The enhancement of 3D object detection is pivotal for precise environmental perception and improved task execution capabilities in autonomous driving. LiDAR point clouds, offering accurate depth information, serve as a crucial information for this purpose. Our study focuses on key challenges in 3D target detection. To tackle the challenge of expanding the receptive field of a 3D convolutional kernel, we introduce the Dynamic Feature Fusion Module (DFFM). This module achieves adaptive expansion of the 3D convolutional kernel's receptive field, balancing the expansion with acceptable computational loads. This innovation reduces operations, expands the receptive field, and allows the model to dynamically adjust to different object requirements. Simultaneously, we identify redundant information in 3D features. Employing the Feature Selection Module (FSM) quantitatively evaluates and eliminates non-important features, achieving the separation of output box fitting and feature extraction. This innovation enables the detector to focus on critical features, resulting in model compression, reduced computational burden, and minimized candidate frame interference. Extensive experiments confirm that both DFFM and FSM not only enhance current benchmarks, particularly in small target detection, but also accelerate network performance. Importantly, these modules exhibit effective complementarity.
相關內容
Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling linearly in the number of model components, which can be prohibitively expensive for SoTA Large Language Models (LLMs). We investigate Attribution Patching (AtP), a fast gradient-based approximation to Activation Patching and find two classes of failure modes of AtP which lead to significant false negatives. We propose a variant of AtP called AtP*, with two changes to address these failure modes while retaining scalability. We present the first systematic study of AtP and alternative methods for faster activation patching and show that AtP significantly outperforms all other investigated methods, with AtP* providing further significant improvement. Finally, we provide a method to bound the probability of remaining false negatives of AtP* estimates.
We address the problem of testing conditional mean and conditional variance for non-stationary data. We build e-values and p-values for four types of non-parametric composite hypotheses with specified mean and variance as well as other conditions on the shape of the data-generating distribution. These shape conditions include symmetry, unimodality, and their combination. Using the obtained e-values and p-values, we construct tests via e-processes, also known as testing by betting, as well as some tests based on combining p-values for comparison. Although we mainly focus on one-sided tests, the two-sided test for the mean is also studied. Simulation and empirical studies are conducted under a few settings, and they illustrate features of the methods based on e-processes.
We systematically evaluated the performance of seven large language models in generating programming code using various prompt strategies, programming languages, and task difficulties. GPT-4 substantially outperforms other large language models, including Gemini Ultra and Claude 2. The coding performance of GPT-4 varies considerably with different prompt strategies. In most LeetCode and GeeksforGeeks coding contests evaluated in this study, GPT-4 employing the optimal prompt strategy outperforms 85 percent of human participants. Additionally, GPT-4 demonstrates strong capabilities in translating code between different programming languages and in learning from past errors. The computational efficiency of the code generated by GPT-4 is comparable to that of human programmers. These results suggest that GPT-4 has the potential to serve as a reliable assistant in programming code generation and software development.
We study the problem of adaptive variable selection in a Gaussian white noise model of intensity $\varepsilon$ under certain sparsity and regularity conditions on an unknown regression function $f$. The $d$-variate regression function $f$ is assumed to be a sum of functions each depending on a smaller number $k$ of variables ($1 \leq k \leq d$). These functions are unknown to us and only few of them are nonzero. We assume that $d=d_\varepsilon \to \infty$ as $\varepsilon \to 0$ and consider the cases when $k$ is fixed and when $k=k_\varepsilon \to \infty$, $k=o(d)$ as $\varepsilon \to 0$. In this work, we introduce an adaptive selection procedure that, under some model assumptions, identifies exactly all nonzero $k$-variate components of $f$. In addition, we establish conditions under which exact identification of the nonzero components is impossible. These conditions ensure that the proposed selection procedure is the best possible in the asymptotically minimax sense with respect to the Hamming risk.
The deconfounder was proposed as a method for estimating causal parameters in a context with multiple causes and unobserved confounding. It is based on recovery of a latent variable from the observed causes. We disentangle the causal interpretation from the statistical estimation problem and show that the deconfounder in general estimates adjusted regression target parameters. It does so by outcome regression adjusted for the recovered latent variable termed the substitute. We refer to the general algorithm, stripped of causal assumptions, as substitute adjustment. We give theoretical results to support that substitute adjustment estimates adjusted regression parameters when the regressors are conditionally independent given the latent variable. We also introduce a variant of our substitute adjustment algorithm that estimates an assumption-lean target parameter with minimal model assumptions. We then give finite sample bounds and asymptotic results supporting substitute adjustment estimation in the case where the latent variable takes values in a finite set. A simulation study illustrates finite sample properties of substitute adjustment. Our results support that when the latent variable model of the regressors hold, substitute adjustment is a viable method for adjusted regression.
This paper presents a method for thematic agreement assessment of geospatial data products of different semantics and spatial granularities, which may be affected by spatial offsets between test and reference data. The proposed method uses a multi-scale framework allowing for a probabilistic evaluation whether thematic disagreement between datasets is induced by spatial offsets due to different nature of the datasets or not. We test our method using real-estate derived settlement locations and remote-sensing derived building footprint data.
Understanding a surgical scene is crucial for computer-assisted surgery systems to provide any intelligent assistance functionality. One way of achieving this scene understanding is via scene segmentation, where every pixel of a frame is classified and therefore identifies the visible structures and tissues. Progress on fully segmenting surgical scenes has been made using machine learning. However, such models require large amounts of annotated training data, containing examples of all relevant object classes. Such fully annotated datasets are hard to create, as every pixel in a frame needs to be annotated by medical experts and, therefore, are rarely available. In this work, we propose a method to combine multiple partially annotated datasets, which provide complementary annotations, into one model, enabling better scene segmentation and the use of multiple readily available datasets. Our method aims to combine available data with complementary labels by leveraging mutual exclusive properties to maximize information. Specifically, we propose to use positive annotations of other classes as negative samples and to exclude background pixels of binary annotations, as we cannot tell if they contain a class not annotated but predicted by the model. We evaluate our method by training a DeepLabV3 on the publicly available Dresden Surgical Anatomy Dataset, which provides multiple subsets of binary segmented anatomical structures. Our approach successfully combines 6 classes into one model, increasing the overall Dice Score by 4.4% compared to an ensemble of models trained on the classes individually. By including information on multiple classes, we were able to reduce confusion between stomach and colon by 24%. Our results demonstrate the feasibility of training a model on multiple datasets. This paves the way for future work further alleviating the need for one large, fully segmented datasets.
Exceptionally elegant formulae exist for the fractional Laplacian operator applied to weighted classical orthogonal polynomials. We utilize these results to construct a solver, based on frame properties, for equations involving the fractional Laplacian of any power, $s \in (0,1)$, on an unbounded domain in one or two dimensions. The numerical method represents solutions in an expansion of weighted classical orthogonal polynomials as well as their unweighted counterparts with a specific extension to $\mathbb{R}^d$, $d \in \{1,2\}$. We examine the frame properties of this family of functions for the solution expansion and, under standard frame conditions, derive an a priori estimate for the stationary equation. Moreover, we prove one achieves the expected order of convergence when considering an implicit Euler discretization in time for the fractional heat equation. We apply our solver to numerous examples including the fractional heat equation (utilizing up to a $6^\text{th}$-order Runge--Kutta time discretization), a fractional heat equation with a time-dependent exponent $s(t)$, and a two-dimensional problem, observing spectral convergence in the spatial dimension for sufficiently smooth data.
We derive sharp-interface models for one-dimensional brittle fracture via the inverse-deformation approach. Methods of Gamma-convergence are employed to obtain the singular limits of previously proposed models. The latter feature a local, non-convex stored energy of inverse strain, augmented by small interfacial energy, formulated in terms of the inverse-strain gradient. They predict spontaneous fracture with exact crack-opening discontinuities, without the use of damage (phase) fields or pre-existing cracks; crack faces are endowed with a thin layer of surface energy. The models obtained herewith inherit the same properties, except that surface energy is now concentrated at the crack faces. Accordingly, we construct energy-minimizing configurations. For a composite bar with a breakable layer, our results predict a pattern of equally spaced cracks whose number is given as an increasing function of applied load.
In recent years, object detection has experienced impressive progress. Despite these improvements, there is still a significant gap in the performance between the detection of small and large objects. We analyze the current state-of-the-art model, Mask-RCNN, on a challenging dataset, MS COCO. We show that the overlap between small ground-truth objects and the predicted anchors is much lower than the expected IoU threshold. We conjecture this is due to two factors; (1) only a few images are containing small objects, and (2) small objects do not appear enough even within each image containing them. We thus propose to oversample those images with small objects and augment each of those images by copy-pasting small objects many times. It allows us to trade off the quality of the detector on large objects with that on small objects. We evaluate different pasting augmentation strategies, and ultimately, we achieve 9.7\% relative improvement on the instance segmentation and 7.1\% on the object detection of small objects, compared to the current state of the art method on MS COCO.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191