Modeling Conceptual Understanding in Image Reference Games · Learning via Explanation Lombrozo...

Modeling Conceptual Understanding in Image Reference Games

Prof. Dr. Zeynep Akata

Interpretable ML Tutorial at CVPR 2020

15 June 2020

1

Outline

Background: Explanation and Learning Are Related

Modeling Conceptual Understanding With Image Reference Games

Conclusion: Explaining Through Communication Is Exciting

2

Outline




3

Learning via Explanation Lombrozo TICS’16

4


4


4


4


4

Attributes as Explanations Lampert et al. CVPR’09

attributes classes

Red crownOrange bellyBlack eyes

Blue crownWhite bellyBlack eyes

Eastern bluebird

[1 1 1 0 0]

Cardinal[0 0 1 1 1]

images

5


attributes classes



Eastern bluebird

[1 1 1 0 0]

Cardinal[0 0 1 1 1]

images

5


attributes classes



Eastern bluebird

[1 1 1 0 0]

Cardinal[0 0 1 1 1]

images

5

Natural Language as Explanations for Communication

6


What type of bird is this?

6



It is a Cardinal


It is a Cardinal because it is a red bird with a red beak and a black face

Why not a Vermilion

Flycatcher?

It is not a Vermilion Flycatcher because it does not have black wings.

6




6




Why not a Vermilion

Flycatcher?

6




Why not a Vermilion

Flycatcher?

It is not a Vermilion Flycatcher because it does not have black wings.

6

Grounding Visual Explanations Hendricks et al. ECCV’16 & ECCV’18

Explanation Sampler

This red bird has a red beak and a black face.

7


Explanation Sampler

attribute chunker


Explanation Grounder

red birdred beak

black face

7


Explanation Sampler

attribute chunker

attribute chunker


This red bird has a black beak and a black face.

Explanation Grounder

red birdblack beak

black face

red birdred beak

black face

7


Explanation Sampler

1.02

attribute chunker

2.05

attribute chunker


This red bird has a black beak and a black face.

Phrase-CriticExplanation Grounder

red beak black

facered bird

black face

red birdblack beak

red birdblack beak

black face

red birdred beak

black face

7

Rational Quantitative Attribution of Beliefs, Desires and Percepts inHuman Mentalizing Baker et al. Nature’17

8


8


8


8

Machine Theory of Mind Rabinowitz et al. ICML’18

9


9


9


9

M3RL: Mind-aware Multi-agent Management ReinforcementLearning Shu et al. ICLR’19

10


10


10

Outline




11

Image Reference Games with Failure in Concept Understanding

Round

Red ???

12


Round

Red ???

12


RoundRed ???

12

Modeling Conceptual Understanding Corona, Alaniz, Akata NeurIPS’19

Speaker Listener (color-blind)

Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Cone beak

Yellow feet

Red beak

Red beak

Cone beak

Yellow feetCone beakRed beak

Yellow feetCone beak

Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

13



Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

13



Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

= Cone beak Red beak

Cone beak

Yellow feet

Red beak-Yellow feet

Cone beak

13



Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

13

Perceptual Modules (PM)


Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

1. Extract image-level features using a CNN

2. Predict attribute-level features

φ(x) = f(CNN(x))

• each element in φ(x) ∈ [0, 1]|A|

represents a separate attribute

• |A|: # of visual attribute labels

• Speaker is one: φS ,Multiple listeners: φL

attributes classes



Eastern bluebird

[1 1 1 0 0]

Cardinal[0 0 1 1 1]

images

14

Perceptual Modules (PM)


Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

1. Extract image-level features using a CNN

2. Predict attribute-level features

φ(x) = f(CNN(x))

• each element in φ(x) ∈ [0, 1]|A|

represents a separate attribute

• |A|: # of visual attribute labels

• Speaker is one: φS ,Multiple listeners: φL

attributes classes



Eastern bluebird

[1 1 1 0 0]

Cardinal[0 0 1 1 1]

images

14

Agent Embedding (AE)

Speaker: Select attribute ak from

zas = φaS(xkt )− φaS(xkc ).

Listener: Select attribute ak from

zal = φaL(xkt )− φaL(xkc ).

receives reward rk ∈ {−1, 1}


Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

AE module: LSTM, AE hk: LSTM hidden state

hk = LSTM(hk−1, ok)

ok: One-hot vector, the index of the non-zero entryis ak and its value is rk.

15

Agent Embedding (AE)

Speaker: Select attribute ak from

zas = φaS(xkt )− φaS(xkc ).

Listener: Select attribute ak from

zal = φaL(xkt )− φaL(xkc ).

receives reward rk ∈ {−1, 1}


Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

AE module: LSTM, AE hk: LSTM hidden state

hk = LSTM(hk−1, ok)

ok: One-hot vector, the index of the non-zero entryis ak and its value is rk.

15

Policy Learning


Red beak


-

Reward

“It’s image ”

+1 -1Agent

Embedding

= Cone beak

Red beak

Cone beak

Yellow feetRed beak

Cone beak

Cone beak

Yellow feetRed beak

Cone beakRed beak

Yellow feet

Cone beak

Yellow feet

Yellow feet

Red beak

Red beak

Cone beak



Red beak-

Red beakYellow feet

Cone beak

Yellow feet

Yellow feet

Cone beak

or

-

Agent Embedding

Reward

“It’s image ”

+1 -1


Cone beak

Yellow feet


Cone beak

Concatenate image-pair difference and AE

sk =[φ(xkt )− φ(xkc );hk

]Predict V (sk, ak) of using ak to describe xkt :

LV =1

N +M

∑N+M

MSE(V (sk, ak), rk)

16

Policy Learning: Different Policies Implemented Here

1. Epsilon Greedy Policy: Randomly sample ak with prob. ε or greedily choose ak

ak = argmaxa∈A

V (sk, a)

2. Active Policy: Train using policy gradient

La =1

N

∑N

−R log πS(st, at) with R = − 1

M

∑M

MSE(V (sk, ak), rk) (1)

3. Random Agent policy: Always select ak at random4. Reactive policy: Select ak at random, if rk = −1 sample a different ak5. Random Sampling: Select ak at random during N + greedy during M

17

Comparing Learned Policies vs Baselines

18


18


18


18

Showing Necessity of Agent Embeddings

19

Evaluating Cluster Quality

1. Generate AE in 50K episodes

2. Perform K-Means on AE: C ′ (GT = C)

3. Evaluate: variation of information (VI)

V I(C,C ′) = H(C) +H(C ′)− 2I(C,C ′)

where H: entropy, I: mutual information

• V I measures amount of informationneeded to switch from C to C ′

20

Modeling Conceptual Understanding Qualitative Results

21


21


21

Outline




22

Conclusions

Modeling conceptual understanding is necessary to succeed in some tasks

1. Formulation for modeling other agents’ understanding

2. Allows XAI systems to tailor their explanations to the specific users

3. Learned AEs recovers a clustering over other agents’ conceptual understanding

Modeling Conceptual Understanding in Image Reference GamesRodolfo Corona, Stephan Alaniz and Zeynep Akata

published at NeurIPS 2019

23

Baker, C. L., Jara-Ettinger, J., Saxe, R., and Tenenbaum, J. B. (2017).

Rational quantitative attribution of beliefs, desires and percepts in human mentalizing.

Nature Human Behaviour, 1.

Christoph H. Lampert, H. N. and Harmeling, S. (2014).

Attribute-based classification for zero-shot visual object categorization.

IEEE TPAMI.

Corona, R., Alaniz, S., and Akata, Z. (2019).

Modeling conceptual understanding in image reference games.

In Neural Information Processing Systems (NeurIPS).

Hendricks, L.-A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., and Darrell, T. (2016).

Generating visual explanations.

In European Conference of Computer Vision (ECCV).

Hendricks, L. A., Hu, R., Darrell, T., and Akata, Z. (2018).

Grounding visual explanations.

In European Conference of Computer Vision (ECCV).

24

Lombrozo, T. (2016).

Explanatory preferences shape learning and inference.

In Trends in Cognitive Science.

Rabinowitz, N., Perbet, F., Song, F., Zhang, C., Eslami, S. M. A., and Botvinick, M. (2018).

Machine theory of mind.

In ICML.

Reed, S., Akata, Z., Lee, H., and Schiele, B. (2016).

Learning deep representations of fine-grained visual descriptions.

In IEEE Computer Vision and Pattern Recognition (CVPR).

Shu, T. and Tian, Y. (2019).

M3RL: Mind-aware multi-agent management reinforcement learning.

In ICLR.

Thank you!

25

Date post:	27-Aug-2020
Category:	Documents
Upload:	others
View:	0 times
Download:	0 times

Modeling Conceptual Understanding in Image Reference Games · Learning via Explanation Lombrozo...

Documents