Puneet Dokania
10 papers · 2016–2024 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(6)
Learning Types · Deep Learning
(5)
Optimization & Theory · Machine Learning
(5)
Application Areas
(4)
Learning Types · Machine Learning
(4)
Mathematics & Optimization
(2)
Core Methods
(2)
Optimization
(2)
Artificial Intelligence
(1)
Core AI
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
catastrophic forgetting
(2)
experience replay
(2)
continual learning
(2)
data augmentation
(2)
gradient descent
(1)
mirror descent
(1)
adversarial training
(1)
covariate shift
(1)
structured prediction
(1)
episodic memory
(1)
continuous optimization
(1)
oracle complexity
(1)
out-of-distribution detection
(1)
bilevel optimization
(1)
deep neural network
(1)
constrained optimization
(1)
stochastic gradient langevin dynamics
(1)
uncertainty estimation
(1)
straight-through estimator
(1)
model compression
(1)
Papers
"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines"
ECCV 2024
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation
ECCV 2024
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
NeurIPS 2022
Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness
NeurIPS 2022
A Continuous Mapping For Augmentation Design
NeurIPS 2021
Mirror Descent View for Neural Network Quantization
AISTATS 2021
Using Hindsight to Anchor Past Knowledge in Continual Learning
AAAI 2021
Calibrating Deep Neural Networks using Focal Loss
NeurIPS 2020
Continual Learning in Low-rank Orthogonal Subspaces
NeurIPS 2020
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
ICML 2016