Canada

Very deep neural networks lead to significantly better performance on various real tasks. However, it usually causes slow inference and is hard to be deployed on real-world devices. How to reduce the number of layers to save memory and to accelerate the inference is an eye-catching topic. 
   In this work, we introduce an intermediate objective, a continuous-time network, before distilling deep networks into shallow networks.
   First, we distill a given deep network into a continuous-time neural flow model, which can be discretized with an ODE solver and the inference requires passing through the network multiple times.
   By forcing the flow transport trajectory to be straight lines, we find that it is easier to compress the infinite step model into a one-step neural flow model, which only requires passing through the flow model once.
   Secondly, we refine the one-step flow model together with the final head layer with knowledge distillation and finally, we can replace the given deep network with this one-step flow network. 
   Empirically, we demonstrate that our method outperforms direct distillation and other baselines on different model architectures (e.g. ResNet, ViT) on image classification and semantic segmentation tasks. 
   We also manifest that our distilled model naturally serves as an early-exit dynamic inference model.

AAAI 2024

Layer Compression of Deep Networks with Straight Flows

efficient models

technical paper

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. 

Omnidirectional images have attracted significant attention in recent years due to the rapid development of virtual reality technologies. Equirectangular projection (ERP), a naive form to store and transfer omnidirectional images, however, is not easy to be handled by existing two-dimensional (2D) image super-resolution (SR) methods since its inhomogeneous distributed sampling density and distortion across latitude. In this paper, we make one of the first attempts to design a spherical pseudo-cylindrical representation, which not only can let pixels at different latitudes adaptively adopt the best distinct sampling density but also is model-agnostic to most off-the-shelf SR methods to improve their performances. Specifically, we first upsample each latitude of the input ERP image and design a computationally tractable optimization algorithm to adaptively obtain a (sub)-optimal sampling density for each latitude of the ERP image. Then, for the distortion of ERP, we propose a new viewport-based training loss based on the original 3D sphere format of the omnidirectional image since the original format does not contain distortion. Finally, a simple yet effective recursive progressive omnidirectional SR network is designed to demonstrate the feasibility of our idea. The experimental results on public datasets demonstrate the effectiveness of the proposed method as well as the consistently superior performance of our method over most state-of-the-art methods quantitatively and qualitatively.

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Artistic style transfer aims to repaint the content image with the learned artistic style. Existing artistic style transfer methods can be divided into two categories: small model-based approaches and pre-trained large-scale model-based approaches. Small model-based approaches can preserve the content strucuture, but fail to produce highly realistic stylized images and introduce artifacts and disharmonious patterns; Pre-trained large-scale model-based approaches can generate highly realistic stylized images but struggle with preserving the content structure. To address the above issues, we propose ArtBank, a novel artistic style transfer framework, to generate highly realistic stylized images while preserving the content structure of the content images. Specifically, to sufficiently dig out the knowledge embedded in pre-trained large-scale models, an Implicit Style Prompt Bank (ISPB), a set of trainable parameter matrices, is designed to learn and store knowledge from the collection of artworks and behave as a visual prompt to guide pre-trained large-scale models to generate highly realistic stylized images while preserving content structure. Besides, to accelerate training the above ISPB, we propose a novel Spatial-Statistical-based self-Attention Module (SSAM). The qualitative and quantitative experiments demonstrate the superiority of our proposed method over state-of-the-art artistic style transfer methods. Code is available at https://github.com/Jamie-Cheung/ArtBank.

ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank

Model counting, a fundamental task in computer science, involves determining the number of satisfying assignments to a Boolean formula, typically represented in conjunctive normal form (CNF). While model counting for CNF formulas has received extensive attention with a broad range of applications, the study of model counting for Pseudo-Boolean (PB) formulas has been relatively overlooked. Pseudo-Boolean formulas, being more succinct than propositional Boolean formulas, offer greater flexibility in representing real-world problems. Consequently, there is a crucial need to investigate efficient techniques for model counting for PB formulas.

In this work, we propose the first exact Pseudo-Boolean model counter, PBCount , that relies on knowledge compilation approach via algebraic decision diagrams. Our extensive empirical evaluation shows that PBCount  can compute counts for 1513 instances while the current state-of-the-art approach could only handle 1013 instances. Our work opens up several avenues for future work in the context of model counting for PB formulas, such as the development of preprocessing techniques and exploration of approaches other than knowledge compilation.

Engineering an Exact Pseudo-Boolean Model Counter | VIDEO

The field of 4D point cloud understanding is rapidly developing with the goal of analyzing dynamic 3D point cloud sequences. However, it remains a challenging task due to the sparsity and lack of texture in point clouds.  Moreover, the irregularity of point cloud poses a difficulty in aligning temporal information within video sequences. To address these issues, we propose a novel cross-modal knowledge transfer framework, called X4D-SceneFormer. This framework enhances 4D-Scene understanding by transferring texture priors from RGB sequences using a Transformer architecture with temporal relationship mining. Specifically, the framework is designed with a dual-branch architecture, consisting of an 4D point cloud transformer and a Gradient-aware Image Transformer (GIT). The GIT combines visual texture and temporal correlation features to offer rich semantics and dynamics for better point cloud representation. During training, we employ multiple knowledge transfer techniques, including temporal consistency losses and masked self-attention, to strengthen the knowledge transfer between modalities. This leads to enhanced performance during inference using single-modal 4D point cloud inputs. Extensive experiments demonstrate the superior performance of our framework on various 4D point cloud video understanding tasks, including action recognition, action segmentation and semantic segmentation. The results achieve 1st places, i.e., 85.3% (+7.9%) accuracy and 47.3% (+5.0%) mIoU for 4D action segmentation and semantic segmentation, on the HOI4D challenge, outperforming previous state-of-the-art by a large margin.

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

In the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query. To enhance the expression ability of a proposal, we propose a Gaussian mixture proposal (GMP) that can depict arbitrary shapes by learning importance, centroid, and range of every Gaussian in the mixture. In learning GMP, each Gaussian is not trained in a feature space but is implemented over a temporal location. Thus the conventional feature-based learning for Gaussian mixture model is not valid for our case. In our special setting, to learn moderately coupled Gaussian mixture capturing diverse events, we newly propose a pull-push learning scheme using pulling and pushing losses, each of which plays an opposite role to the other. The effects of components in our scheme are verified in-depth with extensive ablation studies and the overall scheme achieves state-of-the-art performance. Our code is available at https://github.com/sunoh-kim/pps.

Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding

The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design and retrieval augmented generation for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.

Knowledge Graph Prompting for Multi-Document Question Answering

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse teammate policies obtained through maximizing specific diversity metrics. However, prior heuristic-based diversity metrics do not always maximize the agent's robustness in all cooperative problems. In this work, we first propose that maximizing an AHT agent's robustness requires it to emulate policies in the minimum coverage set (MCS), the set of best-response policies to any partner policies in the environment. We then introduce the L-BRDiv algorithm that generates a set of teammate policies that, when used for AHT training, encourage agents to emulate policies from the MCS. L-BRDiv works by solving a constrained optimization problem to jointly train teammate policies for AHT training and approximating AHT agent policies that are members of the MCS. We empirically demonstrate that L-BRDiv produces more robust AHT agents than state-of-the-art methods in a broader range of two-player cooperative problems without the need for extensive hyperparameter tuning for its objectives.  Our study shows that L-BRDiv outperforms the baseline methods by prioritizing discovering distinct members of the MCS instead of repeatedly finding redundant policies.

Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents | VIDEO

Langevin dynamics (LD) is widely used for sampling from distributions and for optimization. In this work, we derive a closed-form expression for the expected loss of preconditioned LD near stationary points of the objective function. We use the fact that at the vicinity of such points, LD reduces to an Ornstein–Uhlenbeck process, which is amenable to convenient mathematical treatment. Our analysis reveals that when the preconditioning matrix satisfies a particular relation with respect to the noise covariance, LD's expected loss becomes proportional to the rank of the objective's Hessian. We illustrate the applicability of this result in the context of neural networks, where the Hessian rank has been shown to capture the complexity of the predictor function but is usually computationally hard to probe. Finally, we use our analysis to compare SGD-like and Adam-like preconditioners and identify the regimes under which each of them leads to a lower expected loss.

The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank | VIDEO

Object detection in low-light scenarios has attracted much attention in the past few years. A mainstream and representative scheme introduces enhancers as the pre-processing for regular detectors. However, because of the disparity in task objectives between the enhancer and detector, this paradigm cannot shine at its best ability. In this work, we try to \textit{arouse the potential of enhancer + detector}. Different from existing works, we extend the illumination-based enhancers (our newly designed or existing) as a scene decomposition module, whose removed illumination is exploited as the auxiliary in the detector for extracting detection-friendly features. A semantic aggregation module is further established for integrating multi-scale scene-related semantic information in the context space. Actually, our built scheme successfully transforms the ``\textit{trash}'' (i.e., the ignored illumination in the detector) into the ``\textit{treasure}'' for the detector. Plenty of experiments are conducted to reveal our superiority against other state-of-the-art methods. The code will be public if it is accepted.

Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation | VIDEO

Capturing the underlying structural causal relations represented by Directed Acyclic Graphs (DAGs) has been a fundamental task in various AI disciplines. Causal DAG learning via the continuous optimization framework has recently achieved promising performance in terms of accuracy and efficiency. However, most methods make strong assumptions of homoscedastic noise, i.e., exogenous noises have equal variances across variables, observations, or even both. The noises in real data usually violate both assumptions due to the biases introduced by different data collection processes. To address the heteroscedastic noise issue, we introduce relaxed implementable sufficient conditions and prove the identifiability of a general class of SEM subject to those conditions. Based on the identifiable general SEM, we propose a novel formulation for DAG learning which accounts for the noise variance variation across variables and observations. We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and learn a causal DAG from data with heteroscedastic variables noise under varying variance. We show significant empirical gains of the proposed approaches over state-of-the-art methods on both synthetic data and real data.

Content not yet available

Layer Compression of Deep Networks with Straight Flows

Downloads

Next from AAAI 2024

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Layer Compression of Deep Networks with Straight Flows

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads