Opening the paper…
Deep Learning for Computer Vision, End Term
Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these would be more complex or learned; for simplicity, we provide them here):
Calculate the query, key and value vectors for each word?
Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these would be more complex or learned; for simplicity, we provide them here): $$\text{Word}_1 = \begin{bmatrix} 1 & 0 & 0 \end{bmatrix}, \quad \text{Word}_2 = \begin{bmatrix} 0 & 1 & 0 \end{bmatrix}$$ $$W_Q = \begin{bmatrix} 2 & 0 & 2 \\ 2 & 0 & 0 \\ 2 & 1 & 2 \end{bmatrix}, \quad W_K = \begin{bmatrix} 2 & 2 & 2 \\ 0 & 2 & 1 \\ 0 & 1 & 1 \end{bmatrix}, \quad W_V = \begin{bmatrix} 1 & 1 & 0 \\ 0 & 1 & 1 \\ 0 & 0 & 0 \end{bmatrix}$$ Calculate the query, key and value vectors for each word? What is the role of the Gaussian blur in the Canny edge detection algorithm, and how does the choice of the standard deviation parameter affect the performance of edge detection? Which option do you think best describes the role of the Gaussian blur and its relationship with the standard deviation parameter in the Canny edge detection algorithm? Which property of the SIFT descriptor is primarily responsible for its resilience to changes in scale, viewpoint, and illumination?