Search Results for author: Akash Kumar

Found 25 papers, 8 papers with code

Solar Potential Analysis of Rooftops Using Satellite Imagery

1 code implementation30 Dec 2018 Akash Kumar

In this work, we introduce an approach through which we can generate a report remotely that provides the amount of solar potential of a building using only its latitude and longitude.

Bird Species Classification using Transfer Learning with Multistage Training

2 code implementations9 Oct 2018 Sourya Dipta Das, Akash Kumar

Bird species classification has received more and more attention in the field of computer vision, for its promising applications in biology and environmental studies.

Classification General Classification +1

Detecting Deepfakes with Metric Learning

1 code implementation19 Mar 2020 Akash Kumar, Arnav Bhavsar

With the arrival of several face-swapping applications such as FaceApp, SnapChat, MixBooth, FaceBlender and many more, the authenticity of digital media content is hanging on a very loose thread.

Data Compression Face Swapping +2

End-to-End Semi-Supervised Learning for Video Action Detection

1 code implementation CVPR 2022 Akash Kumar, Yogesh Singh Rawat

In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data.

Action Detection Classification Consistency +4

Syn2Real: Forgery Classification via Unsupervised Domain Adaptation

1 code implementation3 Feb 2020 Akash Kumar, Arnav Bhavasar

In recent years, image manipulation is becoming increasingly more accessible, yielding more natural-looking images, owing to the modern tools in image processing and computer vision techniques.

Classification General Classification +3

Improving Landmark Recognition using Saliency detection and Feature classification

1 code implementation30 Nov 2018 Akash Kumar, Sagnik Bhowmick, N. Jayanthi, S. Indu

Image Landmark Recognition has been one of the most sought-after classification challenges in the field of vision and perception.

Classification General Classification +3

Combining Gradients and Probabilities for Heterogeneous Approximation of Neural Networks

1 code implementation15 Aug 2022 Elias Trommer, Bernd Waschneck, Akash Kumar

We further demonstrate that our error model can predict the parameters of an approximate multiplier in the context of the commonly used additive Gaussian noise (AGN) model with high accuracy.

Combinatorial Optimization

Testing $k$-Monotonicity

no code implementations1 Sep 2016 Clément L. Canonne, Elena Grigorescu, Siyao Guo, Akash Kumar, Karl Wimmer

Our results include the following: - We demonstrate a separation between testing $k$-monotonicity and testing monotonicity, on the hypercube domain $\{0, 1\}^d$, for $k\geq 3$; - We demonstrate a separation between testing and learning on $\{0, 1\}^d$, for $k=\omega(\log d)$: testing $k$-monotonicity can be performed with $2^{O(\sqrt d \cdot \log d\cdot \log{1/\varepsilon})}$ queries, while learning $k$-monotone functions requires $2^{\Omega(k\cdot \sqrt d\cdot{1/\varepsilon})}$ queries (Blais et al. (RANDOM 2015)).

Learning Theory

Copy-Move Forgery Classification via Unsupervised Domain Adaptation

no code implementations14 Nov 2019 Akash Kumar, Arnav Bhavsar

In the current era, image manipulation is becoming increasingly easier, yielding more natural looking images, owing to the modern tools in image processing and computer vision techniques.

Classification General Classification +3

Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries

no code implementations25 Jun 2020 Akash Kumar, Adish Singla, Yisong Yue, Yuxin Chen

We investigate the average teaching complexity of the task, i. e., the minimal number of samples (halfspace queries) required by a teacher to help a version-space learner in locating a randomly selected target.

ExPAN(N)D: Exploring Posits for Efficient Artificial Neural Network Design in FPGA-based Systems

no code implementations24 Oct 2020 Suresh Nambi, Salim Ullah, Aditya Lohana, Siva Satyendra Sahoo, Farhad Merchant, Akash Kumar

Towards this end, we propose a novel Posit to fixed-point converter for enabling high-performance and energy-efficient hardware implementations for ANNs with minimal drop in the output accuracy.

Network Pruning

The Teaching Dimension of Kernel Perceptron

no code implementations27 Oct 2020 Akash Kumar, Hanqi Zhang, Adish Singla, Yuxin Chen

As a warm-up, we show that the teaching complexity is $\Theta(d)$ for the exact teaching of linear perceptrons in $\mathbb{R}^d$, and $\Theta(d^k)$ for kernel perceptron with a polynomial kernel of order $k$.

SIMDive: Approximate SIMD Soft Multiplier-Divider for FPGAs with Tunable Accuracy

no code implementations2 Nov 2020 Zahra Ebrahimi, Salim Ullah, Akash Kumar

The ever-increasing quest for data-level parallelism and variable precision in ubiquitous multimedia and Deep Neural Network (DNN) applications has motivated the use of Single Instruction, Multiple Data (SIMD) architectures.

Compiler Toolchains for Deep Learning Workloads on Embedded Platforms

no code implementations8 Mar 2021 Max Sponner, Bernd Waschneck, Akash Kumar

As the usage of deep learning becomes increasingly popular in mobile and embedded solutions, it is necessary to convert the framework-specific network representations into executable code for these embedded platforms.

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

no code implementations NeurIPS 2021 Akash Kumar, Yuxin Chen, Adish Singla

This learning paradigm has been extensively studied when the learner receives worst-case or random counterexamples; in this paper, we consider the optimal teacher who picks best-case counterexamples to teach the target hypothesis within a hypothesis class.

Video Action Detection: Analysing Limitations and Challenges

no code implementations17 Apr 2022 Rajat Modi, Aayush Jung Rana, Akash Kumar, Praveen Tirupattur, Shruti Vyas, Yogesh Singh Rawat, Mubarak Shah

Beyond possessing large enough size to feed data hungry machines (eg, transformers), what attributes measure the quality of a dataset?

Action Detection

Robust Empirical Risk Minimization with Tolerance

no code implementations2 Oct 2022 Robi Bhattacharjee, Max Hopkins, Akash Kumar, Hantao Yu, Kamalika Chaudhuri

Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring exponential sample complexity and complicated improper learning rules fall far from answering the need.

Robust classification

Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

no code implementations11 Sep 2023 Max Sponner, Julius Ott, Lorenzo Servadei, Bernd Waschneck, Robert Wille, Akash Kumar

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging.

AxOCS: Scaling FPGA-based Approximate Operators using Configuration Supersampling

no code implementations22 Sep 2023 Siva Satyendra Sahoo, Salim Ullah, Soumyo Bhattacharjee, Akash Kumar

The rising usage of AI and ML-based processing across application domains has exacerbated the need for low-cost ML implementation, specifically for resource-constrained embedded systems.

AxOMaP: Designing FPGA-based Approximate Arithmetic Operators using Mathematical Programming

no code implementations23 Sep 2023 Siva Satyendra Sahoo, Salim Ullah, Akash Kumar

Compared to traditional evolutionary algorithms-based optimization, we report up to 21% improvement in the hypervolume, for joint optimization of PPA and BEHAV, in the design of signed 8-bit multipliers.

Evolutionary Algorithms

Semi-supervised Active Learning for Video Action Detection

no code implementations12 Dec 2023 Ayush Singh, Aayush J Rana, Akash Kumar, Shruti Vyas, Yogesh Singh Rawat

First, we demonstrate its effectiveness on video action detection where the proposed approach outperforms prior works in semi-supervised and weakly-supervised learning along with several baseline approaches in both UCF101-24 and JHMDB-21.

Action Detection Active Learning +6

Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks

no code implementations12 Mar 2024 Max Sponner, Lorenzo Servadei, Bernd Waschneck, Robert Wille, Akash Kumar

These findings highlight the importance of considering temporal correlation in sensor data to improve the termination decision.

Image Classification

Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments

no code implementations12 Mar 2024 Max Sponner, Lorenzo Servadei, Bernd Waschneck, Robert Wille, Akash Kumar

For an ECG classification task, it was able to terminate all samples early, reducing the mean inference energy by 74. 9% and computations by 78. 3%.

ECG Classification Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.