Canada

BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However, taking the noises in camera parameters and LiDAR scans into consideration, we usually obtain BEV representation with harmful noises. Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to utilize the diffusion model to get a better BEV representation. In this work, we propose an end-to-end framework, named DiffBEV, to exploit the potential of diffusion model to generate a more comprehensive BEV representation. To the best of our knowledge, we are the first to apply diffusion model to BEV perception. In practice, we design three types of conditions to guide the training of the diffusion model which denoises the coarse samples and refines the semantic feature in a progressive way. What&#39;s more, a cross-attention module is leveraged to fuse the context of BEV feature and the semantic content of conditional diffusion model. DiffBEV achieves a 25.9% mIoU on the nuScenes dataset, which is 6.2% higher than the best-performing existing approach. Quantitative and qualitative results on multiple benchmarks demonstrate the effectiveness of DiffBEV in BEV semantic segmentation and 3D object detection tasks. The code will be available soon.

AAAI 2024

DiffBEV: Conditional Diffusion Model for Bird’s Eye View Perception

scene analysis & understanding

diffusion model

3d computer vision

autonomous driving

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However, taking the noises in camera parameters and LiDAR scans into consideration, we usually obtain BEV representation with harmful noises. Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to utilize the diffusion model to get a better BEV representation. In this work, we propose an end-to-end framework, named DiffBEV, to exploit the potential of diffusion model to generate a more comprehensive BEV representation. To the best of our knowledge, we are the first to apply diffusion model to BEV perception. In practice, we design three types of conditions to guide the training of the diffusion model which denoises the coarse samples and refines the semantic feature in a progressive way. What's more, a cross-attention module is leveraged to fuse the context of BEV feature and the semantic content of conditional diffusion model. DiffBEV achieves a 25.9% mIoU on the nuScenes dataset, which is 6.2% higher than the best-performing existing approach. Quantitative and qualitative results on multiple benchmarks demonstrate the effectiveness of DiffBEV in BEV semantic segmentation and 3D object detection tasks. The code will be available soon.

technical paper

Traditional machine learning is generally treated as a black-box optimization problem and does not typically produce interpretable functions that connect inputs and outputs. However, the ability to discover such interpretable functions is desirable. In this work, we propose GINN-LP, an interpretable neural network to discover the form and coefficients of the underlying equation of a dataset, when the equation is assumed to take the form of a multivariate Laurent Polynomial. This is facilitated by a new type of interpretable neural network block, named the “power-term approximator block”, consisting of logarithmic and exponential activation functions. GINN-LP is end-to-end differentiable, making it possible to use backpropagation for training. We propose a neural network growth strategy that will enable finding the suitable number of terms in the Laurent polynomial that represents the data, along with sparsity regularization to promote the discovery of concise equations. To the best of our knowledge, this is the first model that can discover arbitrary multivariate Laurent polynomial terms without any prior information on the order. Our approach is first evaluated on a subset of data used in SRBench, a benchmark for symbolic regression. We first show that GINN-LP outperforms the state-of-the-art symbolic regression methods on datasets generated using 48 real-world equations in the form of multivariate Laurent polynomials. Next, we propose an ensemble method that combines our method with a high-performing symbolic regression method, enabling us to discover non-Laurent polynomial equations. We achieve state-of-the-art results in equation discovery, showing an absolute improvement of 7.1% over the best contender, by applying this ensemble method to 113 datasets within SRBench with known ground-truth equations.

GINN-LP: A Growing Interpretable Neural Network for Discovering Multivariate Laurent Polynomial Equations

3D semantic occupancy has garnered considerable attention due to its abundant structural information encompassing the entire scene in autonomous driving.
However, existing 3D occupancy prediction methods contend with the constraint of low-resolution 3D voxel features arising from the limitation of computational memory.
To address this limitation and achieve a more fine-grained representation of 3D scenes, we propose OctOcc, a novel octree-based approach for 3D semantic occupancy prediction. 
OctOcc is conceptually rooted in the observation that the vast majority of 3D space is left unoccupied. 
Capitalizing on this insight, we endeavor to cultivate memory-efficient high-resolution 3D occupancy predictions by mitigating superfluous cross-attentions. 
Specifically, we devise a hierarchical octree structure that selectively generates finer-grained cross-attentions solely in potentially occupied regions.
Extending our inquiry beyond 3D space, we identify analogous redundancies within another side of cross attentions, 2D images.
Consequently, a 2D image feature filtering network is conceived to expunge extraneous regions.
Experimental results demonstrate that the proposed OctOcc significantly outperforms existing methods on nuScenes and SemanticKITTI datasets with limited memory consumption.

OctOcc: High-Resolution 3D Occupancy Prediction with Octree | VIDEO

Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes. This issue primarily stems from the model being trained on pairs of single-scale images and their corresponding text descriptions. Moreover, direct training on images of unlimited sizes is unfeasible, as it would require an immense number of text-image pairs and entail substantial computational expenses. To overcome these challenges, we propose a two-stage pipeline named Any-Size-Diffusion (ASD), designed to efficiently generate well-composed images of any size, while minimizing the need for high-memory GPU resources. Specifically, the initial stage, dubbed Any Ratio Adaptability Diffusion (ARAD), leverages a selected set of images with a restricted range of ratios to optimize the text-conditional diffusion model, thereby improving its ability to adjust composition to accommodate diverse image sizes. To support the creation of images at any desired size, we further introduce a technique called Fast Seamless Tiled Diffusion (FSTD) at the subsequent stage. This method allows for the rapid enlargement of the ASD output to any high-resolution size, avoiding seaming artifacts or memory overloads. Experimental results on the LAION-COCO and MM-CelebA-HQ benchmarks demonstrate that ASD can produce well-structured images of arbitrary sizes, cutting down the inference time by 2X compared to the traditional tiled algorithm. The source code is available at https://github.com/ProAirVerse/Any-Size-Diffusion.

Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images

Few-shot learning (FSL) is essential in practical applications.
However, the limited training examples make the models more
vulnerable to label noise, which can lead to poor generaliza-
tion capability. To address this critical challenge, we propose
a curriculum meta-learning model that employs a novel dual-
level class-example sampling strategy to create a robust cur-
riculum for adaptive task distribution formulation and robust
model training. The dual-level framework proposes a heuristic
class sampling criterion that measures pairwise class bound-
ary complexity to form a class curriculum; and uses effective
example sampling through an under-trained proxy model to
form an example curriculum. By utilizing both class-level and
example-level information, our approach is more robust to
handle limited training data and noisy labels that commonly
occur in few-shot learning tasks. Our proposed model has
efficient convergence behavior, which is verified through rig-
orous convergence analysis. Additionally, we establish a novel
error bound through a hierarchical PAC-Bayesian analysis
for curriculum meta-learning under noise. We conduct exten-
sive experiments that demonstrate the effectiveness of our
framework in outperforming existing noisy few-shot learning
methods under various few-shot classification benchmarks.

Dual-Level Curriculum Meta-Learning for Noisy Few-Shot Learning Tasks | VIDEO

Ensuring fairness in Recommendation Systems (RSs) across demographic groups is critical due to the increased integration of RSs in applications such as personalized healthcare, finance, and e-commerce. Graph-based RSs play a crucial role in capturing intricate higher-order interactions among entities. However, integrating these graph models into the Federated Learning (FL) paradigm with fairness constraints poses formidable challenges as this requires access to the entire interaction graph and sensitive user information (such as gender, age, etc.) at the central server. This paper addresses the pervasive issue of inherent bias within RSs for different demographic groups without compromising the privacy of sensitive user attributes in FL environment with the graph-based model. To address the group bias, we propose F2PGNN (Fair Federated Personalized Graph Neural Network), a novel framework that leverages the power of Personalized Graph Neural Network (GNN) coupled with fairness considerations. Additionally, we use differential privacy techniques to fortify privacy protection. Experimental evaluation on three publicly available datasets showcases the efficacy of F2PGNN in mitigating group unfairness by 47% ∼ 99% compared to the state-of-the-art while preserving privacy and maintaining the utility. The results validate the significance of our framework in achieving equitable and personalized recommendations using GNN within the FL landscape. Source code is at:
https://github.com/nimeshagrawal/F2PGNN-AAAI24

No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation

Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.

Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling

So far, multi-intent spoken language understanding (SLU) has become a research hotspot in the field of natural language processing (NLP) due to its ability to recognize and extract multiple intents expressed and annotate corresponding sequence slot tags within a single utterance. Previous research has primarily concentrated on the token-level intent-slot interaction to model joint intent detection and slot filling, which resulted in a failure to fully utilize anisotropic intent-guiding information during joint training. In this work, we present a novel architecture by modeling the multi-intent SLU as a multi-view intent-slot interaction. The architecture resolves the kernel bottleneck of unified multi-intent SLU by effectively modeling the intent-slot relations with utterance, chunk, and token-level interaction. We further develop a neural framework, namely Uni-MIS, in which the unified multi-intent SLU is modeled as a three-view intent-slot interaction fusion to better capture the interaction information after special encoding. A chunk-level intent detection decoder is used to sufficiently capture the multi-intent, and an adaptive intent-slot graph network is used to capture the fine-grained intent information to guide final slot filling. We perform extensive experiments on two widely used benchmark datasets for multi-intent SLU, where our model bets on all the current strong baselines, pushing the state-of-the-art performance of unified multi-intent SLU. Additionally, the ChatGPT benchmark that we have developed demonstrates that there is a considerable amount of potential research value in the field of multi-intent SLU.

Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction | VIDEO

Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting local features through GCNs, while ignoring the relationship between point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between the voxelized point parts, which are treated as graph nodes. Motivated by the intuition that the contextual information between point parts lies in the pairwise adjacent relationship, which can be depicted by the hop distance of the graph quantitatively, we devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. In addition, we propose the Hop Graph Attention (HGA), which takes the learned hop distance as input for producing attention weights to allow edge features to contribute distinctively in aggregation. Eventually, the proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks. Comprehensive experiments on different backbones and tasks demonstrate that our self-supervised method achieves state-of-the-art performance. Our source codes are available at: https://github.com/Jinec98/DHGCN.

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning

The ability of humans to understand the world in terms of cause and effect relationships, as well as their ability to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in tandem under the theory of causal abstractions, but it is an open problem how to best leverage abstraction theory in real-world causal inference tasks, where the true model is not known, and limited data is available in most practical settings. In this paper, we focus on a family of causal abstractions constructed by clustering variables and their domains, redefining abstractions to be amenable to individual causal distributions. We show that such abstractions can be learned in practice using Neural Causal Models (Xia et al. (2021)), allowing us to utilize the deep learning toolkit to solve causal tasks (identification, estimation, sampling) at different levels of abstraction granularity. Finally, we show how representation learning can be used to learn abstractions, which we apply in our experiments to scale causal inferences to high dimensional settings such as with image data.

Neural Causal Abstractions | VIDEO

In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively been conducted. Nevertheless, owing to the severe difficulty of embedding a lengthy and untrimmed video into a single feature, these studies have been insufficient for accurate retrieval compared to frame-level feature-based studies. In this paper, we show that appropriate suppression of irrelevant frames can provide insight into the current obstacles of the video-level approaches. Furthermore, we propose a Video-to-Video Suppression network (VVS) as a solution. VVS is an end-to-end framework that consists of an easy distractor elimination stage to identify which frames to remove and a suppression weight generation stage to determine the extent to suppress the remaining frames. This structure is intended to effectively describe an untrimmed video with varying content and meaningless information. Its efficacy is proved via extensive experiments, and we show that our approach is not only state-of-the-art in video-level approaches but also has a fast inference time despite possessing retrieval capabilities close to those of frame-level approaches. Code is available at https://github.com/sejong-rcv/VVS

Downloads

Next from AAAI 2024

GINN-LP: A Growing Interpretable Neural Network for Discovering Multivariate Laurent Polynomial Equations

Similar lecture

M-BEV: Masked BEV Perception for Robust Autonomous Driving