## Introduction

Two distinct research paradigms have studied how prior tasks or experiences can be used by an agent to inform future learning.

* Meta Learning:  past experience is used to acquire a prior over model parameters or a learning procedure, and typically studies a setting where a set of meta-training tasks are made available together upfront
* Online learning : a sequential setting where tasks are revealed one after another, but aims to attain zero-shot generalization without any task-specific adaptation.

We argue that neither setting is ideal for studying continual lifelong learning. Meta-learning deals with learning to learn, but neglects the sequential and non-stationary aspects of the problem. Online learning offers an appealing theoretical framework, but does not generally consider how past experience can accelerate adaptation to a new task.

## Online Learning

Online learning focuses on regret minimization. Most standard notion of regret is to compare to the cumulative loss of the best fixed model in hindsight:
https://i.imgur.com/pbZG4kK.png
One way minimize regret is with Follow the Leader (FTL):
https://i.imgur.com/NCs73vG.png

## Online Meta-learning Setting:

let $U_t$ be the update procedure for task $t$
e.g. in MAML:
https://i.imgur.com/Q4I4HkD.png


The overall protocol for the setting is as follows:
1. At round t, the agent chooses a model defined by $w_t$
2. The world simultaneously chooses task defined by $f_t$ 
3. The agent obtains access to the update procedure $U_t$, and uses it to update parameters as $\tilde w_t = U_t(w_t)$
4. The agent incurs loss $f_t(\tilde w_t )$. Advance to round t + 1.

the goal for the agent is to minimize regrets over rounds.
Achieving sublinear regrets means you're improving and converging to upper bound (joint training on all tasks)


## Algorithm and Analysis:

Follow the meta-leader (FTML): 
https://i.imgur.com/qWb9g8Q.png

FTML’s regret is sublinear (under some assumption)

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.

The paper designs some basic tests to compare saliency methods. It founds that some of the most popular methods are independent of model parameters and the data, meaning they are effectively useless.

## Methods compared

The paper compare the following methods: gradient explanation, gradient x input, integrated gradients, guided backprop, guided GradCam and SmoothGrad. They provide a refresher on those methods in the appendix.

All those methods can be put in the same framework. They require a classification model and an input (typically an image). The output of the method is an *explanation map* of the shape of the input where a higher value for a feature implies greater relevance in the decision of the model. 

## Metrics of comparison

The authors argue that visual inspection of the saliency maps can be misleading. They propose to compute the Spearman rank correlation, the structural similarity index (SSMI) and the Pearson correlation of the histogram of gradients. The authors point out that those metrics capture various notions of similarity, but it is an active area of research and those metrics are imperfect.

## First test: model parameters randomization

A saliency method must be dependent of model parameters, otherwise it cannot help us understand a model. In this test, the authors randomize the model parameters, layer per layer, starting from the top.

Surprisingly, methods such as guided backprop and guided gradcam are completely insensitive to model parameters, as illustrated on this Inception v3 trained on ImageNet:

![image](https://user-images.githubusercontent.com/8659132/61403152-b10b8000-a8a2-11e9-9f6a-cf1ed6a876cc.png)

Integrated gradients looks also dubious as the bird is still visible with a mostly fully randomized model, but the quantitative metrics reveal the difference is actually big between the two models.

## Second test: data randomization

It is well-known that randomly shuffling the labels of a dataset does not prevent a neural network from getting a high accuracy on the training set, though it does prevent generalization. The model is able to learn by either memorizing the data or finding spurious patterns. As a result, saliency maps obtained from such a network should have no clearly interpretable signal.

Here is the result for a ConvNet trained on MNIST and a shuffled MNIST:

![image](https://user-images.githubusercontent.com/8659132/61406757-7efe1c00-a8aa-11e9-9826-a859a373cb4f.png)

The results are very damning for most methods. Only gradients and GradCam are very different between both models, as confirmed by the low correlation.

## Discussion

- Even though some methods do no depend on model parameters and data, they might still depend on the architecture of the models, which could be of some use in some contexts.
- Methods that multiply the input with the gradient are dominated by the input.
- Complex saliency methods are just fancy edge detectors.
- Only gradient, smooth gradient and GradCam survives the sanity checks.

# Comments

- Why is their GradCam maps so ugly? They don't look like usual GradCam maps at all.
- Their tests are simple enough that it's hard to defend a method that doesn't pass them.
- The methods that are left are not very good either. They give fuzzy maps that are difficult to interpret.
- In the case of integrated gradients (IG), I'm not convinced this is sufficient to discard the method. IG requires a "baseline input" that represents the absence of features. In the case of images, people usually just set the image to 0, which is not at all the absence of a feature. The authors also use the "set the image to 0" strategy, and I'd say their tests are damning for this strategy, not for IG in general. I'd expect an estimation of the baseline such as done in [this paper](https://arxiv.org/abs/1702.04595) would be a fairer evaluation of IG.

Code: [GitHub](https://github.com/adebayoj/sanity_checks_saliency) (not available as of 17/07/19)

This paper builds upon the previous work in gradient-based meta-learning methods. 
The objective of meta-learning is to find meta-parameters ($\theta$) which can be "adapted" to yield "task-specific" ($\phi$) parameters.
Thus, $\theta$ and $\phi$ lie in the same hyperspace. 
A meta-learning problem deals with several tasks, where each task is specified by its respective training and test datasets. 
At the inference time of gradient-based meta-learning methods, before the start of each task, one needs to perform some gradient-descent (GD) steps initialized from the meta-parameters to obtain these task-specific parameters. 
The objective of meta-learning is to find $\theta$, such that GD on each task's training data yields parameters that generalize well on its test data. 

Thus, the objective function of meta-learning is the average loss on the training dataset of each task ($\mathcal{L}_{i}(\phi)$), where the parameters of that task ($\phi$) are obtained by performing GD initialized from the meta-parameters ($\theta$). 

\begin{equation}
F(\theta) = \frac{1}{M}\sum_{i=1}^{M} \mathcal{L}_i(\phi)
\end{equation}

In order to backpropagate the gradients for this task-specific loss function back to the meta-parameters, one needs to backpropagate through task-specific loss function ($\mathcal{L}_{i}$) and the GD steps (or any other optimization algorithm that was used), which were performed to yield $\phi$.
As GD is a series of steps, a whole sequence of changes done on $\theta$ need to be considered for backpropagation. 
Thus, the past approaches have focused on RNN + BPTT or Truncated BPTT. 

However, the author shows that with the use of the proximal term in the task-specific optimization (also called inner optimization), one can obtain the gradients without having to consider the entire trajectory of the parameters. 
The authors call these implicit gradients.
The idea is to constrain the $\phi$ to lie closer to $\theta$ with the help of proximal term which is similar to L2-regularization penalty term.
Due to this constraint, one obtains an implicit equation of $\phi$  in terms of $\theta$ as 
\begin{equation}
\phi = \theta - \frac{1}{\lambda}\nabla\mathcal{L}_i(\phi)
\end{equation}
This is then differentiated to obtain the implicit gradients as 

\begin{equation}
\frac{d\phi}{d\theta} = \big( \mathbf{I} + \frac{1}{\lambda}\nabla^{2} \mathcal{L}_i(\phi) \big)^{-1}
\end{equation}

and the contribution of gradients from $\mathcal{L}_i$ is thus, 
\begin{equation}
 \big( \mathbf{I} + \frac{1}{\lambda}\nabla^{2} \mathcal{L}_i(\phi) \big)^{-1} \nabla \mathcal{L}_i(\phi)
\end{equation}

The hessian in the above gradients are memory expensive computations, which become infeasible in deep neural networks.
Thus, the authors approximate the above term by minimizing the quadratic formulation using conjugate gradient method which only requires Hessian-vector products (cheaply available via reverse backpropagation).
\begin{equation}
\min_{\mathbf{w}} \mathbf{w}^\intercal \big( I + \frac{1}{\lambda}\nabla^{2} \mathcal{L}_i(\phi) \big) \mathbf{w} - \mathbf{w}^\intercal \nabla \mathcal{L}_i(\phi)
\end{equation} 

Thus, the paper introduces computationally cheap and constant memory gradient computation for meta-learning.

This paper deals with an important problem where a deep classification system is made explainable. After the (continuing) success of Deep Networks, researchers are trying to open the blackbox and this work is one of the foremosts. The authors explored the strength of a deep learning method (vision-language model) to explain the performance of another deep learning model (image classification). The approach jointly predicts a class label and explains why it predicted so in natural language.

The paper starts with a very important differentiation between two basic schools of *explnation* systems - the *introspection* explanation system and the *justification* explanation system. The introspection system looks into the model to get an explanation (e.g., "This is a Western Grebe because filter 2 has a high activation..."). On the other hand, a justification system justifies the decision by producing sentence details on how visual evidence is compatible with the system output (e.g., "This is a Western Grebe because it has red eyes..."). The paper focuses on *justification* explanation system and proposes a novel one.

The authors argue that unlike a description of an image or a sentence defining a class (not necessarily in presence of an image), visual explanation, conditioned on an input image, provides much more of an explanatory text on why the image is classified as a certain category mentioning only image relevant features. The broad outline of the approach is given in Fig (2) of the paper.
https://i.imgur.com/tta2qDp.png
The first stage consists of a deep convolutional network for classification which generates a softmax distribution over the classes. As the task handles fine-grained bird species classification, it uses a compact bilinear feature representation known to work well for the fine-grained classification tasks. The second stage is a stacked LSTM which generates natural language sentences or explanations justifying the decision of the first stage. The first LSTM of the stack receives the previously generated word. The second LSTM receives the output of the first LSTM along with image features and predicted label distribution from the classification network. This LSTM produces the sequence of output words until an "end-of-sentence" token is generated. The intuition behind using predicted label distribution for explanation is that it would inform the explanation generation model which words and attributes are more likely to occur in the description.

Two kinds of losses are used for the second stage *i.e.*, the language model. The first one is termed as the *Relevance Loss* which is the typical sentence generation loss that is seen in literature. This is the sum of cross-entropy losses of the generated words with respect to the ground truth words. Its role is to optimize the alignment between generated and ground truth sentences. However, this loss is not very effective in producing sentences which include class discriminative information. class specificity is a global sentence property. This is illustrated with the following example - *whereas a sentence "This is an all black bird with a bright red eye" is class specific to a "Bronzed Cowbird", words and phrases in the sentence, such as "black" or "red eye" are less class discriminative on their own.* As a result, cross entropy loss on individual words turns out to be less effective in capturing the global sentence property of which class specifity is an example. The authors address this issue by proposing an addiitonal loss, termed as the *Discriminative Loss* which is based on a reinforcement learning paradigm. Before computing the loss, a sentence is sampled. The sentence is passed through a LSTM-based classification network whose task is to produce the ground truth category $C$ given only the sampled sentence. The reward for this operation is simply the probability of the ground truth category $C$ given only the sentence. The intuition is - for the model to produce an output with a large reward, the generated sentence must include enough information to classify the original image properly. The *Discriminative Loss* is the expectation of the negative of this reward and a wieghted linear combination of the two losses is optimized during training.

My experience in reinforcement learning is limited. However, I must say I did not quite get why is sampling of the sentences required (which called for the special algorithm for backpropagation). If the idea is to see whether a generated sentence can be used to get at the ground truth category, could the last internal state of one of the stacked LSTM not be used? It would have been better to get some more intution behind the sampling operation. Another thing which (is fairly obvious but still I felt) is missing is not mentioning the loss used in the fine grained classification network.

The experimentation is rigorous. The proposed method is compared with four different baseline and ablation models - description, definition, explanation-label, explanation-discriminative with different permutation and combinations of the presence of two types losses, class precition informations etc. Also the evaluation metrics measure different qualities of the generated exlanations, specifically image and class relevances. To measure image relevance METEOR/CIDEr scores of the generated sentences with the ground truth (image based) explanations are computed. On the other hand, to measure the class relevance, CIDEr scores with class definition (not necessarily based on the images from the dataset) sentences are computed. The proposed approach has continuously shown better performance than any of the baseline or ablation methods. I'd specifically mention about one experiment where the effect of class conditioning is studies (end of Sec 5.2). The finding is quite interesting as it shows that providing or not providing correct class information has drastic effect at the generated explanations. It is seen that giving incorrect class information makes the explanation model hallucinate colors or attributes which are not present in the image but are specific to the class. This raises the question whether it is worth giving the class information when the classifier is poor on the first hand? But, I think the answer lies in the observation that row 5 (with class prediction information) in table 1 is always better than row 4 (no class prediction information). Since, row 5 is better than row 4, this means the classifier is also reasonable and this in turn implies that end-to-end training can improve all the stages of a pipeline which ultimately improves the overall performance of the system too!

In summary, the paper is a very good first step to explain intelligent systems and should encourage a lot more effort in this direction.