Dipan Pal


I am an ECE PhD student at Carnegie Mellon University. My current interests lie broadly in the intersection of perception, computer vision and deep learning. I work with Prof. Marios Savvides, at the CyLab Biometrics Center. I also occasionally collaborate with Prof. Ole Menshoel. Some of my work was inspired by the work of and discussions with Prof. Tomaso Poggio.

Much of my work is centered around the problem of perception and representation learning. Building useful representations of data is of paramount importance. Ideally, a single good representation would be useful for any task one is interested in. Towards this goal, representations that are invariant to nuisance within-class transformations and that are discriminative towards between class transformations in high dimensional kernel spaces are very useful. Currently, I am investigating the invariance and equivariance properties of convolutional architectures and in doing so am developing a new class of convolutional architectures called Non Parametric Transformation Networks. These architectures can learn invariances that are non-parametric in nature and far more general than the translational invariance and are theoretically motivated. Also, some of my work is focused towards building state-of-the-art face recognition systems which are simply large scale supervised learning problems in deep learning. Other projects in and around deep learning include developing L0 sparse approximation algorithms combined with deep learning and single image super resolution. Applications of the former include compression and unsupervised learning. I have also developed a few loss functions towards the traditional large scale supervised learning problem.

Moving forward, I am also interested in aspects of reinforcement learning.

In the works

Dipan K. Pal*, Raied Aljadaany and Marios Savvides, Deep L0 Sparse Approximation
Raied Aljadaany, Dipan K. Pal* and Marios Savvides, Single Image Super Resolution using the L1 Metric

In the pipeline

Dipan K. Pal and Marios Savvides, Non-Parametric Transformation Networks preprint
Dipan K. Pal and Marios Savvides, How Transformation Networks model Non-linear Invariances, preprint
Yutong Zheng, Dipan K. Pal and Marios Savvides, Title held to reduce searchability aiding double blind reviews (loss for face recognition), (submitted to CVPR 2018) preprint
Dipan K. Pal and Marios Savvides, Copernican loss: Learning a Discriminative Cosine Embedding, preprint

Publications (major contribution)

Dipan K. Pal, Ashwin A. Kannan*, Gautam Arakalgud* and Marios Savvides, Max-margin Invariant Features: Unitary-Group Invariant Kernels from Transformed Unlabeled Data , NIPS 2017 (* indicates equal contribution)

Dipan K. Pal, Vishnu N. Boddeti and Marios Savvides, Emergence of Selective Invariance for Object Categorization through Adaptive Pooling, arXiv 2017

Dipan K. Pal and Marios Savvides, Unitary-Group Invariant Kernels and Features from Transformed Unlabeled Data, arXiv 2016

Dipan K. Pal and Ole Mengshoel, Stochastic CoSaMP: Randomizing Greedy Pursuit for Sparse Signal Recovery, ECML-PKDD, 2016. Supplementary Material

Dipan K. Pal, Felix Juefei-Xu and Marios Savvides, Discriminative Invariant Kernel Features: A Bells-and-Whistles-Free Approach to Unsupervised Face Recognition and Pose Estimation, CVPR 2016 (spotlight presentation)

Felix Juefei-Xu, Dipan K. Pal and Marios Savvides, Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD, CVPRW Biometrics, 2014

Dipan K Pal, S. S. Tripathy, Viresh Ranjan, Avinash Das, Robust Content Based Image Retrieval system using Hierarchical Temporal Memory, ICECT, 2012 (only paper proceedings published)

Dipan K Pal, Evaluation of Gabor Filter enhanced Hierarchical Temporal Memories in image classification applications, IEEE ICCIC, 2011 (only paper proceedings published)

Dipan K Pal, Biometric identification using Hierarchical Temporal Memory with face recognition as a case study, IEEE ICCIC, 2011 (only paper proceedings published)

Other Publications

Pokkalla Harsha Vardhan, Kunal Sekhri, Dipan K. Pal and Marios Savvides, Class Correlation affects Single Object Localization using Pre-trained ConvNets, arXiv 2017

Shreyas Venugopalan, Dipan K. Pal, Marios Savvides, Exploiting Sparsity in Local Iris Texture Representation: An Iris Spoofing Paradigm (under review)

Ngan Le, Chi Nhan Duong, Ligong Han, Khoa Luu, Marios Savvides, Dipan K. Pal, Deep Contextual Recurrent Residual Networks for Scene Labeling, arXiv 2017

Felix Juefei-Xu, Dipan K. Pal and Marios Savvides, NIR-VIS Heterogeneous Face Recognition via Cross-Spectral Joint Dictionary Learning and Reconstruction, CVPRW Perception Beyond the Visual Spectrum Workshop, 2015

Keshav Seshadri, Felix Juefei-Xu, Dipan K. Pal, Marios Savvides and C.P. Thor, Driver Cell Phone Usage Detection on Strategic Highway Research Program (SHRP2) Face View Videos, CVPRW Workshop on Computer Vision in Vehicle Technology, 2015

Felix Juefei-Xu, Dipan K. Pal, Karanhaar Singh, and Marios Savvides, A Preliminary Investigation on the Sensitivity of COTS Face Recognition Systems to Forensic Analyst-style Face Processing for Occlusions, CVPRW Biometrics, 2015

Niv Zehngut, Felix Juefei-Xu, Rishabh Bardia, Dipan K. Pal, Chandrasekhar Bhagavatula, and Marios Savvides, Investigating the Feasibility of Image-Based Nose Biometrics, ICIP, 2015

Jun Shi, Ole Mengshoel, Dipan K. Pal, Feedback control for multi-modal optimization using genetic algorithms, GECCO, 2014


Felix Juefei-Xu, Dipan K. Pal, and Marios Savvides, “Methods and Software for Hallucinating Facial Features by Prioritizing Reconstruction Errors”, U.S. Provisional Patent Application Serial No. 61/998,043, June 17, 2014.

Curriculum Vitae

Please download a copy of my CV from here.