Zhichao Lu

TL;DR: Experimental results suggest that combining the dual objectives of minimizing an error metric and computational complexity, as measured by FLOPs, allows NSGA-Net to find competitive neural architectures.

TL;DR: Experimental evaluation indicates that, across diverse image classification tasks and computational objectives, NAT is an appreciably more effective alternative to conventional transfer learning of fine-tuning weights of an existing network architecture learned on standard datasets.

TL;DR: This work presents Multiview Transformers for Video Recognition (MTV), a model that consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views and achieves state-of-the-art results on six standard datasets.

TL;DR: In this paper, an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs), is proposed, which improves computational efficiency by carefully down-scaling the architectures during the search and reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning.

TL;DR: Experimental results suggest that combining the objectives of minimizing both an error metric and computational complexity, as measured by FLOPS, allows NSGA-Net to find competitive neural architectures near the Pareto front of both objectives on two different tasks, object classification and object alignment.