Department of Computer Science and Engineering

Indian Institute of Technology Hyderabad (IITH) is a premier institute of science and technology established in 2008. IITH has been consistently ranked in the&nbsp;<a href="https://iith.ac.in/reports/" rel="noopener noreferrer">top 10 institutes</a>&nbsp;in India for Engineering&nbsp;<a href="https://www.nirfindia.org/2021/EngineeringRanking.html" rel="noopener noreferrer" target="_blank">according to NIRF</a>&nbsp;making it one of the most coveted schools for science and technology in the country.

IITH offers&nbsp;<a href="https://iith.ac.in/academics/under-graduate/">undergraduate programs</a>&nbsp;in all the classical engineering disciplines, applied sciences, design, as well as several modern interdisciplinary areas. Students are given a flexibility to explore a broad set of areas, and potentially pursue a minor or double major in a discipline that is not their own. Students who wish to seek a deeper understanding of their own discipline are strongly encouraged to get involved in cutting-edge research with the help of a faculty to mentor them, and earn an Honors in their own field.

The very foundation of IIT Hyderabad is based on&nbsp;<a href="https://iith.ac.in/research/">research and innovation</a>. The vibrant research culture is evident from the number of patents and publications that IITH produces consistently every year. IITH offers&nbsp;<a href="https://iith.ac.in/academics/programmes-offered/">graduate programs</a>&nbsp;at both a masters, and a doctoral level, in several diverse areas. There are separate programs for technology, design, science, and liberal arts. The&nbsp;<a href="https://iith.ac.in/academics/post-graduate/">MTech program</a>&nbsp;is offered in various modes and durations to cater to the ever-growing need of postgraduate level professionals in the country.

IITH encourages and supports&nbsp;<a href="https://iic-iith.netlify.app/index.html" rel="noopener noreferrer" target="_blank">innovation and entrepreneurship</a>&nbsp;at every stage. The minor program in entrepreneurship is open to all students of IITH, and many of the courses are offered by industrialists who are entrepreneurs themselves. There are various&nbsp;<a href="https://iith.ac.in/research/centres-incubators/">innovation centers and incubators</a>&nbsp;that promote entrepreneurship and help mentor young innovators. IITH has been very successful in building tie-ups with leading academic institutions around the globe.

IITH enjoys a very special relationship with Japanese universities and industries that goes beyond academic and research collaborations. In fact, some of the iconic buildings in IITH campus will carry the signature of Japanese architecture.

IITH creates a unique holistic ecosystem for education that offers interactive learning, a very flexible academic structure, cutting-edge research, strong industry collaboration, and entrepreneurship. This is an environment which enables students and faculty to translate their dreams into realities.

IIT Hyderabad

Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model reuse and distillation, there is a need to also study transfer of interpretability from one model to another. We present Proto2Proto, a novel method to transfer interpretability of one prototypical part network to another via knowledge distillation. Our approach aims to add interpretability to the 'dark' knowledge transferred from the teacher to the shallower student model. We propose two novel losses: 'Global Explanation' loss and 'Patch-Prototype Correspondence' loss to facilitate such a transfer. Global Explanation loss forces the student prototypes to be close to teacher prototypes, and Patch-Prototype Cor-respondence loss enforces the local representations of the student to be similar to that of the teacher. Further, we propose three novel metrics to evaluate the student's proximity to the teacher as measures of interpretability transfer in our settings. We qualitatively and quantitatively demon-strate the effectiveness of our method on CUB-200-2011 and Stanford Cars datasets. Our experiments show that the proposed method indeed achieves interpretability transfer from teacher to student while simultaneously exhibiting competitive performance. The code is available at h t tps: //github.com/archmaester/proto2proto © 2022 IEEE.

World University root node

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Proto2Proto: Can you recognize the car, the way I do?

Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence assumptions, more recently, weak supervision and correlated features have been explored, but without a causal view of the generative process. In contrast, we work under the regime of a causal generative process where generative factors are either independent or can be potentially confounded by a set of observed or unobserved confounders. We present an analysis of disentangled representations through the notion of disentangled causal process. We motivate the need for new metrics and datasets to study causal disentanglement and propose two evaluation metrics and a dataset. We show that our metrics capture the desiderata of disentangled causal process. Finally, we perform an empirical study on state of the art disentangled representation learners using our metrics and dataset to evaluate them from causal perspective. © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

On Causally Disentangled Representations

Aircraft type recognition remains challenging, due to their tiny sizes and geometric distortions in large-scale panchromatic satellite images. This paper proposes a framework for aircraft type recognition by focusing on shape preservation, spatial transformations, and geospatial attributes derivation. First, we construct an aircraft segmentation model to obtain masks representing the shape of aircrafts by employing a learnable shape-preserved and deformable network in the mask RCNN architecture. Then, the orientation of the segmented aircrafts is determined by estimating the symmetrical axes using their gradient information. Besides template matching, we derive the length and width of aircrafts using the geotagged information of images to further categorize the types of aircrafts. Also, we present an effective inferencing mechanism to overcome the issue of partial detection or missing aircrafts in large-scale images. The efficacy of the proposed framework is demonstrated on large-scale panchromatic images with ground sampling distances of 0.65m (C2S). © 2022 SPIE.

Proceedings of SPIE - The International Society for Optical Engineering

A Framework to Derive Geospatial Attributes for Aircraft Type Recognition in Large-Scale Remote Sensing Images

Monitoring airport runways in panchromatic remote sensing images is helpful for both civil and strategic communities in effective utilization of the large-area acquisitions. This paper proposes a novel multimodal semantic segmentation approach for effective delineation of the runways in panchromatic remote sensing images. The proposed approach aims to learn complementary information from two modalities, namely, panchromatic image and digital elevation model (DEM) to obtain discriminative features of the runway. The fusion of image features and the corresponding terrain information is performed by stacking the image and DEM by leveraging the merits of both Transformers and U-Net architecture. We perform the experiments on Cartosat-1 panchromatic satellite images with the corresponding Cartosat-1 DEM scenes. The experimental results demonstrate a significant contribution of terrain information to the segmentation process in achieving the contours of airport runways effectively. © 2022 SPIE.

A Multimodal Semantic Segmentation for Airport Runway Delineation in Panchromatic Remote Sensing Images

Today’s graph-based analytics tasks in domains such as blockchains, social networks, biological networks, and several others demand real-time data updates at high speed. The real-time updates are efficiently ingested if the data structure naturally supports dynamic addition and removal of both edges and vertices. These dynamic updates are best facilitated by concurrency in the underlying data structure. Unfortunately, the existing dynamic graph frameworks broadly refurbish the static processing models using approaches such as versioning and incremental computation. Consequently, they carry their original design traits such as high memory footprint and batch processing that do not honor the real-time changes. At the same time, multi-core processors–a natural setting for concurrent data structures–are now commonplace, and the analytics tasks are moving closer to data sources over lightweight devices. Thus, exploring a fresh design approach for real-time graph analytics is significant. This paper reports a novel concurrent graph data structure that provides breadth-first search, single-source shortest-path, and betweenness centrality with concurrent dynamic updates of both edges and vertices. We evaluate the proposed data structure theoretically – by an amortized analysis – and experimentally via a C++ implementation. The experimental results show that (a) our algorithm outperforms the current state-of-the-art by a throughput speed-up of up to three orders of magnitude in several cases, and (b) it offers up to 80x lighter memory-footprint compared to existing methods. The experiments include several counterparts: Stinger, Ligra and GraphOne. We prove that the presented concurrent algorithms are non-blocking and linearizable. © Bapi Chatterjee, Sathya Peri, Muktikanta Sa, and Komma Manogna.

Leibniz International Proceedings in Informatics, LIPIcs

Non-Blocking Dynamic Unbounded Graphs with Worst-Case Amortized Bounds

Software Transactional Memory systems (STMs) have garnered significant interest as an elegant alternative for addressing synchronization and concurrency issues with multi-threaded programming in multi-core systems. Client programs use STMs by issuing transactions. STM ensures that transaction either commits or aborts. A transaction aborted due to conflicts is typically re-issued with the expectation that it will complete successfully in a subsequent incarnation. However, many existing STMs fail to provide starvation freedom, i.e., in these systems, it is possible that concurrency conflicts may prevent an incarnated transaction from committing. To overcome this limitation, we systematically derive a novel starvation free algorithm for multi-version STM. Our algorithm can be used either with the case where the number of versions is unbounded and garbage collection is used or where only the latest K versions are maintained, KSFTM. We have demonstrated that our proposed algorithm performs better than existing state-of-the-art STMs. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.

Fulltext

Computing

Achieving starvation-freedom in multi-version transactional memory systems

A parameter crucial for preserving the underlying shortest path information in spanning tree construction is called stretch. It is the ratio of the distance of two nodes x and y in the spanning tree to the shortest distance between x and y in the graph. In this paper, we present a heuristic LSTree that constructs a Minimum Average Stretch Spanning Tree of an n-node undirected and unweighted graph in \mathcal{O}(n) rounds of the CONGEST model. We like to stress that LSTree protocol is the first use of Betweenness centrality in the construction of low stretch trees. The heuristic outperforms the current benchmark algorithm of Alon et. al. as well as other spanning tree construction techniques presently known, when tested against synthetic as well as real-world graph inputs. © 2022 IEEE.

Proceedings - 30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2022

A Heuristic for Constructing Minimum Average Stretch Spanning Tree Using Betweenness Centrality

Remote Sensing Letters

ACLNet: an attention and clustering-based cloud segmentation network

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space geometry of such models is organised well enough to perform on datasets where the style is “coarse-grained” i.e. a small fraction of words alone in a sentence are enough to determine the overall style label. A recent study uses a discrete token-based perturbation approach to map “similar” sentences (“similar” defined by low Levenshtein distance/high word overlap) close by in latent space. This definition of “similarity” does not look into the underlying nuances of the constituent words while mapping latent space neighbourhoods and therefore fails to recognise sentences with different style-based semantics while mapping latent neighbourhoods. We introduce EPAAEs (Embedding Perturbed Adversarial AutoEncoders) which completes this perturbation model, by adding a finely adjustable noise component on the continuous embeddings space. We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than similar denoising-inspired baselines, and (c) is capable of fine-grained control of Style Transfer strength. We also extend the text style transfer tasks to NLI datasets and show that these more complex definitions of style are learned best by EPAAE. To the best of our knowledge, extending style transfer to NLI tasks has not been explored before. © 2022 Association for Computational Linguistics.

NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer

Processing cores and the accompanying main memory working in tandem enable modern processors. Dissipating heat produced from computation remains a significant problem for processors. Therefore, the thermal management of processors continues to be an active subject of research. Most thermal management research is performed using simulations, given the challenges in measuring temperatures in real processors. Fast yet accurate interval thermal simulation toolchains remain the research tool of choice to study thermal management in processors at the system level. However, the existing toolchains focus on the thermal management of cores in the processors, since they exhibit much higher power densities than memory. The memory bandwidth limitations associated with 2D processors lead to high-density 2.5D and 3D packaging technology: 2.5D packaging technology places cores and memory on the same package; 3D packaging technology takes it further by stacking layers of memory on the top of cores themselves. These new packagings significantly increase the power density of the processors, making them prone to overheating. Therefore, mitigating thermal issues in high-density processors (packaged with stacked memory) becomes even more pressing. However, given the lack of thermal modeling for memories in existing interval thermal simulation toolchains, they are unsuitable for studying thermal management for high-density processors. To address this issue, we present the first integrated Core and Memory interval Thermal (CoMeT) simulation toolchain. CoMeT comprehensively supports thermal simulation of high- and low-density processors corresponding to four different core-memory (integration) configurations - off-chip DDR memory, off-chip 3D memory, 2.5D, and 3D. CoMeT supports several novel features that facilitate overlying system research. CoMeT adds only an additional ∼5% simulation-time overhead compared to an equivalent state-of-the-art core-only toolchain. The source code of CoMeT has been made open for public use under the MIT license. © 2022 Association for Computing Machinery.