[Retracted] Identifying Animals in Camera Trap Images via Neural Architecture Search

Figure 3

Inner structure of a normal cell in a candidate network. This figure illustrates the inner structure of the i th normal cell denoted by a large rectangle with the upper-left corner labelled “cell i”. A normal cell consists of operations grouped as blocks, and there are B blocks represented by smaller rectangles with upper-left corners labelled “block 1” … “block B”. The number of operations in a block is dynamically determined by the sample during the search, and this dynamic number is represented by “…” between two operations in each block. The input of an operation is also dynamically determined by the sampler, and the input is usually sampled from previous cells or blocks, which means outputs of cells or blocks may serve as operation inputs. The cell output is denoted by an arrow emitting from the cell, and an operation output is represented by an arrow emitting from the operation. Outputs of operations not serving as inputs of any other operations are summed to yield the block output, the sum is represented by a rectangle labelled “add”, and the block output is denoted by an arrow emitting from the rectangle. The input and output relationship among both blocks and cells is represented by a cloud labelled “Cell i connection”.