CVIT Home CVIT Home
  • Home
  • People
    • Faculty
    • Staff
    • PhD Students
    • MS Students
    • Alumni
    • Post-doctoral
    • Honours Student
  • Research
    • Publications
    • Thesis
    • Projects
    • Resources
  • Events
    • Talks and Visits
    • Major Events
    • Visitors
    • Summer Schools
  • Gallery
  • News & Updates
    • News
    • Blog
    • Newsletter
    • Banners
  • Contact Us
  • Login

Advancing Domain Generalization through Cross-Domain Class-Contrastive Learning and Addressing Data Imbalances


Saransh Dave

Abstract

This thesis delves into the critical field of Domain Generalization (DG) in machine learning, where models are trained on multiple source distributions with the objective of generalizing to unseen tar- get distributions. We begin by dissecting various facets of DG, including distribution shifts, shortcut learning, representation learning, and data imbalances. This foundational investigation sets the stage for understanding the challenges associated with DG and the complexities that arise. A comprehensive literature review is conducted, highlighting existing challenges and contextualizing our contributions to the field. The review encompasses learning invariant features, parameter sharing techniques, meta-learning techniques, and data augmentation approaches. One of the key contributions of this thesis is the examination of the role low-dimensional representa- tions play in enhancing DG performance. We introduce a method to compute the implicit dimensionality of latent representations, exploring its correlation with performance in a domain generalization context. This essential finding motivated us to further investigate the effects of low-dimensional representations. Building on these insights, we present Cross-Domain Class-Contrastive Learning (CDCC), a tech- nique that learns sparse representations in the latent space, resulting in lower-dimensional represen- tations and improved domain generalization performance. CDCC establishes competitive results on various DG benchmarks, comparing favorably with numerous existing approaches in DomainBed. Venturing beyond traditional DG, we discuss a series of experiments conducted for domain general- ization in long-tailed settings, which are common in real-world applications. Additionally, we present supplementary experiments yielding intriguing findings. Our analysis reveals that the CDCC approach exhibits greater robustness in long-tailed distributions and that the order of performances across test do- mains remains unaffected by the order of training domains in the long-tailed setting. This section aims to inspire researchers to further probe the outcomes of these experiments and advance the understanding of domain generalization. In conclusion, this thesis offers a well-rounded exploration of DG by combining a comprehensive literature review, the discovery of the importance of low-dimensional representations in DG, the devel- opment of the CDCC method, and the meticulous analysis of long-tailed settings and other experimental findings.

Year of completion:  October 2023
 Advisor : Vineet Gandhi

Related Publications


    Downloads

    thesis

    Real-Time Video Processing for Dynamic Content Creation


    Sudheer Achary

    Abstract

    Autonomous camera systems are vital in capturing dynamic events and creating engaging videos. However, existing filtering techniques used to stabilize and smoothen camera trajectories often fail to replicate the natural behavior of human camera operators. To address these challenges, our work proposes novel approaches for real-time camera trajectory optimization and gaze-guided video editing. We introduce two online filtering methods: CineConvex and CineCNN. CineConvex utilizes a sliding window-based convex optimization formulation, while CineCNN employs a convolutional neural network as an encoder-decoder model. Both methods are motivated by cinematographic principles, producing smooth and natural camera trajectories. Evaluation of basketball and stage performance datasets demonstrates superior performance over previous methods and baselines, both quantitatively and qualitatively. With a minor latency of half a second, CineConvex operates at approximately 250 frames per second (fps), while CineCNN achieves an impressive speed of 1000 fps, making them highly suitable for real-time applications. In the realm of video editing, we present Real Time GAZED, a real-time adaptation of the GAZED framework. It enables users to create professionally edited videos in real-time. Comparative evaluations against baseline methods, including the non-real-time GAZED, demonstrate that Real Time GAZED achieves similar editing results, ensuring high-quality video output. Furthermore, a user study confirms the aesthetic quality of the video edits produced by Real Time GAZED. With the advancements in real-time camera trajectory optimization and video editing presented, the demand for immediate and dynamic content creation in industries such as live broadcasting, sports coverage, news reporting, and social media content creation can be met more efficiently. The elimination of time-consuming post-production processes and the ability to deliver high-quality videos in today’s fast-paced digital landscape are the key advantages offered by these real-time approaches

    Year of completion:  November 2023
     Advisor : Vineet Gandhi

    Related Publications


      Downloads

      thesis

      Nerve Block Target Localization and Needle Guidance for Autonomous Robotic Ultrasound Guided Regional Anesthesia


      ABHISHEK TYAGI

      Abstract

      Ultrasound guided regional anesthesia (UGRA) involves approaching target nerves through a needle in real-time, enabling precise deposition of drug with increased success rates and fewer complications. Development of autonomous robotic systems capable of administering UGRA is desirable for remote settings and localities where anesthesiologists are unavailable. Real-time segmentation of nerves, needle tip localization and needle trajectory extrapolation are required for developing such a system. In the first part of this thesis, we developed models to localize nerves in the ultrasound domain using a large dataset. Our prospective study enrolled 227 subjects who were systematically scanned for brachial plexus nerves in various settings using three different ultrasound machines to create a dataset of 227 unique videos. In total, 41,000 video frames were annotated by experienced anaesthesiologists using partial automation with object tracking and active contour algorithms. Four baseline neural network models were trained on the dataset and their performance was evaluated for object detection and segmentation tasks. Generalizability of the best suited model was then tested on the datasets constructed from separate ultrasound scanners with and without fine-tuning. The results demonstrate that deep learning models can be leveraged for real time segmentation of brachial plexus in neck ultrasonography videos with high accuracy and reliability. Using these nerve segmentation predictions, we define automated anesthesia needle targets by fitting an ellipse to the nerve contours. The second part of this thesis focuses on localization of the needles and development of a framework to guide the needles toward their targets. For the segmentation of the needle, a natural RGB pre-trained neural network is first fine-tuned on a large ultrasound dataset for domain transfer and then adapted for the needle using a small dataset. The segmented needle’s trajectory angle is calculated using Radon transformation and the trajectory is extrapolated from the needle tip. The intersection of extrapolated trajectory with the needle target guides the needle navigation for drug delivery. The needle trajectory’s average angle error was 2 o , average error in trajectory’s distance from center of the image was 10 pixels (2 mm) and the average error in needle tip was 19 pixels (3.8 mm) which is within acceptable range of 5 mm as per experienced anesthesiologists. The entire dataset has been released publicly for further study by the research community.

      Year of completion:  November 2023
       Advisor : Jayanthi Sivaswamy

      Related Publications


        Downloads

        thesis

        Data exploration, Playing styles, and Gameplay for Cooperative Partially Observable games: Pictionary as a case study


        Kiruthika Kannan

        Abstract

        Cooperative human-human communication becomes challenging when restrictions such as difference in communication modality and limited time are imposed. In this thesis, we present the popular cooperative social game Pictionary as an online multimodal test bed to explore the dynamics of humanhuman interactions in such settings. Pictionary is a multiplayer game where the players attempt to convey a word or phrase through drawing. The restriction imposed on the mode of communication gives rise to intriguing diversity and creativity in the players’ responses. To explore the player activity in Pictionary, an online browser-based Pictionary application is developed and utilized to collect a Pictionary dataset. We conduct an exploratory analysis of the dataset, examining the data across three domains: global session-related statistics, target word-related statistics, and user-related statistics. We also present our interactive dashboard to visualize the analysis results. We identify attributes of player interactions that characterize cooperative gameplay. Using these attributes, we find stable role-specific playing style components independent of game difficulty. In terms of gameplay and the larger context of cooperative partially observable communication, our results suggest that too much interaction or unbalanced interaction negatively impacts game success. Additionally, the playing style components discovered via our analysis align with select player personality types proposed in existing frameworks for multiplayer games. Furthermore, this thesis explores atypical sketch content within the Pictionary dataset. We present various baseline models for detecting such atypical content. We conduct a comparative analysis of three baseline models, namely BiLSTM+CRF, SketchsegNet+, and modified CRAFT. Results indicate that the image segmentation-based deep neural network outperforms recurrent models that rely on stroke features or stroke coordinates as input.

        Year of completion:  November 2023
         Advisor : Ravi Kiran Sarvadevabhatla

        Related Publications


          Downloads

          thesis

          Security from uncertainty: Designing privacy-preserving verification methods using Noise


          Praguna Manvi

          Abstract

          Biometric authentication plays an increasingly prominent role in today’s products and services for verifying an individual’s identity. It is not only efficient but also practical, as it establishes a unique link to an individual through their physical and behavioral characteristics [43]. Unlike conventional authentication mechanisms like passwords or documents, biometric traits are inherent to each individual, eliminating the need to memorize additional information [64]. However, the security and privacy of biometric templates used in authentication remain primary concerns, as biometric data is strongly and irrevocably tied to an individual, as emphasized in the article [42]. In the context of remote authentication, Secure Multiparty Computation (SMC) offers a powerful solution. SMC enables two parties to interactively compute a function using their private inputs without disclosing any information except for the output itself [19]. This approach ensures that biometric template comparison is carried out in a privacy-preserving manner, enhancing both security and privacy in authentication services. In this thesis, we introduce a unique approach to iris, fingerprint, and face verification by incorporating ”noise” into the authentication process. In our work,“noise” refers to signals obtained from non-discriminatory or unreliable regions of biometric characteristics. Our extensive empirical evaluation reveals a correlation among noise features, and we leverage this correlation in a novel Secure Two-Party Computation (STPC) design. This STPC design operates on quantified uncertainty between noise features, providing informationtheoretic security. Our approach has low accuracy degradations, practical computational complexity, wide applicability making it suitable for practical real-time applications.

          Year of completion:  December 2023
           Advisor : Anoop M Namboodiri

          Related Publications


            Downloads

            thesis

            More Articles …

            1. Towards Enhancing Semantic Segmentation in Resource Constrained Settings
            2. High-Quality 3D Fingerprint Generation: Merging Skin Optics, Machine Learning and 3D Reconstruction Techniques
            3. A Holistic Framework for Multimodal Ecosystem of Pictionary
            4. Deploying Multi Camera Multi Player Detection and Tracking Systems in Top View
            • Start
            • Prev
            • 3
            • 4
            • 5
            • 6
            • 7
            • 8
            • 9
            • 10
            • 11
            • 12
            • Next
            • End
            1. You are here:  
            2. Home
            3. Research
            4. Thesis
            5. Thesis Students
            Bootstrap is a front-end framework of Twitter, Inc. Code licensed under MIT License. Font Awesome font licensed under SIL OFL 1.1.