Suhas Lohit

Suhas Lohit

Auto-generated profile, based on publicly available information

Suhas Lohit

Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2018 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
SLSuhas Lohit
Suhas Lohit
KKKuldeep Kulkarni
Kuldeep Kulkarni
RKRonan Kerviche
Ronan Kerviche
PTPavan Turaga
Pavan Turaga
AAAmit Ashok
Amit Ashok
Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet, is a deep neural network, which is learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network and can be done in real-time. We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise. We also propose a variant of ReconNet which uses adversarial loss in order to further improve reconstruction quality. We discuss how adding a fully-connected layer to the existing ReconNet architecture allows for jointly learning the measurement matrix and the reconstruction algorithm in a single network. Experiments on real data obtained from a block compressive imager show that our networks are robust to unseen sensor noise.

22 October 2022
Verified
Book Chapter
Closed access
PDF file
SASk Miraj Ahmed
Sk Miraj Ahmed
SLSuhas Lohit
Suhas Lohit
KPKuan-Chuan Peng
Kuan-Chuan Peng
MJMichael J. Jones
Michael J. Jones
ARAmit K. Roy-Chowdhury
Amit K. Roy-Chowdhury

1 September 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YHYuyang Hu
Yuyang Hu
SLSuhas Lohit
Suhas Lohit
UKUlugbek S. Kamilov
Ulugbek S. Kamilov
TMTim K. Marks
Tim K. Marks
Deep learning has achieved some success in addressing the challenge of cloud removal in optical satellite images, by fusing with synthetic aperture radar (SAR) images. Recently, diffusion models have emerged as powerful tools for cloud removal, delivering higher-quality estimation by sampling from cloud-free distributions, compared to earlier methods. However, diffusion models suffer from limitations that can result in suboptimal performance. In particular, diffusion models initiate sampling from pure Gaussian noise, which complicates the sampling trajectory. Moreover, current methods often inadequately fuse SAR and optical data; simple concatenation of these disparate modalities at the input stage typically yields suboptimal results. To address these limitations, we propose Diffusion Bridges for Cloud Removal, DB-CR, which directly bridges between the cloudy and cloud-free image distributions. In addition, we propose a novel multimodal diffusion bridge architecture with a two-branch backbone for multimodal image restoration, incorporating an efficient backbone and dedicated cross-modality fusion blocks to effectively extract and fuse features from synthetic aperture radar (SAR) and optical images. By formulating cloud removal as a diffusion-bridge problem and leveraging this tailored architecture, DB-CR achieves high-fidelity results while being computationally efficient. We evaluated DB-CR on the SEN12MS-CR cloud-removal dataset, demonstrating that it achieves state-of-the-art results.

1 October 2017
Verified
Conference Paper
Open access
SLSuhas Lohit
Suhas Lohit
PTPavan Turaga
Pavan Turaga
Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference. Often, these geometric constraints can be expressed in the language of Riemannian geometry, where conventional vector space machine learning does not apply directly. The central question this paper deals with is: How does one train deep neural nets whose final outputs are elements on a Riemannian manifold? To answer this, we propose a general framework for manifold-aware training of deep neural networks - we utilize tangent spaces and exponential maps in order to convert the proposed problem into a form that allows us to bring current advances in deep learning to bear upon this problem. We describe two specific applications to demonstrate this approach: prediction of probability distributions for multi-class image classification, and prediction of illumination-invariant subspaces from a single face-image via regression on the Grassmannian. These applications show the generality of the proposed framework, and result in improved performance over baselines that ignore the geometry of the output space. In addition to solving this specific problem, we believe this paper opens new lines of enquiry centered on the implications of Riemannian geometry on deep architectures.

11 September 2023 in arXiv
Verified
Preprint
Open access
PDF file
Anoop CherianAnoop Cherian
Anoop Cherian
KPKuan-Chuan Peng
Kuan-Chuan Peng
SLSuhas Lohit
Suhas Lohit
KSKevin A. Smith
Kevin A. Smith
JTJoshua B. Tenenbaum
Joshua B. Tenenbaum
Recent times have witnessed an increasing number of applications of deep neural networks towards solving tasks that require superior cognitive abilities, e.g., playing Go, generating art, ChatGPT, etc. Such a dramatic progress raises the question: how generalizable are neural networks in solving problems that demand broad skills? To answer this question, we propose SMART: a Simple Multimodal Algorithmic Reasoning Task and the associated SMART-101 dataset, for evaluating the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed specifically for children in the 6--8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture and a question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning, among others. To scale our dataset towards training deep neural networks, we programmatically generate entirely new instances for each puzzle, while retaining their solution algorithm. To benchmark performances on SMART-101, we propose a vision and language meta-learning model using varied state-of-the-art backbones. Our experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization. We also evaluate the recent ChatGPT and other large language models on a subset of SMART-101 and find that while these models show convincing reasoning abilities, the answers are often incorrect.

21 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
HWHuan Wang
Huan Wang
SLSuhas Lohit
Suhas Lohit
MJMike Jones
Mike Jones
YFYun Fu
Yun Fu
Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function), while few have attempted to understand it from the input side. Especially, its interplay with data augmentation (DA) has not been well understood. In this paper, we ask: Why do some DA schemes (e.g., CutMix) inherently perform much better than others in KD? What makes a "good" DA in KD? Our investigation from a statistical perspective suggests that a good DA scheme should reduce the covariance of the teacher-student cross-entropy. A practical metric, the stddev of teacher's mean probability (T. stddev), is further presented and well justified empirically. Besides the theoretical understanding, we also introduce a new entropy-based data-mixing DA scheme, CutMixPick, to further enhance CutMix. Extensive empirical studies support our claims and demonstrate how we can harvest considerable performance gains simply by using a better DA scheme in knowledge distillation.