5 papers
B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency
Cherish Puniani, Tushar Kumar, Arnav Bendre +2
Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in…
Impact of Language Guidance: A Reproducibility Study
Cherish Puniani, Advika Sinha, Shree Singhi +1
Modern deep-learning architectures need large amounts of data to produce state-of-the-art results. Annotating such huge datasets is time-consuming, expensive, and prone to human er…
Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Models
Shree Singhi, Aayan Yadav, Aayush Gupta +2
As AI-generated sensitive images become more prevalent, identifying their source is crucial for distinguishing them from real images. Conventional image watermarking methods are vu…
Riemann Sum Optimization for Accurate Integrated Gradients Computation
Swadesh Swain, Shree Singhi
Integrated Gradients (IG) is a widely used algorithm for attributing the outputs of a deep neural network to its input features. Due to the absence of closed-form integrals for dee…
Strengthening Interpretability: An Investigative Study of Integrated Gradient Methods
Shree Singhi, Anupriya Kumari
We conducted a reproducibility study on Integrated Gradients (IG) based methods and the Important Direction Gradient Integration (IDGI) framework. IDGI eliminates the explanation n…