Author name cluster

Siddharth Roheda

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

CART: Compositional AutoRegressive Transformer for Image Generation

Siddharth Roheda
Rohit Chowdhury
Aniruddha Bala
Rohan Jaiswal

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this success in vision remains challenging due to inherent spatial dependencies in images. Addressing the unique challenges of vision tasks, our method (CART) adds image details iteratively via semantically meaningful decompositions. We demonstrate the flexibility and generality of CART by applying it across three distinct decomposition strategies: (i) Base-Detail Decomposition (Mumford-Shah smoothness), (ii) Intrinsic Decomposition (albedo/shading), and (iii) Specularity Decomposition (diffuse/specular). This “next-detail" strategy outperforms traditional “next-token" and “next-scale" approaches, improving controllability, semantic interpretability, and resolution scalability. Experiments show CART generates visually compelling results while enabling structured image manipulation, opening new directions for controllable generative modeling via physically or perceptually motivated image factorization.

PDF Details DOI

JMLR Journal 2024 Journal Article

Volterra Neural Networks (VNNs)

Siddharth Roheda
Hamid Krim
Bo Jiang

The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals, particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a Volterra filter-inspired Network architecture. This architecture introduces controlled non-linearities in the form of interactions between the delayed input samples of data. We propose a cascaded implementation of Volterra Filtering so as to significantly reduce the number of parameters required to carry out the same classification task as that of a conventional Neural Network. We demonstrate an efficient parallel implementation of this Volterra Neural Network (VNN), along with its remarkable performance while retaining a relatively simpler and potentially more tractable structure. Furthermore, we show a rather sophisticated adaptation of this network to nonlinearly fuse the RGB (spatial) information and the Optical Flow (temporal) information of a video sequence for action recognition. The proposed approach is evaluated on UCF-101 and HMDB-51 datasets for action recognition, and is shown to outperform state of the art CNN approaches. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

PDF Details

AAAI Conference 2020 Conference Paper

Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition

Siddharth Roheda
Hamid Krim

The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a Volterra ﬁlter-inspired Network architecture. This architecture introduces controlled non-linearities in the form of interactions between the delayed input samples of data. We propose a cascaded implementation of Volterra Filtering so as to signiﬁcantly reduce the number of parameters required to carry out the same classiﬁcation task as that of a conventional Neural Network. We demonstrate an efﬁcient parallel implementation of this Volterra Neural Network (VNN), along with its remarkable performance while retaining a relatively simpler and potentially more tractable structure. Furthermore, we show a rather sophisticated adaptation of this network to nonlinearly fuse the RGB (spatial) information and the Optical Flow (temporal) information of a video sequence for action recognition. The proposed approach is evaluated on UCF-101 and HMDB-51 datasets for action recognition, and is shown to outperform state of the art CNN approaches.

PDF Details