85 citations · 133 across the 29 of their papers we have counts for
31 papers
Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs
Beining Xu, Hairui Wang, Jiaxin Wang +2
While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific MLLMs remain largely underexplor…
Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification
Siddharth Seth, Akash Sonth, Anirban Chakraborty
Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be di…
Improving Domain Adaptation Through Class Aware Frequency Transformation
Vikash Kumar, Himanshu Patil, Rohit Lal +1
In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respecti…
Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning
M Yashwanth, Gaurav Kumar Nayak, Arya Singh +2
Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local trai…
Query-guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch
Aditay Tripathi, Anand Mishra, Anirban Chakraborty
In this work, we investigate the problem of sketch-based object localization on natural images, where given a crude hand-drawn sketch of an object, the goal is to localize all the…
Multimodal Query-guided Object Localization
Aditay Tripathi, Rajath R Dani, Anand Mishra +1
Consider a scenario in one-shot query-guided object localization where neither an image of the object nor the object category name is available as a query. In such a scenario, a ha…
Robustifying Deep Vision Models Through Shape Sensitization
Aditay Tripathi, Rishubh Singh, Anirban Chakraborty +1
Recent work has shown that deep vision models tend to be overly dependent on low-level or "texture" features, leading to poor generalization. Various data augmentation strategies h…
CoNMix for Source-free Single and Multi-target Domain Adaptation
Vikash Kumar, Rohit Lal, Himanshu Patil +1
This work introduces the novel task of Source-free Multi-target Domain Adaptation and proposes adaptation framework comprising of \textbf{Co}nsistency with \textbf{N}uclear-Norm Ma…
Grounding Scene Graphs on Natural Images via Visio-Lingual Message Passing
Aditay Tripathi, Anand Mishra, Anirban Chakraborty
This paper presents a framework for jointly grounding objects that follow certain semantic relationship constraints given in a scene graph. A typical natural scene contains several…
Robust Few-shot Learning Without Using any Adversarial Samples
Gaurav Kumar Nayak, Ruchit Rawal, Inder Khatri +1
The high cost of acquiring and annotating samples has made the `few-shot' learning problem of prime importance. Existing works mainly focus on improving performance on clean data a…
DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers
Gaurav Kumar Nayak, Ruchit Rawal, Anirban Chakraborty
Certified defense using randomized smoothing is a popular technique to provide robustness guarantees for deep neural networks against l2 adversarial attacks. Existing works use thi…
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems
Gaurav Kumar Nayak, Ruchit Rawal, Rohit Lal +2
Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (rob…
Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi +4
Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domai…
Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM +3
The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in…
MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID
Chaitra Jambigi, Ruchit Rawal, Anirban Chakraborty
Learning modality invariant features is central to the problem of Visible-Thermal cross-modal Person Reidentification (VT-ReID), where query and gallery images come from different…
Beyond Classification: Knowledge Distillation using Multi-Object Impressions
Gaurav Kumar Nayak, Monish Keswani, Sharan Seshadri +1
Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recen…
Incremental Learning for Animal Pose Estimation using RBF k-DPP
Gaurav Kumar Nayak, Het Shah, Anirban Chakraborty
Pose estimation is the task of locating keypoints for an object of interest in an image. Animal Pose estimation is more challenging than estimating human pose due to high inter and…
Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data
Gaurav Kumar Nayak, Konda Reddy Mopuri, Saksham Jain +1
Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen…
Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Images
Shreya Roy, Anirban Chakraborty
The major drawbacks with Satellite Images are low resolution, Low resolution makes it difficult to identify the objects present in Satellite images. We have experimented with sever…
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation
Gaurav Kumar Nayak, Konda Reddy Mopuri, Anirban Chakraborty
Knowledge Distillation is an effective method to transfer the learning across deep neural networks. Typically, the dataset originally used for training the Teacher model is chosen…
Sketch-Guided Object Localization in Natural Images
Aditay Tripathi, Rajath R Dani, Anand Mishra +1
We introduce the novel problem of localizing all the instances of an object (seen or unseen during training) in a natural image via sketch query. We refer to this problem as sketch…
Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images
Gaurav Kumar Nayak, Saksham Jain, R Venkatesh Babu +1
In the emerging commercial space industry there is a drastic increase in access to low cost satellite imagery. The price for satellite images depends on the sensor quality and revi…
Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Rahul M +3
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose est…
Kernel Density Estimation based Factored Relevance Model for Multi-Contextual Point-of-Interest Recommendation
Anirban Chakraborty, Debasis Ganguly, Annalina Caputo +1
An automated contextual suggestion algorithm is likely to recommend contextually appropriate and personalized 'points-of-interest' (POIs) to a user, if it can extract information f…