Picture for M. Jehanzeb Mirza

M. Jehanzeb Mirza

ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs

Add code
Jun 12, 2024
Viaarxiv icon

Into the Fog: Evaluating Multiple Object Tracking Robustness

Add code
Apr 12, 2024
Viaarxiv icon

Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs

Add code
Mar 19, 2024
Figure 1 for Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Figure 2 for Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Figure 3 for Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Figure 4 for Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Viaarxiv icon

Towards Multimodal In-Context Learning for Vision & Language Models

Add code
Mar 19, 2024
Figure 1 for Towards Multimodal In-Context Learning for Vision & Language Models
Figure 2 for Towards Multimodal In-Context Learning for Vision & Language Models
Figure 3 for Towards Multimodal In-Context Learning for Vision & Language Models
Figure 4 for Towards Multimodal In-Context Learning for Vision & Language Models
Viaarxiv icon

TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification

Add code
Sep 13, 2023
Figure 1 for TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Figure 2 for TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Figure 3 for TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Figure 4 for TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Viaarxiv icon

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

Add code
May 30, 2023
Figure 1 for Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Figure 2 for Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Figure 3 for Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Figure 4 for Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Viaarxiv icon

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

Add code
May 29, 2023
Figure 1 for LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
Figure 2 for LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
Figure 3 for LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
Figure 4 for LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
Viaarxiv icon

MATE: Masked Autoencoders are Online 3D Test-Time Learners

Add code
Nov 24, 2022
Figure 1 for MATE: Masked Autoencoders are Online 3D Test-Time Learners
Figure 2 for MATE: Masked Autoencoders are Online 3D Test-Time Learners
Figure 3 for MATE: Masked Autoencoders are Online 3D Test-Time Learners
Figure 4 for MATE: Masked Autoencoders are Online 3D Test-Time Learners
Viaarxiv icon

An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions

Add code
Apr 21, 2022
Figure 1 for An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
Figure 2 for An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
Figure 3 for An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
Figure 4 for An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
Viaarxiv icon

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

Add code
Dec 01, 2021
Figure 1 for The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
Figure 2 for The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
Figure 3 for The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
Figure 4 for The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
Viaarxiv icon