XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

A well-known fact is that transferring data to and from GPUs is quite slow. For this reason, we decide to store and update all model parameters on the CPU (see green box).

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

Unsupervised Learning of 3D Structure from Images Authors: Danilo Jimenez Rezende, S. M. Ali Eslami, Shakir Mohamed, Peter Battaglia, Max Jaderberg, Nicolas Heess (Submitted on 3 Jul 2016) Abstract: A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods on several datasets, including ShapeNet [2], and establish the first benchmarks in the literature. We also show how these models and their inference networks can be trained end-to-end from 2D images. This demonstrates for the first time the feasibility of learning to infer 3D representations of the world in a purely unsupervised manner.

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning as standard practice for improved new task performance.

Remember that a slicing tuple can always be constructed as obj and used in the x[obj] notation. Slice objects can be used in the construction in place of the [start:stop:step] notation. For example, x[1:10:5,::-1] can also be implemented as obj = (slice(1,10,5), slice(None,None,-1)); x[obj] . This can be useful for constructing generic code that works on arrays of arbitrary dimension.

Fixed this by including zlib1g-dev package in the ami we're using

conda install nomkl

Low-shot visual object recognition

The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies

Beyond Sharing Weights for Deep Domain Adaptation

Deep Convolutional Inverse Graphics Network

Dynamic Filter Networks

Atl=xtifl= 0MAXPOOL(RELU(CONV(Etl1)))l >0(1)^Atl=RELU(CONV(Rtl))(2)Etl= [RELU(Atl^Atl);RELU(^AtlAtl)](3)Rtl=CONVLSTM(Et1l;Rt1l;Rtl+1)(4)

Unsupervised convolutional neural networks for motion estimation

Adversarial Feature Learning

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Two 140mm fan (front)

这门‘乾坤大挪移’功夫，当真令人好生佩服