This work attempts to use meta-learning to learn an update rule for a reinforcement learning agent. In this context, "learning an update rule" means learning the parameters of an LSTM module that takes in information about the agent's recent reward and current model and outputs two values - a scalar and a vector - that are used to update the agent's model. I'm not going to go too deep into meta-learning here, but, at a high level, meta learning methods optimize parameters governing an agent's learning, and, over the course of many training processes over many environments, optimize those parameters such that the reward over the full lifetime of training is higher. 

To be more concrete, the agent in a given environment learns two things: 

- A policy, that is, a distribution over predicted action given a state.
- A "prediction vector". This fits in the conceptual slot where most RL algorithms would learn some kind of value or Q function, to predict how much future reward can be expected from a given state. However, in this context, this vector is *very explicitly* not a value function, but is just a vector that the agent-model generates and updates. The notion here is that maybe our human-designed construction of a value function isn't actually the best quantity for an agent to be predicting, and, if we meta-learn, we might find something more optimal. I'm a little bit confused about the structure of this vector, but I think it's *intended* to be a categorical 1-of-m prediction

At each step, after acting in the environment, the agent passes to an LSTM: 

- The reward at the step
- A binary of whether the trajectory is done
- The discount factor
- The probability of the action that was taken from state t
- The prediction vector evaluated at state t
- The prediction vector evaluated at state t+1

Given that as input (and given access to its past history from earlier in the training process), the LSTM predicts two things: 

- A scalar, pi-hat
- A prediction vector, y-hat

These two quantities are used to update the existing policy and prediction model according to the rule below.

https://i.imgur.com/xx1W9SU.png

 Conceptually, the scalar governs whether to increase or decrease probability assigned to the taken action under the policy, and y-hat serves as a target for the prediction vector to be pulled towards.  An important thing to note about the LSTM structure is that none of the quantities it takes as input are dependent on the action or observation space of the environment, so, once it is learned it can (hopefully) generalize to new environments. 

Given this, the basic meta learning objective falls out fairly easily - optimize the parameters of the LSTM to maximize lifetime reward, taken in expectation over training runs.  However, things don't turn out to be quite that easy. The simplest version of this meta-learning objective is wildly unstable and difficult to optimize, and the authors had to add a number of training hacks in order to get something that would work. (It really is dramatic, by the way, how absolutely essential these are to training something that actually learns a prediction vector). These include: 

- A entropy bonus, pushing the meta learned parameters to learn policies and prediction vectors that have higher entropy (which is to say: are less deterministic)
- An L2 penalty on both pi-hat and y-hat
- A removal of the softmax that had originally been originally taken over the k-dimensional prediction vector categorical, and switching that target from a KL divergence to a straight mean squared error loss. As far as I can tell, this makes the prediction vector no longer actually a 1-of-k categorical, but instead just a continuous vector, with each value between 0 and 1, which makes it make more sense to think of k separate binaries? This I was definitely confused about in the paper overall

https://i.imgur.com/EL8R1yd.png

With the help of all of these regularizers, the authors were able to get something that trained, and that appeared to be able to perform comparably to or better than A2C - the human-designed baseline - across the simple grid-worlds it was being trained in. However, the two most interesting aspects of the evaluation were: 

1. The authors showed that, given the values of the prediction vector, you could predict the true value of a state quite well, suggesting that the vector captured most of the information about what states were high value. However, beyond that, they found that the meta-learned vector was able to be used to predict the value calculated with discount rates different that than one used in the meta-learned training, which the hand-engineered alternative, TD-lambda, wasn't able to do (it could only well-predict values at the same discount rate used to calculate it). This suggests that the network really is learning some more robust notion of value that isn't tied to a specific discount rate. 

2. They also found that they were able to deploy the LSTM update rule learned on grid worlds to Atari games, and have it perform reasonably well - beating A2C in a few cases, though certainly not all. This is fairly impressive, since it's an example of a rule learned on a different, much simpler set of environments generalizing to more complex ones, and suggests that there's something intrinsic to Reinforcement Learning that it's capturing

The paper proposes a method to perform joint instance and semantic segmentation. The method is fast as it is meant to run in an embedded environment (such as a robot). While the semantic map may seem redundant given the instance one, it is not as semantic segmentation is a key part of obtaining the instance map.

# Architecture

![image](https://user-images.githubusercontent.com/8659132/63187959-24cdb380-c02e-11e9-9121-77e0923e91c6.png)

The image is first put through a typical CNN encoder (specifically a ResNet derivative), followed by 3 separate decoders. The output of the decoder is at a low resolution for faster processing.

Decoders:
- Semantic segmentation: coupled with the encoder, it's U-Net-like. The output is a segmentation map.
- Instance center: for each pixel, outputs the confidence that it is the center of an object.
- Embedding: for each pixel, computes a 32 dimensional embedding. This embedding must have a low distance to embedding of other pixels of the same instance, and high distance to embedding of other pixels.

To obtain the instance map, the segmentation map is used to mask the other 2 decoder outputs to separate the embeddings and centers of each class. Centers are thresholded at 0.7, and centers with embedding distances lower than a set amount are discarded, as they are considered duplicates.

Then for each class, a similarity matrix is computed between all pixels from that class and centers from that class. Pixels are assigned to their closest centers, which represent different instances of the class.

Finally, the segmentation and instance maps are upsampled using the SLIC algorithm.

# Loss

There is one loss for each decoder head.
- Semantic segmentation: weighted cross-entropy
- Instance center: cross-entropy term modulated by a $\gamma$ parameter to counter the over-representation of the background over the target classes.
![image](https://user-images.githubusercontent.com/8659132/63286485-22659680-c286-11e9-9134-f1b823a34217.png)

- Embedding: composed of 3 parts, an attracting force between embeddings of the same instance, a repelling force between embeddings of different instances, and a l2 regularization on the embedding.
![image](https://user-images.githubusercontent.com/8659132/63286399-f1856180-c285-11e9-9136-feb6c4a555e5.png)
![image](https://user-images.githubusercontent.com/8659132/63286411-fcd88d00-c285-11e9-939f-0771579d8263.png)
$\hat{e}$ are the embeddings, $\delta_a$ is an hyper-parameter defining "close enough", and $\delta_b$ defines "far enough"

The whole model is trained jointly using a weighted sum of the 3 losses.

# Experiments and results

The authors test their method on the Cityscape dataset, which is composed of 5000 annotated images and 8 instance classes. They compare their methods both for semantic segmentation and instance segmentation.

![image](https://user-images.githubusercontent.com/8659132/63287573-a882dc80-c288-11e9-83e0-b352e43bdf28.png)

For semantic segmentation, their method is ok, though ENet for example performs better on average and is much faster.

![image](https://user-images.githubusercontent.com/8659132/63287643-d700b780-c288-11e9-9d40-5bcaf695a744.png)

On the other hand, for instance segmentation, their method is much faster than the other while still performing well. Not SOTA on performance, but considering the real-time constraint, it's much better.

# Comments

- Most instance segmentation methods tend to be sluggish and overly complicated. This approach is much more elegant in my opinion.
- If they removed the aggressive down/up sampling, I wonder if they would beat MaskRCNN and PANet.
- I'm not sure what's the point of upsampling the semantic map given that we already have the instance map.

Contrastive learning works by performing augmentations on a batch of images, and training a network to match the representations of the two augmented parts of a pair together, and push the representations of images not in a pair farther apart. Historically, these algorithms have benefitted from using stronger augmentations, which has the effect of making the two positive elements in a pair more visually distinct from one another. This paper tries to build on that success, and, beyond just using a strong augmentation, tries to learn a way to perturb images that adversarially increases contrastive loss. As with adversarial training in normal supervised setting, the thinking here is that examples which push loss up the highest are the hardest and thus most informative for the network to learn from 

While the concept of this paper made some sense, I found the notation and the explanation of mechanics a bit confusing, particularly when it came to choice to frame a contrastive loss as a cross-entropy loss, with the "weights" of the dot product in the the cross-entropy loss being, in fact, the projection by the learned encoder of various of the examples in the batch. 

https://i.imgur.com/iQXPeXk.png

This notion of the learned representations being "weights" is just odd and counter-intuitive, and the process of trying to wrap my mind around it isn't one I totally succeeded at. I think the point of using this frame is because it provides an easy analogue to the Fast Gradient Sign Method of normal supervised learning adversarial examples, even though it has the weird effect that, as the authors say "your weights vary by batch...rather than being consistent across training," 

Notational weirdness aside, my understanding is that the method of this paper: 

- Runs a forward pass of normal contrastive loss (framed as cross-entropy loss) which takes augmentations p and q and runs both forward through an encoder.
- Calculates a delta to apply to each input image in the q that will increase the loss most, taken over all the images in the p set
    - I think the delta is per-image in q, and is just aggregated over all images in p, but I'm not fully confident of this, as a result of notational confusion. It could also be one delta applied for all all images in q.
- Calculate the loss that results when you run forward the adversarially generated q against the normal p
- Train a combined loss that is a weighted combination of the normal p/q contrastive part and the adversarial p/q contrastive part

https://i.imgur.com/UWtJpVx.png

The authors show a small but relatively consistent improvement to performance using their method. Notably, this improvement is much stronger when using larger encoders (presumably because they have more capacity to learn from harder examples). One frustration I have with the empirics of the paper is that, at least in the main paper, they don't discuss the increase in training time required to calculate these perturbations, which, a priori, I would imagine to be nontrivial.

Predict frames of a video using 3 newly proposed and complementary methods:
1. Multi scale cnn
2. GAN
3. Image gradient difference loss


Datasets:
-----------
* UCF101
* Sports1M


GAN
------
Generator:
   * Input: several frames of video from dataset
   * output: next frame of video

Discriminator:
   * input: original and last frame
   * output: is the last frame from dataset or generated

Problem: Still blurry on edges on moving object.
Solution: Image gradient difference loss

Szegedy et al. were (to the best of my knowledge) the first to describe the phenomen of adversarial examples as researched today. Specifically, they described the main objective in order to obtain adversarial examples as

$\arg\min_r \|r\|_2$ s.t. $f(x+r)=l$ and $x+r$ being a valid image

where $f$ is the neural network and $l$ the target class (i.e. targeted adversarial example). In the paper, they originally headlined the section by “blind spots in neural networks”. While they give some explanation and provide experiments, also introducing the notion of transferability of adversarial examples and an idea of adversarial examples used as regularization during training, many questions are left open. The given conclusion, that these adversarial examples are highly unlikely and that these examples lie dense within regular training examples are controversial in the literature.