Search Results for author:
Found 19 papers, 12 papers with code
PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.
Multi-Game Decision Transformers
Specifically, we show that a single transformer-based model - with a single set of weights - trained purely offline can play a suite of up to 46 Atari games simultaneously at close-to-human performance.
Compressive Visual Representations
We verify this by developing SimCLR and BYOL formulations compatible with the Conditional Entropy Bottleneck (CEB) objective, allowing us to both measure and control the amount of compression in the learned representation, and observe their impact on downstream tasks.
Ranked #43 on
Self-Supervised Image Classification
on ImageNet
Predictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future).
Measuring the Reliability of Reinforcement Learning Algorithms
To aid RL researchers and production users with the evaluation and improvement of reliability, we propose a set of metrics that quantitatively measure different aspects of reliability.
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
In this work, we investigate the problem of grounding language commands as reward functions using inverse reinforcement learning, and argue that language-conditioned rewards are more transferable than language-conditioned policies to new environments.
Tracking Emerges by Colorizing Videos
We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision.
The Devil is in the Decoder: Classification, Regression and GANs
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image.
PixColor: Pixel Recursive Colorization
Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image.
Ranked #3 on
Colorization
on ImageNet val
Semantic Instance Segmentation via Deep Metric Learning
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.
Improved Image Captioning via Policy Gradient optimization of SPIDEr
Finally, we show that using our PG method we can optimize any of the metrics, including the proposed SPIDEr metric which results in image captions that are strongly preferred by human raters compared to captions generated by the same model but trained to optimize MLE or the COCO metrics.
Speed/accuracy trade-offs for modern convolutional object detectors
On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
Ranked #226 on
Object Detection
on COCO test-dev
(using extra training data)
Im2Calories: Towards an Automated Mobile Vision Food Diary
We present a system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories.
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.
Ranked #3 on
Human Interaction Recognition
on BIT
Compute Less to Get More: Using ORC to Improve Sparse Filtering
Sparse Filtering is a popular feature learning algorithm for image classification pipelines.
LSDA: Large Scale Detection Through Adaptation
A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories.
Caffe: Convolutional Architecture for Fast Feature Embedding
The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
