pool of available data. Existing attack strategies utilize approaches like Active Learning and Semi-Supervised learning to minimize costs. However, in the black-box setting, these approaches may select sub-optimal samples as they train only one thief model. Depending on the thief model's capacity and the data it was pretrained on, the model might even select noisy samples that harm the learning process. In this work, we explore the usage of an ensemble of deep learning models as our thief model. We call our attack Army of Thieves(AOT) as we train multiple models with varying complexities to leverage the crowd's wisdom. Based on the ensemble's collective decision, uncertain samples are selected for querying, while the most confident samples are directly included in the training data. Our approach is the first one to utilize an ensemble of thief models to perform model extraction. We outperform the base approaches of existing state-of-the-art methods by at least 3% and achieve a 21% higher adversarial sample transferability than previous work for models trained on the CIFAR-10 dataset.

Depanshu Sani, Sandeep Mahato, Parichya Sirohi et al.

The availability of well-curated datasets has driven the success of Machine Learning (ML) models. Despite the increased access to earth observation data for agriculture, there is a scarcity of curated, labelled datasets, which limits the potential of its use in training ML models for remote sensing (RS) in agriculture. To this end, we introduce a first-of-its-kind dataset, SICKLE, having time-series images at different spatial resolutions from 3 different satellites, annotated with multiple key cropping parameters for paddy cultivation for the Cauvery Delta region in Tamil Nadu, India. The dataset comprises of 2,398 season-wise samples from 388 unique plots distributed across 4 districts of the Delta. The dataset covers multi-spectral, thermal and microwave data between the time period January 2018-March 2021. The paddy samples are annotated with 4 key cropping parameters, i.e. sowing date, transplanting date, harvesting date and crop yield. This is one of the first studies to consider the growing season (using sowing and harvesting dates) as part of a dataset. We also propose a yield prediction strategy that uses time-series data generated based on the observed growing season and the standard seasonal information obtained from Tamil Nadu Agricultural University for the region. The consequent performance improvement highlights the impact of ML techniques that leverage domain knowledge that are consistent with standard practices followed by farmers in a specific region. We benchmark the dataset on 3 separate tasks, namely crop type, phenology date (sowing, transplanting, harvesting) and yield prediction, and develop an end-to-end framework for predicting key crop parameters in a real-world setting.

Depanshu Sani, Sandeep Mahato, Sourabh Saini et al.

The availability of well-curated datasets has driven the success of Machine Learning (ML) models. Despite greater access to earth observation data in agriculture, there is a scarcity of curated and labelled datasets, which limits the potential of its use in training ML models for remote sensing (RS) in agriculture. To this end, we introduce a first-of-its-kind dataset called SICKLE, which constitutes a time-series of multi-resolution imagery from 3 distinct satellites: Landsat-8, Sentinel-1 and Sentinel-2. Our dataset constitutes multi-spectral, thermal and microwave sensors during January 2018 - March 2021 period. We construct each temporal sequence by considering the cropping practices followed by farmers primarily engaged in paddy cultivation in the Cauvery Delta region of Tamil Nadu, India; and annotate the corresponding imagery with key cropping parameters at multiple resolutions (i.e. 3m, 10m and 30m). Our dataset comprises 2,370 season-wise samples from 388 unique plots, having an average size of 0.38 acres, for classifying 21 crop types across 4 districts in the Delta, which amounts to approximately 209,000 satellite images. Out of the 2,370 samples, 351 paddy samples from 145 plots are annotated with multiple crop parameters; such as the variety of paddy, its growing season and productivity in terms of per-acre yields. Ours is also one among the first studies that consider the growing season activities pertinent to crop phenology (spans sowing, transplanting and harvesting dates) as parameters of interest. We benchmark SICKLE on three tasks: crop type, crop phenology (sowing, transplanting, harvesting), and yield prediction

Atharv Goel, Sharat Agarwal, Saket Anand et al.

Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts. In practice, annotators make mistakes, rare categories are ambiguous, and conventional AL heuristics (uncertainty, diversity) often amplify such errors by repeatedly selecting mislabeled or redundant samples. We propose Reliable Active Learning via Neural Collapse Geometry (NCAL-R), a framework that leverages the emergent geometric regularities of deep networks to counteract unreliable supervision. Our method introduces two complementary signals: (i) a Class-Mean Alignment Perturbation score, which quantifies how candidate samples structurally stabilize or distort inter-class geometry, and (ii) a Feature Fluctuation score, which captures temporal instability of representations across training checkpoints. By combining these signals, NCAL-R prioritizes samples that both preserve class separation and highlight ambiguous regions, mitigating the effect of noisy or redundant labels. Experiments on ImageNet-100 and CIFAR100 show that NCAL-R consistently outperforms standard AL baselines, achieving higher accuracy with fewer labels, improved robustness under synthetic label noise, and stronger generalization to out-of-distribution data. These results suggest that incorporating geometric reliability criteria into acquisition decisions can make Active Learning less brittle to annotation errors and distribution shifts, a key step toward trustworthy deployment in real-world labeling pipelines. Our code is available at https://github.com/Vision-IIITD/NCAL.

Ashima Garg, Shaurya Bagga, Yashvardhan Singh et al.

Semi-supervised learning approaches have emerged as an active area of research to combat the challenge of obtaining large amounts of annotated data. Towards the goal of improving the performance of semi-supervised learning methods, we propose a novel framework, HIERMATCH, a semi-supervised approach that leverages hierarchical information to reduce labeling costs and performs as well as a vanilla semi-supervised learning method. Hierarchical information is often available as prior knowledge in the form of coarse labels (e.g., woodpeckers) for images with fine-grained labels (e.g., downy woodpeckers or golden-fronted woodpeckers). However, the use of supervision using coarse category labels to improve semi-supervised techniques has not been explored. In the absence of fine-grained labels, HIERMATCH exploits the label hierarchy and uses coarse class labels as a weak supervisory signal. Additionally, HIERMATCH is a generic-approach to improve any semisupervised learning framework, we demonstrate this using our results on recent state-of-the-art techniques MixMatch and FixMatch. We evaluate the efficacy of HIERMATCH on two benchmark datasets, namely CIFAR-100 and NABirds. HIERMATCH can reduce the usage of fine-grained labels by 50% on CIFAR-100 with only a marginal drop of 0.59% in top-1 accuracy as compared to MixMatch. Code: https://github.com/07Agarg/HIERMATCH

Sharat Agarwal, Himanshu Arora, Saket Anand et al.

Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation budget, allow to select a subset of data that yields maximum accuracy upon fine tuning. State of the art AL approaches typically rely on measures of visual diversity or prediction uncertainty, which are unable to effectively capture the variations in spatial context. On the other hand, modern CNN architectures make heavy use of spatial context for achieving highly accurate predictions. Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field. Exploiting this observation, we use the proposed CD measure within two AL frameworks: (1) a core-set based strategy and (2) a reinforcement learning based policy, for active frame selection. Our extensive empirical evaluation establish state of the art results for active learning on benchmark datasets of Semantic Segmentation, Object Detection and Image Classification. Our ablation studies show clear advantages of using contextual diversity for active learning. The source code and additional results are available at https://github.com/sharat29ag/CDAL.

Depanshu Sani, Mehar Khurana, Saket Anand

Animal Re-ID has recently gained substantial attention in the AI research community due to its high impact on biodiversity monitoring and unique research challenges arising from environmental factors. The subtle distinguishing patterns, handling new species and the inherent open-set nature make the problem even harder. To address these complexities, foundation models trained on labeled, large-scale and multi-species animal Re-ID datasets have recently been introduced to enable zero-shot Re-ID. However, our benchmarking reveals significant gaps in their zero-shot Re-ID performance for both known and unknown species. While this highlights the need for collecting labeled data in new domains, exhaustive annotation for Re-ID is laborious and requires domain expertise. Our analyses show that existing unsupervised (USL) and AL Re-ID methods underperform for animal Re-ID. To address these limitations, we introduce a novel AL Re-ID framework that leverages complementary clustering methods to uncover and target structurally ambiguous regions in the embedding space for mining pairs of samples that are both informative and broadly representative. Oracle feedback on these pairs, in the form of must-link and cannot-link constraints, facilitates a simple annotation interface, which naturally integrates with existing USL methods through our proposed constrained clustering refinement algorithm. Through extensive experiments, we demonstrate that, by utilizing only 0.033% of all annotations, our approach consistently outperforms existing foundational, USL and AL baselines. Specifically, we report an average improvement of 10.49%, 11.19% and 3.99% (mAP) on 13 wildlife datasets over foundational, USL and AL methods, respectively, while attaining state-of-the-art performance on each dataset. Furthermore, we also show an improvement of 11.09%, 8.2% and 2.06% for unknown individuals in an open-world setting.

Depanshu Sani, Sandeep Mahato, Parichya Sirohi et al.

The integration of the modern Machine Learning (ML) models into remote sensing and agriculture has expanded the scope of the application of satellite images in the agriculture domain. In this paper, we present how the accuracy of crop type identification improves as we move from medium-spatiotemporal-resolution (MSTR) to high-spatiotemporal-resolution (HSTR) satellite images. We further demonstrate that high spectral resolution in satellite imagery can improve prediction performance for low spatial and temporal resolutions (LSTR) images. The F1-score is increased by 7% when using multispectral data of MSTR images as compared to the best results obtained from HSTR images. Similarly, when crop season based time series of multispectral data is used we observe an increase of 1.2% in the F1-score. The outcome motivates further advancements in the field of synthetic band generation.

Akshit Jindal, Saket Anand, Chetan Arora et al.

Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning rather than training from scratch. This semi-honest setting creates a security risk where a malicious provider can follow the prompt-tuning protocol yet implant a backdoor, forcing triggered inputs to be classified into an attacker-chosen class, even for out-of-distribution (OOD) data. Such backdoors leave encoders untouched, making them undetectable to existing methods that focus on encoder corruption. Other data-level methods that sanitize data before training or during inference, also fail to answer the critical question, "Is the delivered model backdoored or not?" To address this model-level verification problem, we introduce CLIP-Inspector (CI), a backdoor detection method designed for prompt-tuned CLIP models. Assuming white-box access to the delivered model and a pool of unlabeled OOD images, CI reconstructs possible triggers for each class to determine if the model exhibits backdoor behaviour or not. Additionally, we demonstrate that using CI's reconstructed trigger for fine-tuning on correctly labeled triggered inputs enables us to re-align the model and reduce backdoor effectiveness. Through extensive experiments across ten datasets and four backdoor attacks, we demonstrate that CI can reconstruct effective triggers in a single epoch using only 1,000 OOD images, achieving a 94% detection accuracy (47/50 models). Compared to adapted trigger-inversion baselines, CI yields a markedly higher AUROC score (0.973 vs 0.495/0.687), thus enabling the vetting and post-hoc repair of prompt-tuned CLIP models to ensure safe deployment.

Depanshu Sani, Saket Anand

The growing demand for robust scene understanding in mobile robotics and autonomous driving has highlighted the importance of integrating multiple sensing modalities. By combining data from diverse sensors like cameras and LIDARs, fusion techniques can overcome the limitations of individual sensors, enabling a more complete and accurate perception of the environment. We introduce a novel approach to multi-modal sensor fusion, focusing on developing a graph-based state representation that supports critical decision-making processes in autonomous driving. We present a Sensor-Agnostic Graph-Aware Kalman Filter [3], the first online state estimation technique designed to fuse multi-modal graphs derived from noisy multi-sensor data. The estimated graph-based state representations serve as a foundation for advanced applications like Multi-Object Tracking (MOT), offering a comprehensive framework for enhancing the situational awareness and safety of autonomous systems. We validate the effectiveness of our proposed framework through extensive experiments conducted on both synthetic and real-world driving datasets (nuScenes). Our results showcase an improvement in MOTA and a reduction in estimated position errors (MOTP) and identity switches (IDS) for tracked objects using the SAGA-KF. Furthermore, we highlight the capability of such a framework to develop methods that can leverage heterogeneous information (like semantic objects and geometric structures) from various sensing modalities, enabling a more holistic approach to scene understanding and enhancing the safety and effectiveness of autonomous systems.

Depanshu Sani, Saket Anand

Hierarchy-aware representations ensure that the semantically closer classes are mapped closer in the feature space, thereby reducing the severity of mistakes while enabling consistent coarse-level class predictions. Towards this end, we propose a novel framework, Hierarchical Composition of Orthogonal Subspaces (Hier-COS), which learns to map deep feature embeddings into a vector space that is, by design, consistent with the structure of a given taxonomy tree. Our approach augments neural network backbones with a simple transformation module that maps learned discriminative features to subspaces defined using a fixed orthogonal frame. This construction naturally improves the severity of mistakes and promotes hierarchical consistency. Furthermore, we highlight the fundamental limitations of existing hierarchical evaluation metrics popularly used by the vision community and introduce a preference-based metric, Hierarchically Ordered Preference Score (HOPS), to overcome these limitations. We benchmark our method on multiple large and challenging datasets having deep label hierarchies (ranging from 3 - 12 levels) and compare with several baselines and SOTA. Through extensive experiments, we demonstrate that Hier-COS achieves state-of-the-art hierarchical performance across all the datasets while simultaneously beating top-1 accuracy in all but one case. We also demonstrate the performance of a Vision Transformer (ViT) backbone and show that learning a transformation module alone can map the learned features from a pre-trained ViT to Hier-COS and yield substantial performance benefits.

Shivangi Agarwal, Sanjit K. Kaul, Saket Anand et al.

We propose a novel deep neural network (DNN) based approximation architecture to learn estimates of measurements. We detail an algorithm that enables training of the DNN. The DNN estimator only uses measurements, if and when they are received over a communication network. The measurements are communicated over a network as packets, at a rate unknown to the estimator. Packets may suffer drops and need retransmission. They may suffer waiting delays as they traverse a network path. Works on estimation often assume knowledge of the dynamic model of the measured system, which may not be available in practice. The DNN estimator doesn't assume knowledge of the dynamic system model or the communication network. It doesn't require a history of measurements, often used by other works. The DNN estimator results in significantly smaller average estimation error than the commonly used Time-varying Kalman Filter and the Unscented Kalman Filter, in simulations of linear and nonlinear dynamic systems. The DNN need not be trained separately for different communications network settings. It is robust to errors in estimation of network delays that occur due to imperfect time synchronization between the measurement source and the estimator. Last but not the least, our simulations shed light on the rate of updates that result in low estimation error.

Sharat Agarwal, Sumanyu Muku, Saket Anand et al.

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios in the real world. For example, in COCO, many object categories have a much higher co-occurrence with men compared to women, which can bias a DNN's prediction in favor of men. Recent works have focused on task-specific training strategies to handle bias in such scenarios, but fixing the available data is often ignored. In this paper, we propose a novel and more generic solution to address the contextual bias in the datasets by selecting a subset of the samples, which is fair in terms of the co-occurrence with various classes for a protected attribute. We introduce a data repair algorithm using the coefficient of variation, which can curate fair and contextually balanced data for a protected class(es). This helps in training a fair model irrespective of the task, architecture or training methodology. Our proposed solution is simple, effective, and can even be used in an active learning setting where the data labels are not present or being generated incrementally. We demonstrate the effectiveness of our algorithm for the task of object detection and multi-label image classification across different datasets. Through a series of experiments, we validate that curating contextually fair data helps make model predictions fair by balancing the true positive rate for the protected class across groups without compromising on the model's overall performance.

Nikita Mehrotra, Navdha Agarwal, Piyush Gupta et al.

Code clones are duplicate code fragments that share (nearly) similar syntax or semantics. Code clone detection plays an important role in software maintenance, code refactoring, and reuse. A substantial amount of research has been conducted in the past to detect clones. A majority of these approaches use lexical and syntactic information to detect clones. However, only a few of them target semantic clones. Recently, motivated by the success of deep learning models in other fields, including natural language processing and computer vision, researchers have attempted to adopt deep learning techniques to detect code clones. These approaches use lexical information (tokens) and(or) syntactic structures like abstract syntax trees (ASTs) to detect code clones. However, they do not make sufficient use of the available structural and semantic information hence, limiting their capabilities. This paper addresses the problem of semantic code clone detection using program dependency graphs and geometric neural networks, leveraging the structured syntactic and semantic information. We have developed a prototype tool HOLMES, based on our novel approach, and empirically evaluated it on popular code clone benchmarks. Our results show that HOLMES performs considerably better than the other state-of-the-art tool, TBCCD. We also evaluated HOLMES on unseen projects and performed cross dataset experiments to assess the generalizability of HOLMES. Our results affirm that HOLMES outperforms TBCCD since most of the pairs that HOLMES detected were either undetected or suboptimally reported by TBCCD.

Lokender Tiwari, Anish Madan, Saket Anand et al.

Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraining or fine-tuning the model to achieve reasonable performance. In this work, our investigations of intermediate representations of a pre-trained DNN lead to an interesting discovery pointing to intrinsic robustness to adversarial attacks. We find that we can learn a generative classifier by statistically characterizing the neural response of an intermediate layer to clean training samples. The predictions of multiple such intermediate-layer based classifiers, when aggregated, show unexpected robustness to adversarial attacks. Specifically, we devise an ensemble of these generative classifiers that rank-aggregates their predictions via a Borda count-based consensus. Our proposed approach uses a subset of the clean training data and a pre-trained model, and yet is agnostic to network architectures or the adversarial attack generation method. We show extensive experiments to establish that our defense strategy achieves state-of-the-art performance on the ImageNet validation set.

Lokender Tiwari, Saket Anand

Robust multiple model fitting plays a crucial role in many computer vision applications. Unlike single model fitting problems, the multi-model fitting has additional challenges. The unknown number of models and the inlier noise scale are the two most important of them, which are in general provided by the user using ground-truth or some other auxiliary information. Mode seeking/ clustering-based approaches crucially depend on the quality of model hypotheses generated. While preference analysis based guided sampling approaches have shown remarkable performance, they operate in a time budget framework, and the user provides the time as a reasonable guess. In this paper, we deviate from the mode seeking and time budget framework. We propose a concept called Kernel Residual Density (KRD) and apply it to various components of a multiple-model fitting pipeline. The Kernel Residual Density act as a key differentiator between inliers and outliers. We use KRD to guide and automatically stop the sampling process. The sampling process stops after generating a set of hypotheses that can explain all the data points. An explanation score is maintained for each data point, which is updated on-the-fly. We propose two model selection algorithms, an optimal quadratic program based, and a greedy. Unlike mode seeking approaches, our model selection algorithms seek to find one representative hypothesis for each genuine structure present in the data. We evaluate our method (dubbed as DGSAC) on a wide variety of tasks like planar segmentation, motion segmentation, vanishing point estimation, plane fitting to 3D point cloud, line, and circle fitting, which shows the effectiveness of our method and its unified nature.

Ankita Shukla, Pavan Turaga, Saket Anand

Input transformation based defense strategies fall short in defending against strong adversarial attacks. Some successful defenses adopt approaches that either increase the randomness within the applied transformations, or make the defense computationally intensive, making it substantially more challenging for the attacker. However, it limits the applicability of such defenses as a pre-processing step, similar to computationally heavy approaches that use retraining and network modifications to achieve robustness to perturbations. In this work, we propose a defense strategy that applies random image corruptions to the input image alone, constructs a self-correlation based subspace followed by a projection operation to suppress the adversarial perturbation. Due to its simplicity, the proposed defense is computationally efficient as compared to the state-of-the-art, and yet can withstand huge perturbations. Further, we develop proximity relationships between the projection operator of a clean image and of its adversarially perturbed version, via bounds relating geodesic distance on the Grassmannian to matrix Frobenius norms. We empirically show that our strategy is complementary to other weak defenses like JPEG compression and can be seamlessly integrated with them to create a stronger defense. We present extensive experiments on the ImageNet dataset across four different models namely InceptionV3, ResNet50, VGG16 and MobileNet models with perturbation magnitude set to ε = 16. Unlike state-of-the-art approaches, even without any retraining, the proposed strategy achieves an absolute improvement of ~ 4.5% in defense accuracy on ImageNet.

Gullal Singh Cheema, Saket Anand

Visual animal biometrics is rapidly gaining popularity as it enables a non-invasive and cost-effective approach for wildlife monitoring applications. Widespread usage of camera traps has led to large volumes of collected images, making manual processing of visual content hard to manage. In this work, we develop a framework for automatic detection and recognition of individuals in different patterned species like tigers, zebras and jaguars. Most existing systems primarily rely on manual input for localizing the animal, which does not scale well to large datasets. In order to automate the detection process while retaining robustness to blur, partial occlusion, illumination and pose variations, we use the recently proposed Faster-RCNN object detection framework to efficiently detect animals in images. We further extract features from AlexNet of the animal's flank and train a logistic regression (or Linear SVM) classifier to recognize the individuals. We primarily test and evaluate our framework on a camera trap tiger image dataset that contains images that vary in overall image quality, animal pose, scale and lighting. We also evaluate our recognition system on zebra and jaguar images to show generalization to other patterned species. Our framework gives perfect detection results in camera trapped tiger images and a similar or better individual recognition performance when compared with state-of-the-art recognition techniques.

Lokender Tiwari, Pan Ji, Quoc-Huy Tran et al.

Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely disjoint approaches towards building a 3D map of the surrounding environment. In this paper, we demonstrate that the coupling of these two by leveraging the strengths of each mitigates the other's shortcomings. Specifically, we propose a joint narrow and wide baseline based self-improving framework, where on the one hand the CNN-predicted depth is leveraged to perform pseudo RGB-D feature-based SLAM, leading to better accuracy and robustness than the monocular RGB SLAM baseline. On the other hand, the bundle-adjusted 3D scene structures and camera poses from the more principled geometric SLAM are injected back into the depth network through novel wide baseline losses proposed for improving the depth prediction network, which then continues to contribute towards better pose and 3D structure estimation in the next iteration. We emphasize that our framework only requires unlabeled monocular videos in both training and inference stages, and yet is able to outperform state-of-the-art self-supervised monocular and stereo depth prediction networks (e.g, Monodepth2) and feature-based monocular SLAM system (i.e, ORB-SLAM). Extensive experiments on KITTI and TUM RGB-D datasets verify the superiority of our self-improving geometry-CNN framework.

Anil Sharma, Saket Anand, Sanjit K. Kaul

Surveillance camera networks are a useful infrastructure for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across the network. Most multi-camera tracking works focus on target re-identification and trajectory association problems to track the target. However, since camera networks can generate enormous amount of video data, inefficient schemes for making re-identification or trajectory association queries can incur prohibitively large computational requirements. In this paper, we address the problem of intelligent scheduling of re-identification queries in a multi-camera tracking setting. To this end, we formulate the target tracking problem in a camera network as an MDP and learn a reinforcement learning based policy that selects a camera for making a re-identification query. The proposed approach to camera selection does not assume the knowledge of the camera network topology but the resulting policy implicitly learns it. We have also shown that such a policy can be learnt directly from data. Using the NLPR MCT and the Duke MTMC multi-camera multi-target tracking benchmarks, we empirically show that the proposed approach substantially reduces the number of frames queried.

Ankita Shukla, Sarthak Bhagat, Shagun Uppal et al.

Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation. Various learning frameworks such as VAEs, GANs and auto-encoders have been used in the literature to learn such representations. Most often, the latent space is constrained to a partitioned representation or structured by a prior to impose disentangling. In this work, we advance the use of a latent representation based on a product space of Orthogonal Spheres PrOSe. The PrOSe model is motivated by the reasoning that latent-variables related to the physics of image-formation can under certain relaxed assumptions lead to spherical-spaces. Orthogonality between the spheres is motivated via physical independence models. Imposing the orthogonal-sphere constraint is much simpler than other complicated physical models, is fairly general and flexible, and extensible beyond the factors used to motivate its development. Under further relaxed assumptions of equal-sized latent blocks per factor, the constraint can be written down in closed form as an ortho-normality term in the loss function. We show that our approach improves the quality of disentanglement significantly. We find consistent improvement in disentanglement compared to several state-of-the-art approaches, across several benchmarks and metrics.

Ankita Shukla, Gullal Singh Cheema, Saket Anand et al.

Ecological imbalance owing to rapid urbanization and deforestation has adversely affected the population of several wild animals. This loss of habitat has skewed the population of several non-human primate species like chimpanzees and macaques and has constrained them to co-exist in close proximity of human settlements, often leading to human-wildlife conflicts while competing for resources. For effective wildlife conservation and conflict management, regular monitoring of population and of conflicted regions is necessary. However, existing approaches like field visits for data collection and manual analysis by experts is resource intensive, tedious and time consuming, thus necessitating an automated, non-invasive, more efficient alternative like image based facial recognition. The challenge in individual identification arises due to unrelated factors like pose, lighting variations and occlusions due to the uncontrolled environments, that is further exacerbated by limited training data. Inspired by human perception, we propose to learn representations that are robust to such nuisance factors and capture the notion of similarity over the individual identity sub-manifolds. The proposed approach, Primate Face Identification (PFID), achieves this by training the network to distinguish between positive and negative pairs of images. The PFID loss augments the standard cross entropy loss with a pairwise loss to learn more discriminative and generalizable features, thus making it appropriate for other related identification tasks like open-set, closed set and verification. We report state-of-the-art accuracy on facial recognition of two primate species, rhesus macaques and chimpanzees under the four protocols of classification, verification, closed-set identification and open-set recognition.

Ankita Shukla, Shagun Uppal, Sarthak Bhagat et al.

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these latent spaces has been studied under the lens of Riemannian geometry; via analysis of the non-linearity of the generator function. In new developments, deep generative models have been used for learning semantically meaningful `disentangled' representations; that capture task relevant attributes while being invariant to other attributes. In this work, we explore the geometry of popular generative models for disentangled representation learning. We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space. The results we obtain establish that the class distinguishable features in the disentangled latent space exhibits higher curvature as opposed to a variational autoencoder. We evaluate and compare the geometry of three such models with variational autoencoder on two different datasets. Further, our results show that distances and interpolation in the latent space are significantly improved with Riemannian metrics derived from the curvature of the space. We expect these results will have implications on understanding how deep-networks can be made more robust, generalizable, as well as interpretable.

Ankita Shukla, Gullal Singh Cheema, Saket Anand et al.

Despite loss of natural habitat due to development and urbanization, certain species like the Rhesus macaque have adapted well to the urban environment. With abundant food and no predators, macaque populations have increased substantially in urban areas, leading to frequent conflicts with humans. Overpopulated areas often witness macaques raiding crops, feeding on bird and snake eggs as well as destruction of nests, thus adversely affecting other species in the ecosystem. In order to mitigate these adverse effects, sterilization has emerged as a humane and effective way of population control of macaques. As sterilization requires physical capture of individuals or groups, their unique identification is integral to such control measures. In this work, we propose the Macaque Face Identification (MFID), an image based, non-invasive tool that relies on macaque facial recognition to identify individuals, and can be used to verify if they are sterilized. Our primary contribution is a robust facial recognition and verification module designed for Rhesus macaques, but extensible to other non-human primate species. We evaluate the performance of MFID on a dataset of 93 monkeys under closed set, open set and verification evaluation protocols. Finally, we also report state of the art results when evaluating our proposed model on endangered primate species.

Anil Sharma, Prabhat Kumar, Saket Anand et al.

Target tracking in a camera network is an important task for surveillance and scene understanding. The task is challenging due to disjoint views and illumination variation in different cameras. In this direction, many graph-based methods were proposed using appearance-based features. However, the appearance information fades with high illumination variation in the different camera FOVs. We, in this paper, use spatial and temporal information as the state of the target to learn a policy that predicts the next camera given the current state. The policy is trained using Q-learning and it does not assume any information about the topology of the camera network. We will show that the policy learns the camera network topology. We demonstrate the performance of the proposed method on the NLPR MCT dataset.

Mayank K. Pal, Rupali Bhati, Anil Sharma et al.

Our premise is that autonomous vehicles must optimize communications and motion planning jointly. Specifically, a vehicle must adapt its motion plan staying cognizant of communications rate related constraints and adapt the use of communications while being cognizant of motion planning related restrictions that may be imposed by the on-road environment. To this end, we formulate a reinforcement learning problem wherein an autonomous vehicle jointly chooses (a) a motion planning action that executes on-road and (b) a communications action of querying sensed information from the infrastructure. The goal is to optimize the driving utility of the autonomous vehicle. We apply the Q-learning algorithm to make the vehicle learn the optimal policy, which makes the optimal choice of planning and communications actions at any given time. We demonstrate the ability of the optimal policy to smartly adapt communications and planning actions, while achieving large driving utilities, using simulations.

Ankita Shukla, Gullal Singh Cheema, Saket Anand

Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on large set of labeled data samples. In this paper, we propose ClusterNet that uses pairwise semantic constraints from very few labeled data samples (<5% of total data) and exploits the abundant unlabeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. The proposed network uses convolution autoencoder to learn a latent representation that groups data into k specified clusters, while also learning the cluster centers simultaneously. We evaluate and compare the performance of ClusterNet on several datasets and state of the art deep clustering approaches.

Aditay Tripathi, Aanchan Mohan, Saket Anand et al.

Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of labeled data is necessary, which are often expensive to obtain. This paper explores the application of adversarial training to learn features from raw speech that are invariant to acoustic variability. This acoustic variability is referred to as a domain shift in this paper. The experimental study presented in this paper leverages the architecture of Domain Adversarial Neural Networks (DANNs) [1] which uses data from two different domains. The DANN is a Y-shaped network that consists of a multi-layer CNN feature extractor module that is common to a label (senone) classifier and a so-called domain classifier. The utility of DANNs is evaluated on multiple datasets with domain shifts caused due to differences in gender and speaker accents. Promising empirical results indicate the strength of adversarial training for unsupervised domain adaptation in ASR, thereby emphasizing the ability of DANNs to learn domain invariant features from raw speech.

Ananya Harsh Jha, Saket Anand, Maneesh Singh et al.

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity labels. Inspired by the recent success of cycle-consistent adversarial architectures, we use cycle-consistency in a variational auto-encoder framework. Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations. We show compelling results of disentangled latent subspaces on three datasets and compare with recent works that leverage adversarial training.