Search Results for author: Bharath Hariharan

Found 80 papers, 56 papers with code

Scale-Aware Recognition in Satellite Images under Resource Constraint

no code implementations31 Oct 2024 Shreelekha Revankar, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan, Kavita Bala

depends strongly on the spatial scale of the concept and therefore the resolution of the images.

Learning 3D Perception from Others' Predictions

no code implementations3 Oct 2024 Jinsu Yoo, Zhenyang Feng, Tai-Yu Pan, Yihong Sun, Cheng Perng Phoo, Xiangyu Chen, Mark Campbell, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao

We investigate a new scenario to construct 3D object detectors: learning from the predictions of a nearby unit that is equipped with an accurate detector.

3D Object Detection object-detection +1

Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning

1 code implementation30 Sep 2024 Chia-Hsiang Kao, Bharath Hariharan

Our work presents a direction for biologically inspired and plausible learning algorithms, offering an alternative mechanism of learning and adaptation in neural networks.

Representation Learning

Neural Control Variates with Automatic Integration

no code implementations23 Sep 2024 Zilu Li, Guandao Yang, Qingqing Zhao, Xi Deng, Leonidas Guibas, Bharath Hariharan, Gordon Wetzstein

This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures.

ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects

no code implementations26 Jul 2024 Gemmechu Hassena, Jonathan Moon, Ryan Fujii, Andrew Yuen, Noah Snavely, Steve Marschner, Bharath Hariharan

Given posed multi-view images and a set of user-input clicks to prompt segmentation of the individual objects, our method decomposes the scene into separate objects and reconstructs a high-quality 3D surface for each one.

MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

1 code implementation23 May 2024 Yihong Sun, Bharath Hariharan

As such, prior work has looked at unsupervised instance detection and segmentation, but in the absence of annotated boxes, it is unclear how pixels must be grouped into objects and which objects are of interest.

Motion Segmentation Object +6

Accurate Differential Operators for Hybrid Neural Fields

1 code implementation10 Dec 2023 Aditya Chetan, Guandao Yang, Zichen Wang, Steve Marschner, Bharath Hariharan

Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts.

Pre-Training LiDAR-Based 3D Object Detectors Through Colorization

1 code implementation23 Oct 2023 Tai-Yu Pan, Chenyang Ma, Tianle Chen, Cheng Perng Phoo, Katie Z Luo, Yurong You, Mark Campbell, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao

Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train.

3D Object Detection Colorization +4

RealFill: Reference-Driven Generation for Authentic Image Completion

no code implementations28 Sep 2023 Luming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li, Aleksander Holynski, David E. Jacobs, Bharath Hariharan, Yael Pritch, Neal Wadhwa, Kfir Aberman, Michael Rubinstein

Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene.

Doppelgangers: Learning to Disambiguate Images of Similar Structures

1 code implementation ICCV 2023 Ruojin Cai, Joseph Tung, Qianqian Wang, Hadar Averbuch-Elor, Bharath Hariharan, Noah Snavely

Our evaluation shows that our method can distinguish illusory matches in difficult cases, and can be integrated into SfM pipelines to produce correct, disambiguated 3D reconstructions.

3D Reconstruction Binary Classification

Emergent Correspondence from Image Diffusion

2 code implementations NeurIPS 2023 Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, Bharath Hariharan

We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images.

Semantic correspondence

Distilling from Similar Tasks for Transfer Learning on a Budget

1 code implementation ICCV 2023 Kenneth Borup, Cheng Perng Phoo, Bharath Hariharan

To alleviate this, we propose a weighted multi-source distillation method to distill multiple source models trained on different domains weighted by their relevance for the target task into a single efficient model (named DistillWeighted).

Transfer Learning

Unsupervised Adaptation from Repeated Traversals for Autonomous Driving

1 code implementation27 Mar 2023 Yurong You, Cheng Perng Phoo, Katie Z Luo, Travis Zhang, Wei-Lun Chao, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger

For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts.

3D Object Detection Autonomous Driving +2

Polynomial Neural Fields for Subband Decomposition and Manipulation

1 code implementation9 Feb 2023 Guandao Yang, Sagie Benaim, Varun Jampani, Kyle Genova, Jonathan T. Barron, Thomas Funkhouser, Bharath Hariharan, Serge Belongie

We use this framework to design Fourier PNFs, which match state-of-the-art performance in signal representation tasks that use neural fields.

Image-to-Image Translation for Autonomous Driving from Coarsely-Aligned Image Pairs

no code implementations23 Sep 2022 Youya Xia, Josephine Monica, Wei-Lun Chao, Bharath Hariharan, Kilian Q Weinberger, Mark Campbell

In this paper, we investigate the idea of turning sensor inputs (i. e., images) captured in an adverse condition into a benign one (i. e., sunny), upon which the downstream tasks (e. g., semantic segmentation) can attain high accuracy.

Autonomous Driving Image-to-Image Translation +4

Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners

no code implementations7 Jul 2022 Davis Wertheimer, Luming Tang, Bharath Hariharan

Existing approaches generally assume that the shot number at test time is known in advance.

Novel Concepts

Visual Prompt Tuning

6 code implementations23 Mar 2022 Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, Ser-Nam Lim

The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.

Image Classification Long-tail Learning +2

Stay Positive: Non-Negative Image Synthesis for Augmented Reality

1 code implementation CVPR 2021 Katie Luo, Guandao Yang, Wenqi Xian, Harald Haraldsson, Bharath Hariharan, Serge Belongie

In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image.

Image-to-Image Translation Style Transfer

Geometry Processing with Neural Fields

1 code implementation NeurIPS 2021 Guandao Yang, Serge Belongie, Bharath Hariharan, Vladlen Koltun

Most existing geometry processing algorithms use meshes as the default shape representation.

A theoretically grounded characterization of feature representations

no code implementations29 Sep 2021 Bharath Hariharan, Cheng Perng Phoo

We present theoretical results showing how these measurements can be used to bound the error of the downstream classifiers, and show empirically that these bounds correlate well with actual downstream performance.

Few-Shot Learning Self-Supervised Learning +1

Field-Guide-Inspired Zero-Shot Learning

1 code implementation ICCV 2021 Utkarsh Mall, Bharath Hariharan, Kavita Bala

Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment.

Attribute Zero-Shot Learning

Can We Characterize Tasks Without Labels or Features?

1 code implementation CVPR 2021 Bram Wallace, Ziyang Wu, Bharath Hariharan

The problem of expert model selection deals with choosing the appropriate pretrained network ("expert") to transfer to a target task.

Model Selection

Extreme Rotation Estimation using Dense Correlation Volumes

1 code implementation CVPR 2021 Ruojin Cai, Bharath Hariharan, Noah Snavely, Hadar Averbuch-Elor

We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap.

Feature Correlation

Coarsely-Labeled Data for Better Few-Shot Transfer

1 code implementation ICCV 2021 Cheng Perng Phoo, Bharath Hariharan

Few-shot learning is based on the premise that labels are expensive, especially when they are fine-grained and require expertise.

Few-Shot Learning Representation Learning

Learning Feature Descriptors using Camera Pose Supervision

1 code implementation ECCV 2020 Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely

Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks.

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

5 code implementations ECCV 2020 Menglin Jia, Mengyun Shi, Mikhail Sirotenko, Yin Cui, Claire Cardie, Bharath Hariharan, Hartwig Adam, Serge Belongie

In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recognize one or multiple attributes).

Attribute Fine-Grained Visual Categorization +5

Extending and Analyzing Self-Supervised Learning Across Domains

1 code implementation ECCV 2020 Bram Wallace, Bharath Hariharan

There has been little to no work with these methods on other smaller domains, such as satellite, textural, or biological imagery.

Representation Learning Self-Supervised Learning

Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition

1 code implementation CVPR 2020 Luming Tang, Davis Wertheimer, Bharath Hariharan

Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e. g., birds) based on a few images alone.

Classification General Classification

LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images

1 code implementation30 Oct 2019 Brian H. Wang, Wei-Lun Chao, Yan Wang, Bharath Hariharan, Kilian Q. Weinberger, Mark Campbell

We obtain 2-D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3-D lidar point cloud by building a graph of connections among 3-D points and 2-D pixels.

Image Segmentation Point Cloud Segmentation +2

On the Efficacy of Knowledge Distillation

no code implementations ICCV 2019 Jang Hyun Cho, Bharath Hariharan

In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures.

Knowledge Distillation

Few-Shot Generalization for Single-Image 3D Reconstruction via Priors

no code implementations ICCV 2019 Bram Wallace, Bharath Hariharan

To address this problem, we present a new model architecture that reframes single-view 3D reconstruction as learnt, category agnostic refinement of a provided, category-specific prior.

3D Reconstruction Single-View 3D Reconstruction

GeoStyle: Discovering Fashion Trends and Events

1 code implementation ICCV 2019 Utkarsh Mall, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala

Understanding fashion styles and trends is of great potential interest to retailers and consumers alike.

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

12 code implementations ICCV 2019 Guandao Yang, Xun Huang, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan

Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape.

Point Cloud Generation Variational Inference

Boosting Supervision with Self-Supervision for Few-shot Learning

no code implementations17 Jun 2019 Jong-Chyi Su, Subhransu Maji, Bharath Hariharan

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions.

Few-Shot Learning Self-Supervised Learning

Few-Shot Learning with Localization in Realistic Settings

1 code implementation CVPR 2019 Davis Wertheimer, Bharath Hariharan

Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones.

Few-Shot Learning

A Deep-Learning-Based Fashion Attributes Detection Model

1 code implementation24 Oct 2018 Menglin Jia, Yichen Zhou, Mengyun Shi, Bharath Hariharan

Such information analyzing process is called abstracting, which recognize similarities or differences across all the garments and collections.

Deep Learning Marketing

Resource Aware Person Re-identification across Multiple Resolutions

1 code implementation CVPR 2018 Yan Wang, Lequn Wang, Yurong You, Xu Zou, Vincent Chen, Serena Li, Gao Huang, Bharath Hariharan, Kilian Q. Weinberger

Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details.

Person Re-Identification

Low-Shot Learning from Imaginary Data

1 code implementation CVPR 2018 Yu-Xiong Wang, Ross Girshick, Martial Hebert, Bharath Hariharan

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views.

General Classification

Inferring and Executing Programs for Visual Reasoning

5 code implementations ICCV 2017 Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Judy Hoffman, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick

Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes.

Visual Question Answering (VQA) Visual Reasoning

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

5 code implementations CVPR 2017 Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick

When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings.

Question Answering Visual Question Answering +1

Learning Features by Watching Objects Move

1 code implementation CVPR 2017 Deepak Pathak, Ross Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan

Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed 'pretext' tasks studied in the literature.

object-detection Object Detection +1

Iterative Instance Segmentation

no code implementations CVPR 2016 Ke Li, Bharath Hariharan, Jitendra Malik

Existing methods for pixel-wise labelling tasks generally disregard the underlying structure of labellings, often leading to predictions that are visually implausible.

Instance Segmentation Segmentation +2

DeepBox: Learning Objectness with Convolutional Networks

1 code implementation ICCV 2015 Wei-cheng Kuo, Bharath Hariharan, Jitendra Malik

Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct.

Hypercolumns for Object Segmentation and Fine-grained Localization

6 code implementations CVPR 2015 Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation.

Object Semantic Segmentation

R-CNNs for Pose Estimation and Action Detection

no code implementations19 Jun 2014 Georgia Gkioxari, Bharath Hariharan, Ross Girshick, Jitendra Malik

We present convolutional neural networks for the tasks of keypoint (pose) prediction and action classification of people in unconstrained images.

Action Classification Action Detection +3

Using k-Poselets for Detecting People and Localizing Their Keypoints

no code implementations CVPR 2014 Georgia Gkioxari, Bharath Hariharan, Ross Girshick, Jitendra Malik

A k-poselet is a deformable part model (DPM) with k parts, where each of the parts is a poselet, aligned to a specific configuration of keypoints based on ground-truth annotations.

Human Detection

Detecting Objects using Deformation Dictionaries

no code implementations CVPR 2014 Bharath Hariharan, C. L. Zitnick, Piotr Dollar

Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes.

Object

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