Search Results for author: R. Venkatesh Babu

Found 106 papers, 50 papers with code

Exploring Attribute Variations in Style-based GANs using Diffusion Models

no code implementations27 Nov 2023 Rishubh Parihar, Prasanna Balaji, Raghav Magazine, Sarthak Vora, Tejan Karmali, Varun Jampani, R. Venkatesh Babu

We capitalize on disentangled latent spaces of pretrained GANs and train a Denoising Diffusion Probabilistic Model (DDPM) to learn the latent distribution for diverse edits.


Distilling from Vision-Language Models for Improved OOD Generalization in Vision Tasks

1 code implementation12 Oct 2023 Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu

The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application.

Domain Generalization

Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation

no code implementations ICCV 2023 Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri, Akshay Kulkarni, Jogendra Nath Kundu, R. Venkatesh Babu

We are the first to utilize vision transformers for domain adaptation in a privacy-oriented source-free setting, and our approach achieves state-of-the-art performance on single-source, multi-source, and multi-target benchmarks

Disentanglement Source-Free Domain Adaptation +1

Inspecting the Geographical Representativeness of Images from Text-to-Image Models

no code implementations ICCV 2023 Abhipsa Basu, R. Venkatesh Babu, Danish Pruthi

Recent progress in generative models has resulted in models that produce both realistic as well as relevant images for most textual inputs.

Data Augmentation Marketing

Certified Adversarial Robustness Within Multiple Perturbation Bounds

1 code implementation20 Apr 2023 Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani, R. Venkatesh Babu

We further propose a novel \textit{training noise distribution} along with a \textit{regularized training scheme} to improve the certification within both $\ell_1$ and $\ell_2$ perturbation norms simultaneously.

Adversarial Robustness

Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation

1 code implementation15 Apr 2023 Prasanna B, Sunandini Sanyal, R. Venkatesh Babu

In this paper, we propose to develop a method to address unsupervised domain adaptation (UDA) in a practical setting of continual learning (CL).

Continual Learning Unsupervised Domain Adaptation

Few-Shot Domain Adaptation for Low Light RAW Image Enhancement

1 code implementation27 Mar 2023 K. Ram Prabhakar, Vishal Vinod, Nihar Ranjan Sahoo, R. Venkatesh Babu

Enhancing practical low light raw images is a difficult task due to severe noise and color distortions from short exposure time and limited illumination.

Domain Adaptation Low-Light Image Enhancement

RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases

no code implementations CVPR 2023 Abhipsa Basu, Sravanti Addepalli, R. Venkatesh Babu

The first component considers the frequency of answers within a question type in the training data, which addresses the concern of the class-imbalance causing the language biases.

Question Answering Visual Question Answering

Subsidiary Prototype Alignment for Universal Domain Adaptation

no code implementations28 Oct 2022 Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni, Hiran Sarkar, Varun Jampani, R. Venkatesh Babu

Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift.

Object Recognition Transfer Learning +1

Efficient and Effective Augmentation Strategy for Adversarial Training

1 code implementation27 Oct 2022 Sravanti Addepalli, Samyak Jain, R. Venkatesh Babu

We first explain this contrasting behavior by viewing augmentation during training as a problem of domain generalization, and further propose Diverse Augmentation-based Joint Adversarial Training (DAJAT) to use data augmentations effectively in adversarial training.

Domain Generalization

Scaling Adversarial Training to Large Perturbation Bounds

1 code implementation18 Oct 2022 Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu

The presence of images that flip Oracle predictions and those that do not makes this a challenging setting for adversarial robustness.

Adversarial Defense Adversarial Robustness

Towards Efficient and Effective Self-Supervised Learning of Visual Representations

1 code implementation18 Oct 2022 Sravanti Addepalli, Kaushal Bhogale, Priyam Dey, R. Venkatesh Babu

Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches.

Representation Learning Self-Supervised Learning

Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks

no code implementations4 Oct 2022 Sravanti Addepalli, Anshul Nasery, R. Venkatesh Babu, Praneeth Netrapalli, Prateek Jain

To bridge the gap between these two lines of work, we first hypothesize and verify that while SB may not altogether preclude learning complex features, it amplifies simpler features over complex ones.

Improving GANs for Long-Tailed Data through Group Spectral Regularization

1 code implementation21 Aug 2022 Harsh Rangwani, Naman Jaswani, Tejan Karmali, Varun Jampani, R. Venkatesh Babu

Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few samples.

Conditional Image Generation

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

no code implementations7 Aug 2022 Tejan Karmali, Rishubh Parihar, Susmit Agrawal, Harsh Rangwani, Varun Jampani, Maneesh Singh, R. Venkatesh Babu

The quality of the generated images is predicated on two assumptions; (a) The richness of the hierarchical representations learnt by the generator, and, (b) The linearity and smoothness of the style spaces.

Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration

no code implementations20 Jul 2022 Rishubh Parihar, Ankit Dhiman, Tejan Karmali, R. Venkatesh Babu

We propose a novel sampling method to sample latent from the manifold, enabling us to generate a diverse set of attribute styles beyond the styles present in the training set.

Image Generation

Segmentation Guided Deep HDR Deghosting

no code implementations4 Jul 2022 K. Ram Prabhakar, Susmit Agrawal, R. Venkatesh Babu

Our motion segmentation guided HDR fusion approach offers significant advantages over existing HDR deghosting methods.

Motion Segmentation Segmentation

Balancing Discriminability and Transferability for Source-Free Domain Adaptation

1 code implementation16 Jun 2022 Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Deepesh Mehta, Shreyas Kulkarni, Varun Jampani, R. Venkatesh Babu

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.

Semantic Segmentation Source-Free Domain Adaptation

A Closer Look at Smoothness in Domain Adversarial Training

1 code implementation16 Jun 2022 Harsh Rangwani, Sumukh K Aithal, Mayank Mishra, Arihant Jain, R. Venkatesh Babu

Based on the analysis, we introduce the Smooth Domain Adversarial Training (SDAT) procedure, which effectively enhances the performance of existing domain adversarial methods for both classification and object detection tasks.

Domain Adaptation Object Detection

Towards Data-Free Model Stealing in a Hard Label Setting

no code implementations CVPR 2022 Sunandini Sanyal, Sravanti Addepalli, R. Venkatesh Babu

In this work, we show that it is indeed possible to steal Machine Learning models by accessing only top-1 predictions (Hard Label setting) as well, without access to model gradients (Black-Box setting) or even the training dataset (Data-Free setting) within a low query budget.

LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity

no code implementations6 Apr 2022 Tejan Karmali, Abhinav Atrishi, Sai Sree Harsha, Susmit Agrawal, Varun Jampani, R. Venkatesh Babu

Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image, which are further used to learn landmarks in a semi-supervised manner.

Self-Supervised Learning

Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

no code implementations NeurIPS 2021 Mugalodi Rakesh, Jogendra Nath Kundu, Varun Jampani, R. Venkatesh Babu

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques.

3D Human Pose Estimation

Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation

no code implementations9 Feb 2022 Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Varun Jampani, R. Venkatesh Babu

However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CNN features hold a more tractable mapping with domain discrimination.

Disentanglement Domain Adaptation +1

Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting

no code implementations24 Dec 2021 K. Ram Prabhakar, Susmit Agrawal, R. Venkatesh Babu

In the SGM cell, the information flow through a gate is controlled by multiplying the gate's output by a function of itself.

S$^3$VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

1 code implementation18 Sep 2021 Harsh Rangwani, Arihant Jain, Sumukh K Aithal, R. Venkatesh Babu

Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain.

Unsupervised Domain Adaptation

Labeled From Unlabeled: Exploiting Unlabeled Data for Few-Shot Deep HDR Deghosting

no code implementations CVPR 2021 K. Ram Prabhakar, Gowtham Senthil, Susmit Agrawal, R. Venkatesh Babu, Rama Krishna Sai S Gorthi

To derive data for the next stage of training, we propose a novel method for generating corresponding dynamic inputs from the predicted HDRs of unlabeled data.

Few-Shot Learning

Class Balancing GAN with a Classifier in the Loop

1 code implementation17 Jun 2021 Harsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu

However, majority of the developments focus on performance of GANs on balanced datasets.

Deep Implicit Surface Point Prediction Networks

no code implementations ICCV 2021 Rahul Venkatesh, Tejan Karmali, Sarthak Sharma, Aurobrata Ghosh, R. Venkatesh Babu, László A. Jeni, Maneesh Singh

Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes.

S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

1 code implementation ICCV 2021 Harsh Rangwani, Arihant Jain, Sumukh K Aithal, R. Venkatesh Babu

Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain.

Unsupervised Domain Adaptation

Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

1 code implementation NeurIPS 2020 Gaurang Sriramanan, Sravanti Addepalli, Arya Baburaj, R. Venkatesh Babu

Further, we propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses by utilizing the proposed relaxation term for both attack generation and training.

Adversarial Attack Adversarial Defense

Appearance Consensus Driven Self-Supervised Human Mesh Recovery

no code implementations ECCV 2020 Jogendra Nath Kundu, Mugalodi Rakesh, Varun Jampani, Rahul Mysore Venkatesh, R. Venkatesh Babu

We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision.

3D Pose Estimation Human Mesh Recovery

Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks

no code implementations31 Jul 2020 Sravanti Addepalli, Dipesh Tamboli, R. Venkatesh Babu, Biplab Banerjee

Existing visualization methods develop high confidence images consisting of both background and foreground features.

Learning to Count in the Crowd from Limited Labeled Data

no code implementations ECCV 2020 Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu, R. Venkatesh Babu, Vishal M. Patel

In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data.

Crowd Counting

Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation

no code implementations24 Jun 2020 Jogendra Nath Kundu, Siddharth Seth, Rahul M. V, Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty

However, generalizability of human pose estimation models developed using supervision on large-scale in-studio datasets remains questionable, as these models often perform unsatisfactorily on unseen in-the-wild environments.

3D Human Pose Estimation 3D Pose Estimation +2

From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks

1 code implementation CVPR 2020 K L Navaneet, Ansu Mathew, Shashank Kashyap, Wei-Chih Hung, Varun Jampani, R. Venkatesh Babu

We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making use of differentiable point cloud renderer to train with 2D supervision.

3D Object Reconstruction From A Single Image 3D Point Cloud Reconstruction +2

Adversarial Fooling Beyond "Flipping the Label"

no code implementations27 Apr 2020 Konda Reddy Mopuri, Vaisakh Shaj, R. Venkatesh Babu

Therefore, the metric to quantify the vulnerability of the models should capture the severity of the flipping as well.

Single-step Adversarial training with Dropout Scheduling

no code implementations CVPR 2020 Vivek B. S., R. Venkatesh Babu

In this work, (i) we show that models trained using single-step adversarial training method learn to prevent the generation of single-step adversaries, and this is due to over-fitting of the model during the initial stages of training, and (ii) to mitigate this effect, we propose a single-step adversarial training method with dropout scheduling.

Autonomous Driving Medical Diagnosis +1

Universal Source-Free Domain Adaptation

1 code implementation CVPR 2020 Jogendra Nath Kundu, Naveen Venkat, Rahul M. V, R. Venkatesh Babu

1) In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift.

Source-Free Domain Adaptation

Towards Inheritable Models for Open-Set Domain Adaptation

1 code implementation CVPR 2020 Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur, Rahul M. V, R. Venkatesh Babu

Addressing this, we introduce a practical DA paradigm where a source-trained model is used to facilitate adaptation in the absence of the source dataset in future.

Domain Adaptation

Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes

1 code implementation CVPR 2020 Sravanti Addepalli, Vivek B. S., Arya Baburaj, Gaurang Sriramanan, R. Venkatesh Babu

In this work, we attempt to address this problem by training networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction.

Adversarial Robustness

Regularizers for Single-step Adversarial Training

1 code implementation3 Feb 2020 B. S. Vivek, R. Venkatesh Babu

The proposed regularizers mitigate the effect of gradient masking by harnessing on properties that differentiate a robust model from that of a pseudo robust model.

DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier

no code implementations27 Dec 2019 Sravanti Addepalli, Gaurav Kumar Nayak, Anirban Chakraborty, R. Venkatesh Babu

We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework.

Incremental Learning Knowledge Distillation +1

FDA: Feature Disruptive Attack

1 code implementation ICCV 2019 Aditya Ganeshan, B. S. Vivek, R. Venkatesh Babu

Though Deep Neural Networks (DNN) show excellent performance across various computer vision tasks, several works show their vulnerability to adversarial samples, i. e., image samples with imperceptible noise engineered to manipulate the network's prediction.

Adversarial Attack Image Classification

GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions

2 code implementations ICCV 2019 Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal, R. Venkatesh Babu

Despite the remarkable success of generative adversarial networks, their performance seems less impressive for diverse training sets, requiring learning of discontinuous mapping functions.


UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation

1 code implementation ICCV 2019 Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu

In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting.

Multi-Task Learning Representation Learning +2

Enhancing Salient Object Segmentation Through Attention

no code implementations27 May 2019 Anuj Pahuja, Avishek Majumder, Anirban Chakraborty, R. Venkatesh Babu

Segmenting salient objects in an image is an important vision task with ubiquitous applications.

Semantic Segmentation

Zero-Shot Knowledge Distillation in Deep Networks

1 code implementation20 May 2019 Gaurav Kumar Nayak, Konda Reddy Mopuri, Vaisakh Shaj, R. Venkatesh Babu, Anirban Chakraborty

Without even using any meta-data, we synthesize the Data Impressions from the complex Teacher model and utilize these as surrogates for the original training data samples to transfer its learning to Student via knowledge distillation.

Knowledge Distillation

Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network

1 code implementation25 Jan 2019 Priyanka Mandikal, R. Venkatesh Babu

Through extensive quantitative and qualitative evaluation on synthetic and real datasets, we demonstrate that DensePCR outperforms the existing state-of-the-art point cloud reconstruction works, while also providing a light-weight and scalable architecture for predicting high-resolution outputs.

3D Point Cloud Reconstruction Point cloud reconstruction

BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN

2 code implementations6 Dec 2018 Jogendra Nath Kundu, Maharshi Gor, R. Venkatesh Babu

The discriminator is trained also to regress this extrinsic factor r, which is used alongside with the intrinsic factor (encoded starting pose sequence) to generate a particular pose sequence.

Human motion prediction motion prediction

Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold

2 code implementations6 Dec 2018 Jogendra Nath Kundu, Maharshi Gor, Phani Krishna Uppala, R. Venkatesh Babu

In this work we propose a novel temporal pose-sequence modeling framework, which can embed the dynamics of 3D human-skeleton joints to a continuous latent space in an efficient manner.

Fine-grained Action Recognition Representation Learning +1

CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision

1 code implementation28 Nov 2018 Navaneet K L, Priyanka Mandikal, Mayank Agarwal, R. Venkatesh Babu

We consider the task of single image 3D point cloud reconstruction, and aim to utilize multiple foreground masks as our supervisory data to alleviate the need for large scale 3D datasets.

3D Point Cloud Reconstruction Point cloud reconstruction +1

Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence

2 code implementations3 Sep 2018 Jogendra Nath Kundu, Rahul M. V., Aditya Ganeshan, R. Venkatesh Babu

In this work, we propose a data-efficient method which utilizes the geometric regularity of intraclass objects for pose estimation.

Pose Estimation Viewpoint Estimation

Gray-box Adversarial Training

no code implementations ECCV 2018 Vivek B. S., Konda Reddy Mopuri, R. Venkatesh Babu

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems.

iSPA-Net: Iterative Semantic Pose Alignment Network

2 code implementations3 Aug 2018 Jogendra Nath Kundu, Aditya Ganeshan, Rahul M. V., Aditya Prakash, R. Venkatesh Babu

Such image comparison based approach also alleviates the problem of data scarcity and hence enhances scalability of the proposed approach for novel object categories with minimal annotation.

Pose Estimation Semantic correspondence +1

Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions

no code implementations ECCV 2018 Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu

Given a model, there exist broadly two approaches to craft UAPs: (i) data-driven: that require data, and (ii) data-free: that do not require data samples.

Top-Down Feedback for Crowd Counting Convolutional Neural Network

no code implementations24 Jul 2018 Deepak Babu Sam, R. Venkatesh Babu

But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people.

Crowd Counting

Operator-in-the-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification

no code implementations19 Jul 2018 K L Navaneet, Ravi Kiran Sarvadevabhatla, Shashank Shekhar, R. Venkatesh Babu, Anirban Chakraborty

Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras.

Person Re-Identification

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

no code implementations CVPR 2018 Jogendra Nath Kundu, Phani Krishna Uppala, Anuj Pahuja, R. Venkatesh Babu

Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies.

Monocular Depth Estimation Unsupervised Domain Adaptation

Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations

2 code implementations24 Jan 2018 Konda Reddy Mopuri, Aditya Ganeshan, R. Venkatesh Babu

Further, via exploiting simple priors related to the data distribution, our objective remarkably boosts the fooling ability of the crafted perturbations.

Adversarial Attack Depth Estimation +2

DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs

1 code implementation ICCV 2017 K. Ram Prabhakar, V. Sai Srikar, R. Venkatesh Babu

To address the above issues, we have gathered a large dataset of multi-exposure image stacks for training and to circumvent the need for ground truth images, we propose an unsupervised deep learning framework for MEF utilizing a no-reference quality metric as loss function.

NAG: Network for Adversary Generation

1 code implementation CVPR 2018 Konda Reddy Mopuri, Utkarsh Ojha, Utsav Garg, R. Venkatesh Babu

Our trained generator network attempts to capture the distribution of adversarial perturbations for a given classifier and readily generates a wide variety of such perturbations.

CNN Fixations: An unraveling approach to visualize the discriminative image regions

2 code implementations22 Aug 2017 Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu

We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks and data modalities.

Image Captioning Object Recognition

Switching Convolutional Neural Network for Crowd Counting

1 code implementation CVPR 2017 Deepak Babu Sam, Shiv Surya, R. Venkatesh Babu

It is observed that the switch relays an image patch to a particular CNN column based on density of crowd.

Crowd Counting

Image Denoising via CNNs: An Adversarial Approach

no code implementations1 Aug 2017 Nithish Divakar, R. Venkatesh Babu

Is it possible to recover an image from its noisy version using convolutional neural networks?

General Classification Image Denoising +2

Confidence estimation in Deep Neural networks via density modelling

no code implementations21 Jul 2017 Akshayvarun Subramanya, Suraj Srinivas, R. Venkatesh Babu

State-of-the-art Deep Neural Networks can be easily fooled into providing incorrect high-confidence predictions for images with small amounts of adversarial noise.


Fast Feature Fool: A data independent approach to universal adversarial perturbations

1 code implementation18 Jul 2017 Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu

In this paper, for the first time, we propose a novel data independent approach to generate image agnostic perturbations for a range of CNNs trained for object recognition.

Object Recognition

Deep image representations using caption generators

1 code implementation25 May 2017 Konda Reddy Mopuri, Vishal B. Athreya, R. Venkatesh Babu

We demonstrate that, owing to richer supervision provided during the process of training, the features learned by the captioning system perform better than those of CNNs.

Retrieval Transfer Learning

Object category understanding via eye fixations on freehand sketches

no code implementations20 Mar 2017 Ravi Kiran Sarvadevabhatla, Sudharshan Suresh, R. Venkatesh Babu

In this paper, we analyze the results of a free-viewing gaze fixation study conducted on 3904 freehand sketches distributed across 160 object categories.


'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems

no code implementations23 Nov 2016 Ravi Kiran Sarvadevabhatla, Shanthakumar Venkatraman, R. Venkatesh Babu

Our results show that the proposed benchmarking procedure enables additional differentiation among state-of-the-art object classifiers in terms of their ability to handle missing content and insufficient object detail.

Benchmarking Object Recognition +3

Training Sparse Neural Networks

no code implementations21 Nov 2016 Suraj Srinivas, Akshayvarun Subramanya, R. Venkatesh Babu

Deep neural networks with lots of parameters are typically used for large-scale computer vision tasks such as image classification.

General Classification Image Classification

Generalized Dropout

no code implementations21 Nov 2016 Suraj Srinivas, R. Venkatesh Babu

One set of methods in this family, called Dropout++, is a version of Dropout with trainable parameters.

Bayesian Inference

Compensating for Large In-Plane Rotations in Natural Images

no code implementations17 Nov 2016 Lokesh Boominathan, Suraj Srinivas, R. Venkatesh Babu

This is inspired by the neuro-scientific concept of mental rotation, which humans use to compare pairs of rotated objects.

Bayesian Optimization Image Retrieval +1

CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

2 code implementations22 Aug 2016 Lokesh Boominathan, Srinivas S. S. Kruthiventi, R. Venkatesh Babu

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds.

Crowd Counting Data Augmentation

A Taxonomy of Deep Convolutional Neural Nets for Computer Vision

no code implementations25 Jan 2016 Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S. S. Kruthiventi, R. Venkatesh Babu

With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective.

Learning Neural Network Architectures using Backpropagation

no code implementations17 Nov 2015 Suraj Srinivas, R. Venkatesh Babu

In this work, we introduce the problem of architecture-learning, i. e; learning the architecture of a neural network along with weights.

DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations

no code implementations10 Oct 2015 Srinivas S. S. Kruthiventi, Kumar Ayush, R. Venkatesh Babu

Understanding and predicting the human visual attentional mechanism is an active area of research in the fields of neuroscience and computer vision.

Saliency Prediction

Attribute-Graph: A Graph based approach to Image Ranking

no code implementations ICCV 2015 Nikita Prabhu, R. Venkatesh Babu

We benchmark the performance of our algorithm on the 'rPascal' and 'rImageNet' datasets, which we have created in order to evaluate the ranking performance on complex queries containing multiple objects.

Semantic Similarity Semantic Textual Similarity

Data-free parameter pruning for Deep Neural Networks

no code implementations22 Jul 2015 Suraj Srinivas, R. Venkatesh Babu

Our experiments in pruning the densely connected layers show that we can remove upto 85\% of the total parameters in an MNIST-trained network, and about 35\% for AlexNet without significantly affecting performance.

Salient Object Detection via Objectness Measure

no code implementations24 Jun 2015 Sai Srivatsa R, R. Venkatesh Babu

Salient object detection has become an important task in many image processing applications.

object-detection RGB Salient Object Detection +1

Crowd Flow Segmentation in Compressed Domain using CRF

no code implementations19 Jun 2015 Srinivas S. S. Kruthiventi, R. Venkatesh Babu

This work in compressed domain can be easily extended to pixel domain by substituting motion vectors with motion based features like optical flow.

Optical Flow Estimation

Expresso : A user-friendly GUI for Designing, Training and Exploring Convolutional Neural Networks

1 code implementation25 May 2015 Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu

With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python.

Object Level Deep Feature Pooling for Compact Image Representation

no code implementations24 Apr 2015 Konda Reddy Mopuri, R. Venkatesh Babu

Convolutional Neural Network (CNN) features have been successfully employed in recent works as an image descriptor for various vision tasks.

Image Retrieval Retrieval +1

Freehand Sketch Recognition Using Deep Features

no code implementations1 Feb 2015 Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu

Therefore, analyzing such sparse sketches can aid our understanding of the neuro-cognitive processes involved in visual representation and recognition.

Retrieval Sketch-Based Image Retrieval +1

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