Previousworkseitheruse zeroth-order optimization, which is slow when the set of parameters increases, or rely on a differentiable proxy of the target finishing pipeline, which is hard to train.

Manyapplicationsinmachine learning relyongradient-based optimization, oratleasttheefficient calculation of derivatives of models expressed as computer programs. Researchers have a wide variety of tools from which they can choose, particularly if they are using the Python language [21,16,24,2,1].

Neural Information Processing Systems http://nips.cc/

We also conduct empirical experiments to verify the effectiveness of those perturbations. As shown in Fig. A1, all of the perturbed text-features In addition, now that every perturbation can directly produce the description ( i.e., text-feature) of And the results are shown in Tab. OOD performance when the ID data is shifted. Table A2: Additionally improved ID accuracy on shifted datasets. Fig. A2, compared to the shifted ImageNet-A [ Sketch only preserve objects' shape and main texture, while the color information is totally vanished.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/