• Publications
  • Influence
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
Caffe: Convolutional Architecture for Fast Feature Embedding
TLDR
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Expand
Fully convolutional networks for semantic segmentation
TLDR
The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. Expand
cuDNN: Efficient Primitives for Deep Learning
TLDR
A library similar in intent to BLAS, with optimized routines for deep learning workloads, that contains routines for GPUs, and similarly to the BLAS library, could be implemented for other platforms. Expand
Fully Convolutional Multi-Class Multiple Instance Learning
TLDR
This work proposes a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network that exploits the further supervision given by images with multiple labels. Expand
Zero-Shot Visual Imitation
TLDR
This workmitating expert demonstration is a powerful mechanism for learning to perform tasks from raw sensory observations by providing multiple demonstrations of a task at training time, and this generates data in the form of observation-action pairs from the agent's point of view. Expand
Clockwork Convnets for Video Semantic Segmentation
TLDR
This work defines a novel family of "clockwork" convnets driven by fixed or adaptive clock signals that schedule the processing of different layers at different update rates according to their semantic stability, and extends clockwork scheduling to adaptive video processing by incorporating data-driven clocks that can be tuned on unlabeled video. Expand
Few-Shot Segmentation Propagation with Guided Networks
TLDR
This work addresses the problem of few-shot segmentation: given few image and few pixel supervision, segment any images accordingly, and proposes guided networks, which extract a latent task representation from any amount of supervision, and optimize the architecture end-to-end for fast, accurate few- shot segmentation. Expand
Loss is its own Reward: Self-Supervision for Reinforcement Learning
TLDR
This work considers a range of self-supervised tasks that incorporate states, actions, and successors to provide auxiliary losses that offer ubiquitous and instantaneous supervision for representation learning even in the absence of reward. Expand
...
1
2
3
...