**Summary**

Representation (or feature) learning with unsupervised learning has yet really to yield the type of results that many believe to be achievable. For example, we’d like to unleash an unsupervised learning algorithm on all web images and then obtain a representation that captures the various factors of variation we know to be present (e.g. objects and people). One popular approach for this is to train a model that assumes a high-level vector representation with independent components. However, despite a large body of literature on such models by now, such so-called disentangling of these factors of variation still seems beyond our reach.

In this short paper, the authors propose an alternative to this approach. They propose that disentangling might be achievable by learning a representation whose dimensions are each separately **controllable**, i.e. that each have an associated policy which changes the value of that dimension **while letting other dimensions fixed**. 

Specifically, the authors propose to minimize the following objective:

$\mathop{\mathbb{E}}_s\left[\frac{1}{2}||s-g(f(s))||^2_2 \right] - \lambda \sum_k \mathbb{E}_{a,s}\left[\sum_a \pi_k(a|s) \log sel(s,a,k)\right]$

where 
- $s$ is an agent’s state (e.g. frame image) which encoder $f$ and decoder $g$ learn to autoencode
- $k$ iterates over all dimensions of the representation space (output of encoder)
- $a$ iterates over actions that the agent can take
- $\pi_k(a|s)$ is the policy that is meant to control the $k^{\rm th}$ dimension of the representation space $f(s)_k$
- $sel(s,a,k)$ is the selectivity of $f(s)_k$ relative to other dimensions in the representation, at state $s$:

$sel(s,a,k) = \mathop{\mathbb{E}}_{s’\sim {\cal P}_{ss’}^a}\left[\frac{|f_k(s’)-f_k(s)|}{\sum_{k’} |f_{k’}(s’)-f_{k’}(s)| }\right]$

${\cal P}_{ss’}^a$ is the conditional distribution over the next step state $s’$ given that you are at state $s$ and are taking action $a$ (i.e. the environment transition distribution). One can see that selectivity is higher when the change $|f_k(s’)-f_k(s)|$ in dimension $k$ is much larger than the change 
$|f_{k’}(s’)-f_{k’}(s)|$ in the other dimensions $k’$. A directed version of selectivity is also proposed (and I believe was used in the experiments), where the absolute value function is removed and $\log sel$ is replaced with $\log(1+sel)$ in the objective.

The learning objective will thus encourage the discovery of a representation that is informative of the input (in that you can reconstruct it) and for which there exists policies that separately control these dimensions.

Algorithm 1 in the paper describes a learning procedure for optimizing this objective. In brief, for every update, a state $s$ is sampled from which an update for the autoencoder part of the loss can be made. Then, iterating over each dimension $k$, REINFORCE is used to get a gradient estimate of the selectivity part of the loss, to update both the policy $\pi_k$ and the encoder $f$ by using the policy to reach a next state $s’$.

**My two cents**

I find this concept very appealing and thought provoking. Intuitively, I find the idea that valuable features are features which reflect an aspect of our environment that we can control more sensible and possibly less constraining than an assumption of independent features. It also has an interesting analogy of an infant learning about the world by interacting with it.

The caveat is that unfortunately, this concept is currently fairly impractical, since it requires an interactive environment where an agent can perform actions, something we can’t easily have short of deploying a robot with sensors. Moreover, the proposed algorithm seems to assume that each state $s$ is sampled independently for each update, whereas a robot would observe a dependent stream of states. 

Accordingly, the experiments in this short paper are mostly “proof of concept”, on simplistic synthetic environments. Yet they do a good job at illustrating the idea.

To me this means that there’s more interesting work worth doing in what seems to be a promising direction!

This paper presents a novel neural network approach (though see [here](https://www.facebook.com/hugo.larochelle.35/posts/172841743130126?pnref=story) for a discussion on prior work) to density estimation, with a focus on image modeling. At its core, it exploits the following property on the densities of random variables. Let $x$ and $z$ be two random variables of equal dimensionality such that $x = g(z)$, where $g$ is some bijective and deterministic function (we'll note its inverse as $f = g^{-1}$). Then the change of variable formula gives us this relationship between the densities of $x$ and $z$:

$p_X(x) = p_Z(z) \left|{\rm det}\left(\frac{\partial g(z)}{\partial z}\right)\right|^{-1}$

Moreover, since the determinant of the Jacobian matrix of the inverse $f$ of a function $g$ is simply the inverse of the Jacobian of the function $g$, we can also write:

$p_X(x) = p_Z(f(x)) \left|{\rm det}\left(\frac{\partial f(x)}{\partial x}\right)\right|$

where we've replaced $z$ by its deterministically inferred value $f(x)$ from $x$.

So, the core of the proposed model is in proposing a design for bijective functions $g$ (actually, they design its inverse $f$, from which $g$ can be derived by inversion), that have the properties of being easily invertible and having an easy-to-compute determinant of Jacobian. Specifically, the authors propose to construct $f$ from various modules that all preserve these properties and allows to construct highly non-linear $f$ functions. Then, assuming a simple choice for the density $p_Z$ (they use a multidimensional Gaussian), it becomes possible to both compute $p_X(x)$ tractably and to sample from that density, by first samples $z\sim p_Z$ and then computing $x=g(z)$.

The building blocks for constructing $f$ are the following:

**Coupling layers**: This is perhaps the most important piece. It simply computes as its output $b\odot x + (1-b) \odot (x \odot \exp(l(b\odot x)) + m(b\odot x))$, where $b$ is a binary mask (with half of its values set to 0 and the others to 1) over the input of the layer $x$, while $l$ and $m$ are arbitrarily complex neural networks with input and output layers of equal dimensionality. 

In brief, for dimensions for which $b_i = 1$ it simply copies the input value into the output. As for the other dimensions (for which $b_i = 0$) it linearly transforms them as $x_i * \exp(l(b\odot x)_i) + m(b\odot x)_i$. Crucially, the bias ($m(b\odot x)_i$) and coefficient ($\exp(l(b\odot x)_i)$) of the linear transformation are non-linear transformations (i.e. the output of neural networks) that only have access to the masked input (i.e. the non-transformed dimensions). While this layer might seem odd, it has the important property that it is invertible and the determinant of its Jacobian is simply $\exp(\sum_i (1-b_i) l(b\odot x)_i)$. See Section 3.3 for more details on that.

**Alternating masks**: One important property of coupling layers is that they can be stacked (i.e. composed), and the resulting composition is still a bijection and is invertible (since each layer is individually a bijection) and has a tractable determinant for its Jacobian (since the Jacobian of the composition of functions is simply the multiplication of each function's Jacobian matrix, and the determinant of the product of square matrices is the product of the determinant of each matrix). This is also true, even if the mask $b$ of each layer is different. Thus, the authors propose using masks that alternate across layer, by masking a different subset of (half of) the dimensions. For images, they propose using masks with a checkerboard pattern (see Figure 3). Intuitively, alternating masks are better because then after at least 2 layers, all dimensions have been transformed at least once.

**Squeezing operations**: Squeezing operations corresponds to a reorganization of a 2D spatial layout of dimensions into 4 sets of features maps with spatial resolutions reduced by half (see Figure 3). This allows to expose multiple scales of resolutions to the model. Moreover, after a squeezing operation, instead of using a checkerboard pattern for masking, the authors propose to use a per channel masking pattern, so that "the resulting partitioning is not redundant with the previous checkerboard masking". See Figure 3 for an illustration.

Overall, the models used in the experiments usually stack a few of the following "chunks" of layers: 1) a few coupling layers with alternating checkboard masks, 2) followed by squeezing, 3) followed by a few coupling layers with alternating channel-wise masks. Since the output of each layers-chunk must technically be of the same size as the input image, this could become expensive in terms of computations and space when using a lot of layers. Thus, the authors propose to explicitly pass on (copy) to the very last layer ($z$) half of the dimensions after each layers-chunk, adding another chunk of layers only on the other half. This is illustrated in Figure 4b.

Experiments on CIFAR-10, and 32x32 and 64x64 versions of ImageNet show that the proposed model (coined the real-valued non-volume preserving or Real NVP) has competitive performance (in bits per dimension), though slightly worse than the Pixel RNN.

**My Two Cents**

The proposed approach is quite unique and thought provoking. Most interestingly, it is the only powerful generative model I know that combines A) a tractable likelihood, B) an efficient / one-pass sampling procedure and C) the explicit learning of a latent representation. While achieving this required a model definition that is somewhat unintuitive, it is nonetheless mathematically really beautiful!

I wonder to what extent Real NVP is penalized in its results by the fact that it models pixels as real-valued observations. First, it implies that its estimate of bits/dimensions is an upper bound on what it could be if the uniform sub-pixel noise was integrated out (see Equations 3-4-5 of [this paper](http://arxiv.org/pdf/1511.01844v3.pdf)). Moreover, the authors had to apply a non-linear transformation (${\rm logit}(\alpha + (1-\alpha)\odot x)$) to the pixels, to spread the $[0,255]$ interval further over the reals. Since the Pixel RNN models pixels as discrete observations directly, the Real NVP might be at a disadvantage.

I'm also curious to know how easy it would be to do conditional inference with the Real NVP. One could imagine doing approximate MAP conditional inference, by clamping the observed dimensions and doing gradient descent on the log-likelihood with respect to the value of remaining dimensions. This could be interesting for image completion, or for structured output prediction with real-valued outputs in general. I also wonder how expensive that would be.

In all cases, I'm looking forward to saying interesting applications and variations of this model in the future!

The last two years have seen a number of improvements in the field of language model pretraining, and BERT - Bidirectional Encoder Representations from Transformers - is the most recent entry into this canon. The general problem posed by language model pretraining is: can we leverage huge amounts of raw text, which aren’t labeled for any specific classification task, to help us train better models for supervised language tasks (like translation, question answering, logical entailment, etc)? Mechanically, this works by either 1) training word embeddings and then using those embeddings as input feature representations for supervised models, or 2) treating the problem as a transfer learning problem, and fine-tune to a supervised task - similar to how you’d fine-tune a model trained on ImageNet by carrying over parameters, and then training on your new task. Even though the text we’re learning on is strictly speaking unsupervised (lacking a supervised label), we need to design a task on which we calculate gradients in order to train our representations. For unsupervised language modeling, that task is typically structured as predicting a word in a sequence given prior words in that sequence. Intuitively, in order for a model to do a good job at predicting the word that comes next in a sentence, it needs to have learned patterns about language, both on grammatical and semantic levels. A notable change recently has been the shift from learning unconditional word vectors (where the word’s representation is the same globally) to contextualized ones, where the representation of the word is dependent on the sentence context it’s found in. All the baselines discussed here are of this second type. 

The two main baselines that the BERT model compares itself to are OpenAI’s GPT, and Peters et al’s ELMo. The GPT model uses a self-attention-based Transformer architecture, going through each word in the sequence, and predicting the next word by calculating an attention-weighted representation of all prior words. (For those who aren’t familiar, attention works by multiplying a “query” vector with every word in a variable-length sequence, and then putting the outputs of those multiplications into a softmax operator, which inherently gets you a weighting scheme that adds to one). ELMo uses models that gather context in both directions, but in a fairly simple way: it learns one deep LSTM that goes from left to right,  predicting word k using words 0-k-1, and a second LSTM that goes from right to left, predicting word k using words k+1 onward. These two predictions are combined (literally: just summed together) to get a representation for the word at position k. 

https://i.imgur.com/2329e3L.png

BERT differs from prior work in this area in several small ways, but one primary one: instead of representing a word using only information from words before it, or a simple sum of prior information and subsequent information, it uses the full context from before and after the word in each of its multiple layers. It also uses an attention-based Transformer structure, but instead of incorporating just prior context, it pulls in information from the full sentence. To allow for a model that actually uses both directions of context at a time in its unsupervised prediction task, the authors of BERT slightly changed the nature of that task: it replaces the word being predicted with the “mask” token, so that even with multiple layers of context aggregation on both sides, the model doesn’t have any way of knowing what the token is. By contrast, if it weren’t masked, after the first layer of context aggregation, the representations of other words in the sequence would incorporate information about the predicted word k, making it trivial, if another layer were applied on top of that first one, for the model to directly have access to the value it’s trying to predict. This problem can either be solved by using multiple layers, each of which can only see prior context (like GPT), by learning fully separate L-R and R-L models, and combining them at the final layer (like ELMo) or by masking tokens, and predicting the value of the masked tokens using the full remainder of the context. 

This task design crucially allows for a multi-layered bidirectional architecture, and consequently a much richer representation of context in each word’s pre-trained representation. BERT demonstrates dramatic improvements over prior work when fine tuned on a small amount of supervised data, suggesting that this change added substantial value.

Facebook has [released a series of papers](https://research.facebook.com/blog/learning-to-segment/) for object segmentation and detection. This paper is the first in that series.

This is how modern object detection works (think [RCNN](https://arxiv.org/abs/1311.2524), [Fast RCNN](http://arxiv.org/abs/1504.08083)):

1.  A rich set of object proposals (i.e., a set of image regions which are likely to contain an object) is generated using a fast (but possibly imprecise) algorithm.
2.  A CNN classifier is applied on each of the proposals.

The current paper improves the step 1, i.e., region/object proposals.

Most object proposals approaches fall into three categories: 
* Objectness scoring
* Seed Segmentation
* Superpixel Merging

Current method is different from these three. 
It share similarities with [Faster R-CNN](https://arxiv.org/abs/1506.01497) in that proposals are generated using a CNN.
The method predicts a segmentation mask given an input *patch* and assigns a score corresponding to how likely the patch is to contain an object.


## Model and Training

Both mask and score predictions are achieved with a single convolutional network but with multiple outputs. All the convolutional layers except the last few are from VGG-A pretrained model.

Each training sample is a triplet of RGB input patch, the binary mask corresponding to the input patch, a label which specifies whether the patch contains an object. A patch is given label 1 only if it satisfies the following constraints:
* the patch contains an object roughly centered in the input patch
* the object is fully contained in the patch and in a given scale range

Note that the network must output a mask for a single object at the center even when multiple objects are present.

Figure 1 shows the architecture and sampling for training.
![figure1](https://i.imgur.com/zSyP0ij.png)

Model is then jointly trained for segmentation and objectness. Negative samples are not used for segmentation.

## Inference

During full image inference, model is applied densely at multiple locations and scales.
This can be done efficiently since all computations are convolutional like in a fully convolutional network (FCN). 

![figure2](https://i.imgur.com/dQWfy8R.png)

This approach surpasses the previous state of the art by a large margin in both box and segmentation proposal generation. 

Mask RCNN takes off from where Faster RCNN left, with some augmentations aimed at bettering instance segmentation (which was out of scope for FRCNN). Instance segmentation was achieved remarkably well in *DeepMask* , *SharpMask* and later *Feature Pyramid Networks* (FPN).

Faster RCNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is most evident in how RoIPool , the de facto core operation for attending to instances, performs coarse spatial quantization for feature extraction. Mask RCNN fixes that by introducing RoIAlign in place of RoIPool.

#### Methodology

Mask RCNN retains most of the architecture of Faster RCNN. It adds the a third branch for segmentation. The third branch takes the output from RoIAlign layer and predicts binary class masks for each class.

##### Major Changes and intutions

**Mask prediction**

Mask prediction segmentation predicts a binary mask for each RoI using fully convolution - and the stark difference being usage of *sigmoid* activation for predicting final mask instead of *softmax*, implies masks don't compete with each other. This *decouples* segmentation from classification. The class prediction branch is used for class prediction and for calculating loss, the mask of predicted loss is used calculating Lmask.

Also, they show that a single class agnostic mask prediction works almost as effective as separate mask for each class, thereby supporting their method of decoupling classification from segmentation

**RoIAlign**

RoIPool first quantizes a floating-number RoI to the discrete granularity of the feature map, this quantized RoI is then subdivided into spatial bins which are themselves quantized, and finally feature values covered by each bin are aggregated (usually by max pooling). Instead of  quantization of the RoI boundaries
or bin bilinear interpolation is used to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and aggregate the result (using max or average).

**Backbone architecture**

Faster RCNN uses a VGG like structure for extracting features from image, weights of which were shared among RPN and region detection layers. Herein, authors experiment with 2 backbone architectures - ResNet based VGG like in FRCNN and ResNet based [FPN](http://www.shortscience.org/paper?bibtexKey=journals/corr/LinDGHHB16) based. FPN uses convolution feature maps from previous layers and recombining them to produce pyramid of feature maps to be used for prediction instead of single-scale feature layer (final output of conv layer before connecting to fc layers was used in Faster RCNN) 

**Training Objective**

The training objective looks like this 
![](https://i.imgur.com/snUq73Q.png)

Lmask is the addition from Faster RCNN. The method to calculate was mentioned above

#### Observation

Mask RCNN performs significantly better than COCO instance segmentation winners *without any bells and whiskers*. Detailed results are available in the paper