What the paper is about:
KeypointNet learns the optimal set of 3D keypoints and their 2D detectors for a specified downstream task. The authors demonstrate this by extracting 3D keypoints and their 2D detectors for the task of relative pose estimation across views. They show that, using keypoints extracted by KeypointNet, relative pose estimates are superior to ones that are obtained from a supervised set of keypoints.


Approach:
Training samples for KeypointNet comprise two views (images) of an object. The task is to then produce an ordered list of 3D keypoints that, upon orthogonal procrustes alignment, produce the true relative 3D pose across those views. The network has N heads, each of which extracts one (3D) keypoint (from a 2D image). There are two primary loss terms. A multi-view consistency loss measures the discrepancy between the two sets of extracted keypoints under the ground-truth transform. A relative-pose estimation loss penalizes the angular discrepency (under orthogonal procrustes) of the estimated transform using the extracted keypoints vs the GT transform. Additionally, they require keypoints to be distant from each other, and to lie within the object silhouette.

Catastrophic forgetting is the tendency of an neural network to forget previously learned information when learning new information. This paper combats that by keeping a buffer of experience and applying meta-learning to it. They call their new module Meta Experience Replay or MER.

How does this work? At each update they compute multiple possible updates to the model weights. One for the new batch of information and some more updates for batches of previous experience. Then they apply  meta-learning using the REPTILE algorithm, here the meta-model sees each possible update and has to predict the output which combines them with the least interference. This is done by predicting an update vector that maximizes the dot product between the new and old update vectors, that way it transfers as much learning as possible from the new update without interfering with the old updates. https://i.imgur.com/TG4mZOn.png

Does it work? Yes, while it may take longer to train, the results show that it generalizes better and needs a much smaller buffer of experience than the popular approach of using replay buffers.

## TL;DR

The paper presents a model-agnostic strategy to perform few-shot learning taking advantage of prior knowledge acquired during in multitask learning. Such prior knowledge derives from priors acquired about generalized model parameters (e.g. weights or hyperparameters) during the Model Agnostic Meta-Learning (MAML) algorithm. The strategy can be applied to any algorithm trained with gradient descent (not only neural networks) being more general and perhaps effective than transfer learning. It can loosely be referred to as "learning to learn".

## Why this is interesting

* Suitable in combination with any technique that uses gradient descent (supervised learning, reinforcement learning)
* Interesting idea: instead of further optimize existing models for performances, search a representation that can be subsequently tuned
* when only a few and diverse data is available, multiple tasks can be defined to harness the ability of the meta-model to learn while preserving generalization (see Experiments)

## Details

The key idea is performing the meta-learner update on a different data batch with respect to the parameters update(s) done for a single task. This leads   (formally) the same update procedure both for the learning and meta-learning phases of the algorithm (see Figure below) and provides a general framework for MAML. 

https://i.imgur.com/xq1wCai.png
image from [lilianweng post](https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html)

As [clearly worked out here](https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html), the method requires to compute the second derivatives for the outer-loop update. Surprisingly enough, omitting them and performing a first-order MAML does not sensibly affect the results according to the reported experiment. It is hypothesized that this is because ReLU networks are almost linear (and hence depends upon the actual network structure). 

## Experiments
### Supervised learning
1. regression from input to output of a sine wave. Amplitude and phase are varied among tasks. It is shown that MAML leads to good results and can generalize better than fine-tuning in the experiment conditions ("due to the often contradictory outputs on pre-training tasks". See Figure 2 in the paper)
2. few-shot image classification on Omniglot and MiniImageNet datasets (N, unseen, multiclass trained with K different instances). SOTA performance on the first dataset, and better-than SOTA on the second one where first-order MAML is also tested. 

### Reinforcement learning
1. 2D navigation: a single agent point must move to different positions (tasks). The model trained with MAML shows better performances, for the same number of gradient steps (Figure 4)
2. Locomotion: two simulated robots are provided with a set of tasks. MAML can learn a model that adapts much faster to new tasks (this is a case where pretraining is detrimental)
 
## Related work and resources
* official [gthub repo](https://github.com/cbfinn/maml)
* [videos](https://sites.google.com/view/maml) of the learned policies in MAML paper
* paper appendix: the part on the multi-task baseline is interesting
* [how to train your MAML](https://arxiv.org/abs/1810.09502): discusses various modifications to MAML to stabilize and improve performances
* [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://arxiv.org/abs/1909.09157)

The paper proposed a new object detection method to detect novel classes by using Conditional Matching. This detector can be conditioned on either image or text, which means a user can use an image or text to let the model detect the corresponding bounding boxes in the picture.

This model has 2 changes compared to other open-vocabulary detectors:

1) Other detectors rely on Region Proposal Network (RPN) which can not cover all the objects in a picture, so it will worsen the performance of detecting novel objects. So in this work, they use CLIP to detect novel objects, it is better than RPN because it uses queries as a reader to read the whole picture, then these queries can cover many objects in the picture.

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

2) Other detectors rely on Bipartite Matching to match between class label names and detected bounding boxes. But the downside of Bipartite Matching is that it can not match the novel objects with any label names because the novel objects do not have the labels. So, in this work, they proposed to use Conditional Matching which turns the matching problem into a binary matching problem. By using Conditional Matching, an object can be assigned to a "matched" or "not matched" label.

https://i.imgur.com/FjI2iub.png

#### Problem addressed: 
Learning recursive structure from natural data - sentences and images

#### Summary: 
This paper introduces recursive neural networks in order to learn recursive structure in data. This recursive structure is illustrated by using examples of scene understanding using superpixel labels and parsing of natural language sentences. The authors go on define a novel neural network architecture, an objective function based on max-margin estimation and provide methods for backpropagation to train this network. They then evaluate its performance for accuracy in pixel labelling on the Stanford background dataset as well as for parsing sentences of Wall Street Journal section of the Penn TreeBank database. They achieve state-of-the-art and near state-of-the-art results respectively.

#### Novelty:
Introduction of recursive neural networks, framing an objective function to learn a recursive tree structure from data
 
 State of the art results on scene understanding and pixel labels for Stanford background dataset

#### Drawbacks:
Computational analysis of method not provided Not many details about the backpropagation method.

#### Datasets:
Stanford background dataset, Penn TreeBank

#### Additional remarks:
The thesis of the first author, Chapter 3 was referred during presentation. This paper almost identical to that and the thesis provides slightly more details.

#### Resources:
paper: http://www-nlp.stanford.edu/pubs/SocherLinNgManning_ICML2011.pdf
 
 thesis: http://nlp.stanford.edu/~socherr/thesis.pdf

#### Presenter:
Bhargava U. Kota