C.2 Consolidated CV with random features Alternatively, one can use random features (Rahimi and Recht, 2007) to approximate the kernel matrix. Suppose that we consider shift-invariant kernels that satisfy K(x,y) = K(x y). In this work we use the radial kernel K(x,y) = exp( σ x y 22). The kernel can be approximated by K(x,y) φ(x),φ(y), where an explicit randomized feature mapping φ: IRp IRm is obtained by sampling from a distribution defined by the inverse Fourier transformation.

On the construction of almost uniformly convergent random variables with given weakly convergent image laws.

We study the problem of designing mechanisms when agents' valuation functions are drawn from unknown and correlated prior distributions. In particular, we are given a prior distribution D, and we are interested in designing a (truthful) mechanism that has good performance for all "true distributions" that are close to Din Total Variation (TV) distance. We show that DSIC and BIC mechanisms in this setting are strongly robust with respect to TV distance, for any bounded objective function O, extending a recent result of Brustle et al. ([BCD20], EC 2020). At the heart of our result is a fundamental duality property of total variation distance. As direct applications of our result, we (i) demonstrate how to find approximately revenue-optimal and approximately BIC mechanisms for weakly dependent prior distributions; (ii) show how to find correlation-robust mechanisms when only "noisy" versions of marginals are accessible, extending recent results of Bei et.

Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are "small" but "realistic" semantic changes of the image changing the classifier decision. Current approaches for the generation of VCEs are restricted to adversarially robust models and often contain non-realistic artefacts, or are limited to image classification problems with few classes. In this paper, we overcome this by generating Diffusion Visual Counterfactual Explanations (DVCEs) for arbitrary ImageNet classifiers via a diffusion process. Two modifications to the diffusion process are key for our DVCEs: first, an adaptive parameterization, whose hyperparameters generalize across images and models, together with distance regularization and late start of the diffusion process, allow us to generate images with minimal semantic changes to the original ones but different classification. Second, our cone regularization via an adversarially robust model ensures that the diffusion process does not converge to trivial non-semantic changes, but instead produces realistic images of the target class which achieve high confidence by the classifier.

We propose two methods for text-image alignmentchair on the porch of the evaluation: VQ2 and VNLI, demonstrated with example pairs.

As the perception range of LiDAR increases, LiDAR-based 3D object detection becomes a dominant task in the long-range perception task of autonomous driving. The mainstream 3D object detectors usually build dense feature maps in the network backbone and prediction head. However, the computational and spatial costs on the dense feature map are quadratic to the perception range, which makes them hardly scale up to the long-range setting. To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD). The computational and spatial cost of FSD is roughly linear to the number of points and independent of the perception range. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module.

For the synthetic-to-real domain generalization (DG), we use one of the synthetic datasets (GTAV [12] or SYNTHIA [13]) as the source domain and evaluate the model performance on three real-world datasets (CityScapes [2], BDD-100K [16], and Mapillary [11]). GTAV [12] contains 24,966 images with the size of 1914 1052. It is splited into 12,403, 6,382, and 6,181 images for training, validating, and testing. SYNTHIA [13] contains 9,400 images of 960 720, where 6,580 images are used for training. We use the validation sets of the three real-world datasets for evaluation.