Sarthak Bhagat

Sarthak Bhagat, Simon Stepputtis, Joseph Campbell et al.

Despite the advances made in visual object recognition, state-of-the-art deep learning models struggle to effectively recognize novel objects in a few-shot setting where only a limited number of examples are provided. Unlike humans who excel at such tasks, these models often fail to leverage known relationships between entities in order to draw conclusions about such objects. In this work, we show that incorporating a symbolic knowledge graph into a state-of-the-art recognition model enables a new approach for effective few-shot classification. In our proposed neuro-symbolic architecture and training methodology, the knowledge graph is augmented with additional relationships extracted from a small set of examples, improving its ability to recognize novel objects by considering the presence of interconnected entities. Unlike existing few-shot classifiers, we show that this enables our model to incorporate not only objects but also abstract concepts and affordances. The existence of the knowledge graph also makes this approach amenable to interpretability through analysis of the relationships contained within it. We empirically show that our approach outperforms current state-of-the-art few-shot multi-label classification methods on the COCO dataset and evaluate the addition of abstract concepts and affordances on the Visual Genome dataset.

Sahil Goyal, Shagun Uppal, Sarthak Bhagat et al.

Several works have developed end-to-end pipelines for generating lip-synced talking faces with various real-world applications, such as teaching and language translation in videos. However, these prior works fail to create realistic-looking videos since they focus little on people's expressions and emotions. Moreover, these methods' effectiveness largely depends on the faces in the training dataset, which means they may not perform well on unseen faces. To mitigate this, we build a talking face generation framework conditioned on a categorical emotion to generate videos with appropriate expressions, making them more realistic and convincing. With a broad range of six emotions, i.e., \emph{happiness}, \emph{sadness}, \emph{fear}, \emph{anger}, \emph{disgust}, and \emph{neutral}, we show that our model can adapt to arbitrary identities, emotions, and languages. Our proposed framework is equipped with a user-friendly web interface with a real-time experience for talking face generation with emotions. We also conduct a user study for subjective evaluation of our interface's usability, design, and functionality. Project page: https://midas.iiitd.edu.in/emo/

Devansh Gupta, Aditya Saini, Drishti Bhasin et al.

Retrieving facial images from attributes plays a vital role in various systems such as face recognition and suspect identification. Compared to other image retrieval tasks, facial image retrieval is more challenging due to the high subjectivity involved in describing a person's facial features. Existing methods do so by comparing specific characteristics from the user's mental image against the suggested images via high-level supervision such as using natural language. In contrast, we propose a method that uses a relatively simpler form of binary supervision by utilizing the user's feedback to label images as either similar or dissimilar to the target image. Such supervision enables us to exploit the contrastive learning paradigm for encapsulating each user's personalized notion of similarity. For this, we propose a novel loss function optimized online via user feedback. We validate the efficacy of our proposed approach using a carefully designed testbed to simulate user feedback and a large-scale user study. Our experiments demonstrate that our method iteratively improves personalization, leading to faster convergence and enhanced recommendation relevance, thereby, improving user satisfaction. Our proposed framework is also equipped with a user-friendly web interface with a real-time experience for facial image retrieval.

Sarthak Bhagat, Simon Stepputtis, Joseph Campbell et al.

This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives. To this end, we imbue a transformer network with a symbolic knowledge graph for action anticipation in video segments by boosting certain aspects of the transformer's attention mechanism at run-time. Demonstrated on two benchmark datasets, Breakfast and 50Salads, our approach outperforms current state-of-the-art methods for long-term action anticipation using short video context by up to 9%.

Samuel Li, Sarthak Bhagat, Joseph Campbell et al.

Task-oriented grasping of unfamiliar objects is a necessary skill for robots in dynamic in-home environments. Inspired by the human capability to grasp such objects through intuition about their shape and structure, we present a novel zero-shot task-oriented grasping method leveraging a geometric decomposition of the target object into simple, convex shapes that we represent in a graph structure, including geometric attributes and spatial relationships. Our approach employs minimal essential information - the object's name and the intended task - to facilitate zero-shot task-oriented grasping. We utilize the commonsense reasoning capabilities of large language models to dynamically assign semantic meaning to each decomposed part and subsequently reason over the utility of each part for the intended task. Through extensive experiments on a real-world robotics platform, we demonstrate that our grasping approach's decomposition and reasoning pipeline is capable of selecting the correct part in 92% of the cases and successfully grasping the object in 82% of the tasks we evaluate. Additional videos, experiments, code, and data are available on our project website: https://shapegrasp.github.io/.

Dvij Kalaria, Shreya Sharma, Sarthak Bhagat et al.

Off-road navigation is a challenging problem both at the planning level to get a smooth trajectory and at the control level to avoid flipping over, hitting obstacles, or getting stuck at a rough patch. There have been several recent works using classical approaches involving depth map prediction followed by smooth trajectory planning and using a controller to track it. We design an end-to-end reinforcement learning (RL) system for an autonomous vehicle in off-road environments using a custom-designed simulator in the Unity game engine. We warm-start the agent by imitating a rule-based controller and utilize Proximal Policy Optimization (PPO) to improve the policy based on a reward that incorporates Control Barrier Functions (CBF), facilitating the agent's ability to generalize effectively to real-world scenarios. The training involves agents concurrently undergoing domain-randomized trials in various environments. We also propose a novel simulation environment to replicate off-road driving scenarios and deploy our proposed approach on a real buggy RC car. Videos and additional results: https://sites.google.com/view/wroom-utd/home

Dvij Kalaria, Sudarshan S Harithas, Pushkal Katara et al.

We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior trained on human motion data, which subsequently guides an RL policy in simulation to complete specific tasks of interest (e.g., opening a drawer or picking up an object). We demonstrate that this human motion-informed prior allows RL to discover solutions unattainable by direct RL, and that diffusion models inherently promote natural looking motions, aiding in sim-to-real transfer. We validate DreamControl's effectiveness on a Unitree G1 robot across a diverse set of challenging tasks involving simultaneous lower and upper body control and object interaction. Project website at https://genrobo.github.io/DreamControl/

FNU Aryan, Simon Stepputtis, Sarthak Bhagat et al.

Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches.

Sarthak Bhagat, P. B. Sujit

Target tracking in unknown real-world environments in the presence of obstacles and target motion uncertainty demand agents to develop an intrinsic understanding of the environment in order to predict the suitable actions to be taken at each time step. This task requires the agents to maximize the visibility of the mobile target maneuvering randomly in a network of roads by learning a policy that takes into consideration the various aspects of a real-world environment. In this paper, we propose a DDQN-based extension to the state-of-the-art in target tracking using a UAV TF-DQN, that we call TF-DDQN, that isolates the value estimation and evaluation steps. Additionally, in order to carefully benchmark the performance of any given target tracking algorithm, we introduce a novel target tracking evaluation scheme that quantifies its efficacy in terms of a wide set of diverse parameters. To replicate the real-world setting, we test our approach against standard baselines for the task of target tracking in complex environments with varying drift conditions and changes in environmental configuration.

Shagun Uppal, Sarthak Bhagat, Devamanyu Hazarika et al.

Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data. More recently, this has enhanced research interests in the intersection of the Vision and Language arena with its numerous applications and fast-paced growth. In this paper, we present a detailed overview of the latest trends in research pertaining to visual and language modalities. We look at its applications in their task formulations and how to solve various problems related to semantic perception and content generation. We also address task-specific trends, along with their evaluation strategies and upcoming challenges. Moreover, we shed some light on multi-disciplinary patterns and insights that have emerged in the recent past, directing this field towards more modular and transparent intelligent systems. This survey identifies key trends gravitating recent literature in VisLang research and attempts to unearth directions that the field is heading towards.

Sarthak Bhagat, Sujit PB

Persistent target tracking in urban environments using UAV is a difficult task due to the limited field of view, visibility obstruction from obstacles and uncertain target motion. The vehicle needs to plan intelligently in 3D such that the target visibility is maximized. In this paper, we introduce Target Following DQN (TF-DQN), a deep reinforcement learning technique based on Deep Q-Networks with a curriculum training framework for the UAV to persistently track the target in the presence of obstacles and target motion uncertainty. The algorithm is evaluated through several simulation experiments qualitatively as well as quantitatively. The results show that the UAV tracks the target persistently in diverse environments while avoiding obstacles on the trained environments as well as on unseen environments.

Sarthak Bhagat, Vishaal Udandarao, Shagun Uppal

Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a self-supervised framework DisCont to disentangle multiple attributes by exploiting the structural inductive biases within images. Motivated by the recent surge in contrastive learning paradigms, our model bridges the gap between self-supervised contrastive learning algorithms and unsupervised disentanglement. We evaluate the efficacy of our approach, both qualitatively and quantitatively, on four benchmark datasets.

Shagun Uppal, Anish Madan, Sarthak Bhagat et al.

Visual Question Generation (VQG) is the task of generating natural questions based on an image. Popular methods in the past have explored image-to-sequence architectures trained with maximum likelihood which have demonstrated meaningful generated questions given an image and its associated ground-truth answer. VQG becomes more challenging if the image contains rich contextual information describing its different semantic categories. In this paper, we try to exploit the different visual cues and concepts in an image to generate questions using a variational autoencoder (VAE) without ground-truth answers. Our approach solves two major shortcomings of existing VQG systems: (i) minimize the level of supervision and (ii) replace generic questions with category relevant generations. Most importantly, by eliminating expensive answer annotations, the required supervision is weakened. Using different categories enables us to exploit different concepts as the inference requires only the image and the category. Mutual information is maximized between the image, question, and answer category in the latent space of our VAE. A novel category consistent cyclic loss is proposed to enable the model to generate consistent predictions with respect to the answer category, reducing redundancies and irregularities. Additionally, we also impose supplementary constraints on the latent space of our generative model to provide structure based on categories and enhance generalization by encapsulating decorrelated features within each dimension. Through extensive experiments, the proposed model, C3VQG outperforms state-of-the-art VQG methods with weak supervision.

Sarthak Bhagat, Shagun Uppal, Zhuyun Yin et al.

We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled representations in video sequences. We improve upon previous work by establishing a framework by which multiple features, static or dynamic, can be disentangled. Specifically we use fractional Brownian motions (fBM) and Brownian bridges (BB) to enforce an inter-frame correlation structure in each independent channel, and show that varying this structure enables one to capture different factors of variation in the data. We demonstrate the quality of our representations with experiments on three publicly available datasets, and also quantify the improvement using a video prediction task. Moreover, we introduce a novel geodesic loss function which takes into account the curvature of the data manifold to improve learning. Our experiments show that the combination of the improved representations with the novel loss function enable MGP-VAE to outperform the baselines in video prediction.

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, 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.