Search Results for author: Mahyar Najibi

Found 30 papers, 12 papers with code

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

1 code implementation24 Apr 2024 Sachin Mehta, Maxwell Horton, Fartash Faghri, Mohammad Hossein Sekhavat, Mahyar Najibi, Mehrdad Farajtabar, Oncel Tuzel, Mohammad Rastegari

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings.

Contrastive Learning

Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation

no code implementations10 Apr 2024 Thomas Merth, Qichen Fu, Mohammad Rastegari, Mahyar Najibi

Despite the successes of large language models (LLMs), they exhibit significant drawbacks, particularly when processing long contexts.

Question Answering Retrieval

Speculative Streaming: Fast LLM Inference without Auxiliary Models

no code implementations16 Feb 2024 Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model.

Language Modelling

Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving

no code implementations ICCV 2023 Mahyar Najibi, Jingwei Ji, Yin Zhou, Charles R. Qi, Xinchen Yan, Scott Ettinger, Dragomir Anguelov

Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment.

Autonomous Driving Knowledge Distillation

3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels

no code implementations CVPR 2023 Zhenzhen Weng, Alexander S. Gorban, Jingwei Ji, Mahyar Najibi, Yin Zhou, Dragomir Anguelov

We show that by training on a large training set from Waymo Open Dataset without any human annotated keypoints, we are able to achieve reasonable performance as compared to the fully supervised approach.

GINA-3D: Learning to Generate Implicit Neural Assets in the Wild

no code implementations CVPR 2023 Bokui Shen, Xinchen Yan, Charles R. Qi, Mahyar Najibi, Boyang Deng, Leonidas Guibas, Yin Zhou, Dragomir Anguelov

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving.

Autonomous Driving Representation Learning

Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining

no code implementations15 Oct 2022 Chiyu Max Jiang, Mahyar Najibi, Charles R. Qi, Yin Zhou, Dragomir Anguelov

Continued improvements in deep learning architectures have steadily advanced the overall performance of 3D object detectors to levels on par with humans for certain tasks and datasets, where the overall performance is mostly driven by common examples.

3D Object Detection Active Learning +3

Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving

no code implementations14 Oct 2022 Mahyar Najibi, Jingwei Ji, Yin Zhou, Charles R. Qi, Xinchen Yan, Scott Ettinger, Dragomir Anguelov

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories.

Autonomous Driving Trajectory Prediction

Revisiting 3D Object Detection From an Egocentric Perspective

no code implementations NeurIPS 2021 Boyang Deng, Charles R. Qi, Mahyar Najibi, Thomas Funkhouser, Yin Zhou, Dragomir Anguelov

Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours.

3D Object Detection Autonomous Driving +2

Offboard 3D Object Detection from Point Cloud Sequences

no code implementations CVPR 2021 Charles R. Qi, Yin Zhou, Mahyar Najibi, Pei Sun, Khoa Vo, Boyang Deng, Dragomir Anguelov

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels.

3D Object Detection 3D Object Recognition +2

Scale Normalized Image Pyramids with AutoFocus for Object Detection

1 code implementation10 Feb 2021 Bharat Singh, Mahyar Najibi, Abhishek Sharma, Larry S. Davis

The resulting algorithm is referred to as AutoFocus and results in a 2. 5-5 times speed-up during inference when used with SNIP.

Object object-detection +1

ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors

1 code implementation19 Jul 2020 Rohun Tripathi, Vasu Singla, Mahyar Najibi, Bharat Singh, Abhishek Sharma, Larry Davis

The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines.

object-detection Object Detection +1

An Analysis of Pre-Training on Object Detection

no code implementations11 Apr 2019 Hengduo Li, Bharat Singh, Mahyar Najibi, Zuxuan Wu, Larry S. Davis

We analyze how well their features generalize to tasks like image classification, semantic segmentation and object detection on small datasets like PASCAL-VOC, Caltech-256, SUN-397, Flowers-102 etc.

Avg Classification +6

AutoFocus: Efficient Multi-Scale Inference

1 code implementation ICCV 2019 Mahyar Najibi, Bharat Singh, Larry S. Davis

Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales.

Universal Adversarial Training

no code implementations27 Nov 2018 Ali Shafahi, Mahyar Najibi, Zheng Xu, John Dickerson, Larry S. Davis, Tom Goldstein

Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels.

Generate, Segment and Refine: Towards Generic Manipulation Segmentation

1 code implementation24 Nov 2018 Peng Zhou, Bor-Chun Chen, Xintong Han, Mahyar Najibi, Abhinav Shrivastava, Ser Nam Lim, Larry S. Davis

The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being shared on the internet.

Detecting Image Manipulation Image Generation +3

Soft Sampling for Robust Object Detection

1 code implementation18 Jun 2018 Zhe Wu, Navaneeth Bodla, Bharat Singh, Mahyar Najibi, Rama Chellappa, Larry S. Davis

Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.

Object object-detection +1

SNIPER: Efficient Multi-Scale Training

4 code implementations NeurIPS 2018 Bharat Singh, Mahyar Najibi, Larry S. Davis

Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47. 6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU.

object-detection Object Detection +1

Face-MagNet: Magnifying Feature Maps to Detect Small Faces

1 code implementation14 Mar 2018 Pouya Samangouei, Mahyar Najibi, Larry Davis, Rama Chellappa

In this paper, we introduce the Face Magnifier Network (Face-MageNet), a face detector based on the Faster-RCNN framework which enables the flow of discriminative information of small scale faces to the classifier without any skip or residual connections.

Face Detection Region Proposal

SSH: Single Stage Headless Face Detector

6 code implementations ICCV 2017 Mahyar Najibi, Pouya Samangouei, Rama Chellappa, Larry Davis

Surprisingly, with a headless VGG-16, SSH beats the ResNet-101-based state-of-the-art on the WIDER dataset.

General Classification

Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection

no code implementations31 Jul 2017 Mahyar Najibi, Fan Yang, Qiaosong Wang, Robinson Piramuthu

In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks.

Object object-detection +2

Supervised Incremental Hashing

no code implementations25 Apr 2016 Bahadir Ozdemir, Mahyar Najibi, Larry S. Davis

In the first stage of classification, binary codes are considered as class labels by a set of binary SVMs; each corresponds to one bit.

General Classification Image Retrieval

On Large-Scale Retrieval: Binary or n-ary Coding?

no code implementations20 Sep 2015 Mahyar Najibi, Mohammad Rastegari, Larry S. Davis

To make large-scale search feasible, Distance Estimation and Subset Indexing are the main approaches.

Image Retrieval Quantization +1

Local Similarities, Global Coding: An Algorithm for Feature Coding and its Applications

no code implementations24 Nov 2013 Amirreza Shaban, Hamid R. Rabiee, Mahyar Najibi

Data coding as a building block of several image processing algorithms has been received great attention recently.

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