Ankit Goyal

I am a Ph.D. student in Computer Science at Princeton University. I am a member of the Princeton Vision and Learning Lab, advised by Prof. Jia Deng. I completed Masters from University of Michigan and Bachelors from IIT Kanpur.

I am looking for full-time research positions starting from Summer/Fall 2022.

I have been fortunate to intern at some wonderful places and work with amazing mentors.

Summer 2021: Nvidia with Dieter Fox
Winter 2021: Intel with Vladlen Koltun
Summer 2016: Microsoft Research India with Prateek Jain
Summer 2015: USC with Shrikanth Narayanan, Tanaya Guha and Naveen Kumar

Recent News:

October 2021: Paper on Non-deep Networks is available on arxiv .
August 2021: Recognized as an Outstanding Reviewer at ICCV 2021 .
July 2021: Selected for Qualcomm Innovation Fellowship with Zachary Teed.
June 2021: Paper on Revisiting point cloud classification accepted to ICML 2021.

Email / CV / Google Scholar / LinkedIn / Follow @imankitgoyal


PhD, CS Princeton University 2018 - 2022	Research Intern NVIDIA Summer-Fall* 2021	Research Intern Intel Winter 2021	MS, CSE University of Michigan 2016 - 2018	Research Intern MSR Summer 2016	Research Intern USC Summer 2015	BTech, EE IIT Kanpur 2012 - 2016

Research

I am interested in understanding various aspects of intelligence, especially reasoning and common sense. In particular, I want to develop computation models for various reasoning skills that humans possess.

	Non-deep Networks Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun arxiv:2110.07641 2021 [code] Depth is the hallmark of DNNs. But more depth means more sequential computation and higher latency. This begs the question -- is it possible to build high-performing ``non-deep" neural networks? We show it is.
	Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejnadro Newell, Jia Deng ICML 2021 [code] [slides] [poster] [video] Many point-based approaches have been proposed reporting steady benchmark improvements over time. We study the key ingredients of this progress and uncover two critical results. First, auxiliary factors, independent of the model architecture, make a large difference in performance. Second, a very simple projection based method performs surprisingly well.
	Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng NeuRIPS 2020, Spotlight (Top 4% of submitted papers) [code] [slides] [poster] [video] Understanding spatial relations is important for both humans and robots. We create Rel3D, the first large-scale, human-annotated dataset for grounding spatial relations in 3D. The 3D scenes in Rel3D come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other.
	PackIt: A Virtual Environment for Geometric Planning Ankit Goyal, Jia Deng ICML 2020 [code] [slides] [video] Simultaneously reasoning about geometry and planning action is crucial for intelligent agents. This ability of geometric planning comes in handy while grocery shopping, rearranging room, warehouse management etc. We create PackIt, a virtual environment that caters to geometric planning.
	Think Visually: Question Answering through Virtual Imagery Ankit Goyal, Jian Wang, Jia Deng ACL 2018 [code] [poster] We study geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a deep network architecture designed for answering questions that admit latent visual representations.
	ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices C Gupta, AS Suggala, A Goyal, HV Simhadri, BP, AK, SG, RU, MV, P Jain ICML 2017 [code] Resource-Efficient Machine Learning Prateek Jain, Chirag Gupta, AS Suggala, Ankit Goyal, HV Simhadri US Patent Applicaiton We propose ProtoNN, a novel algorithm that addresses the problem of real-time and accurate prediction on resource-scarce devices.
	A Multimodal Mixture-Of-Experts Model for Dynamic Emotion Prediction in Movies Ankit Goyal, Naveen Kumar, Tanaya Guha, Shrikanth S. Narayanan ICASSP 2016 We address the problem of continuous emotion prediction in movies. We propose a Mixture of Experts (MoE)-based fusion model that dynamically combines information from the audio and video modalities for predicting the emotion evoked in movies.
	Object Matching Using Speeded Up Robust Features NK Verma, Ankit Goyal, A Harsha Vardhan, Rahul Kumar Sevakula, Al Salour IES 2016 We propose a robust algorithm which is capable of detecting all the instances of a particular object in a scene image using Speeded Up Robust Features.
	Template Matching for Inventory Management using Fuzzy Color Histogram and Spatial Filters NK Verma, Ankit Goyal, Anadi Chaman, Rahul K Sevakula, Al Salour ICIEA 2015 We propose a methodology for object counting using color histogram based segmentation and spatial filters.

Teaching

I have been a Teaching Assistant for the following courses:

COS529: Advanced Computer Vision at Princeton University [Winter 2020]
COS429: Computer Vision at Princeton University [Fall 2018]
EECS442: Computer Vision at University of Michigan [Fall 2017, Winter 2018]

[Web Cite]