activity
20182021
most citedA Two-Stage Approach to Few-Shot Learning for Image Recognition

156 citations · 200 across the 4 of their papers we have counts for

collaborators

5 papers

cs.RO2021

Global-Position Tracking Control of 3-D Bipedal Walking via Virtual Constraint Design and Multiple Lyapunov Analysis

Yan Gu, Yuan Gao, Bin Yao +1

A safety-critical measure of legged locomotion performance is a robot's ability to track its desired time-varying position trajectory in an environment, which is herein termed as "…

cs.CV2020

Few-shot Image Recognition with Manifolds

Debasmit Das, J. H. Moon, C. S. George Lee

In this paper, we extend the traditional few-shot learning (FSL) problem to the situation when the source-domain data is not accessible but only high-level information in the form…

cs.LG2019★ 156 cited

A Two-Stage Approach to Few-Shot Learning for Image Recognition

Debasmit Das, C. S. George Lee

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transfer…

cs.CV2019

Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration

Debasmit Das, C. S. George Lee

Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out wi…

cs.CV2018★ 44 cited

Unsupervised Domain Adaptation using Regularized Hyper-graph Matching

Debasmit Das, C. S. George Lee

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsuper…