Shantanu Rane

Bio: Shantanu Rane is an academic researcher from PARC. The author has contributed to research in topics: Encryption & Biometrics. The author has an hindex of 29, co-authored 164 publications receiving 4447 citations. Previous affiliations of Shantanu Rane include Mitsubishi Electric & Mitsubishi Electric Research Laboratories.

Distributed Video Coding

Abstract: Distributed coding is a new paradigm for video compression, based on Slepian and Wolf's and Wyner and Ziv's information-theoretic results from the 1970s. This paper reviews the recent development of practical distributed video coding schemes. Wyner-Ziv coding, i.e., lossy compression with receiver side information, enables low-complexity video encoding where the bulk of the computation is shifted to the decoder. Since the interframe dependence of the video sequence is exploited only at the decoder, an intraframe encoder can be combined with an interframe decoder. The rate-distortion performance is superior to conventional intraframe coding, but there is still a gap relative to conventional motion-compensated interframe coding. Wyner-Ziv coding is naturally robust against transmission errors and can be used for joint source-channel coding. A Wyner-Ziv MPEG encoder that protects the video waveform rather than the compressed bit stream achieves graceful degradation under deteriorating channel conditions without a layered signal representation.

Transform-domain Wyner-Ziv codec for video

Abstract: In current interframe video compression systems, the encoder performs predictive coding to exploit the similarities of successive frames. The Wyner-Ziv Theorem on source coding with side information available only at the decoder suggests that an asymmetric video codec, where individual frames are encoded separately, but decoded conditionally (given temporally adjacent frames) could achieve similar efficiency. We propose a transformdomain Wyner-Ziv coding scheme for motion video that uses intraframe encoding, but interframe decoding. In this system, the transform coefficients of a Wyner-Ziv frame are encoded independently using a scalar quantizer and turbo coder. The decoder uses previously reconstructed frames to generate side information to conditionally decode the Wyner-Ziv frames. Simulation results show significant gains above DCT-based intraframe coding and improvements over the pixel-domain Wyner-Ziv video coder.

Structure and texture filling-in of missing image blocks in wireless transmission and compression applications

Abstract: An approach for filling-in blocks of missing data in wireless image transmission is presented. When compression algorithms such as JPEG are used as part of the wireless transmission process, images are first tiled into blocks of 8 /spl times/ 8 pixels. When such images are transmitted over fading channels, the effects of noise can destroy entire blocks of the image. Instead of using common retransmission query protocols, we aim to reconstruct the lost data using correlation between the lost block and its neighbors. If the lost block contained structure, it is reconstructed using an image inpainting algorithm, while texture synthesis is used for the textured blocks. The switch between the two schemes is done in a fully automatic fashion based on the surrounding available blocks. The performance of this method is tested for various images and combinations of lost blocks. The viability of this method for image compression, in association with lossy JPEG, is also discussed.

Wyner-Ziv video coding with hash-based motion compensation at the receiver

Abstract: In the current interframe video compression systems, the encoder performs predictive coding to exploit the similarities of successive frames. The Wyner-Ziv theorem on source coding with side information available only at the decoder suggests that an asymmetric video codec, where individual frames are encoded separately, but decoded conditionally (given temporally adjacent frames) could achieve similar efficiency. In the previous work we propose a Wyner-Ziv coding scheme for motion video that uses intraframe encoding instead of interframe decoding. In this paper we improve on our Wyner-Ziv video codec by sending hash codewords of the current frame to aid the decoder in accurately estimating the motion. This allows us to implement a low-delay system where only the previous reconstructed frame is used to generate the side information of a current frame. Simulation results show significant gains above conventional DCT-based intraframe coding. The Wyner-Ziv video codec with hash-based motion compensation at the receiver enables low-complexity encoding while achieving high compression efficiency.

Multiparty Differential Privacy via Aggregation of Locally Trained Classifiers

Abstract: As increasing amounts of sensitive personal information finds its way into data repositories, it is important to develop analysis mechanisms that can derive aggregate information from these repositories without revealing information about individual data instances. Though the differential privacy model provides a framework to analyze such mechanisms for databases belonging to a single party, this framework has not yet been considered in a multi-party setting. In this paper, we propose a privacy-preserving protocol for composing a differentially private aggregate classifier using classifiers trained locally by separate mutually untrusting parties. The protocol allows these parties to interact with an untrusted curator to construct additive shares of a perturbed aggregate classifier. We also present a detailed theoretical analysis containing a proof of differential privacy of the perturbed aggregate classifier and a bound on the excess risk introduced by the perturbation. We verify the bound with an experimental evaluation on a real dataset.

Region filling and object removal by exemplar-based image inpainting

Abstract: A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way. In the past, this problem has been addressed by two classes of algorithms: 1) "texture synthesis" algorithms for generating large image regions from sample textures and 2) "inpainting" techniques for filling in small image gaps. The former has been demonstrated for "textures"-repeating two-dimensional patterns with some stochasticity; the latter focus on linear "structures" which can be thought of as one-dimensional patterns, such as lines and object contours. This paper presents a novel and efficient algorithm that combines the advantages of these two approaches. We first note that exemplar-based texture synthesis contains the essential process required to replicate both texture and structure; the success of structure propagation, however, is highly dependent on the order in which the filling proceeds. We propose a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting. The actual color values are computed using exemplar-based synthesis. In this paper, the simultaneous propagation of texture and structure information is achieved by a single , efficient algorithm. Computational efficiency is achieved by a block-based sampling process. A number of examples on real and synthetic images demonstrate the effectiveness of our algorithm in removing large occluding objects, as well as thin scratches. Robustness with respect to the shape of the manually selected target region is also demonstrated. Our results compare favorably to those obtained by existing techniques.

A Completed Modeling of Local Binary Pattern Operator for Texture Classification

Abstract: In this correspondence, a completed modeling of the local binary pattern (LBP) operator is proposed and an associated completed LBP (CLBP) scheme is developed for texture classification. A local region is represented by its center pixel and a local difference sign-magnitude transform (LDSMT). The center pixels represent the image gray level and they are converted into a binary code, namely CLBP-Center (CLBP_C), by global thresholding. LDSMT decomposes the image local differences into two complementary components: the signs and the magnitudes, and two operators, namely CLBP-Sign (CLBP_S) and CLBP-Magnitude (CLBP_M), are proposed to code them. The traditional LBP is equivalent to the CLBP_S part of CLBP, and we show that CLBP_S preserves more information of the local structure than CLBP_M, which explains why the simple LBP operator can extract the texture features reasonably well. By combining CLBP_S, CLBP_M, and CLBP_C features into joint or hybrid distributions, significant improvement can be made for rotation invariant texture classification.

Privacy-Preserving Deep Learning

Abstract: Deep learning based on artificial neural networks is a very popular approach to modeling, classifying, and recognizing complex data such as images, speech, and text The unprecedented accuracy of deep learning methods has turned them into the foundation of new AI-based services on the Internet Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training Massive data collection required for deep learning presents obvious privacy issues Users' personal, highly sensitive data such as photos and voice recordings is kept indefinitely by the companies that collect it Users can neither delete it, nor restrict the purposes for which it is used Furthermore, centrally kept data is subject to legal subpoenas and extra-judicial surveillance Many data owners--for example, medical institutions that may want to apply deep learning methods to clinical records--are prevented by privacy and confidentiality concerns from sharing the data and thus benefitting from large-scale deep learning In this paper, we design, implement, and evaluate a practical system that enables multiple parties to jointly learn an accurate neural-network model for a given objective without sharing their input datasets We exploit the fact that the optimization algorithms used in modern deep learning, namely, those based on stochastic gradient descent, can be parallelized and executed asynchronously Our system lets participants train independently on their own datasets and selectively share small subsets of their models' key parameters during training This offers an attractive point in the utility/privacy tradeoff space: participants preserve the privacy of their respective data while still benefitting from other participants' models and thus boosting their learning accuracy beyond what is achievable solely on their own inputs We demonstrate the accuracy of our privacy-preserving deep learning on benchmark datasets