Canada

This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation in faithful PatchMatch multi-view stereo (MVS). We observe that the heuristic depth hypothesis sampling modes employed by PatchMatch MVS solvers are insensitive to (i) the piece-wise smooth distribution of depths across the object surface and (ii) the implicit multi-modal distribution of depth prediction probabilities along the ray direction on the surface points. Accordingly, we develop DeformSampler to learn distribution-sensitive sample spaces to (i) propagate depths consistent with the scene&#39;s geometry across the object surface and (ii) fit a Laplace Mixture model that approaches the point-wise probabilities distribution of the actual depths along the ray direction. We integrate DeformSampler into a learnable PatchMatch MVS system to enhance depth estimation in challenging areas, such as piece-wise discontinuous surface boundaries and weakly-textured regions. Experimental results on DTU and Tanks &amp; Temples datasets demonstrate its superior performance and generalization capabilities compared to state-of-the-art competitors. Code is available at https://github.com/Geo-Tell/DS-PMNet.

AAAI 2024

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo

depth distribution

deformable sampling

depth estimation

This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation in faithful PatchMatch multi-view stereo (MVS). We observe that the heuristic depth hypothesis sampling modes employed by PatchMatch MVS solvers are insensitive to (i) the piece-wise smooth distribution of depths across the object surface and (ii) the implicit multi-modal distribution of depth prediction probabilities along the ray direction on the surface points. Accordingly, we develop DeformSampler to learn distribution-sensitive sample spaces to (i) propagate depths consistent with the scene's geometry across the object surface and (ii) fit a Laplace Mixture model that approaches the point-wise probabilities distribution of the actual depths along the ray direction. We integrate DeformSampler into a learnable PatchMatch MVS system to enhance depth estimation in challenging areas, such as piece-wise discontinuous surface boundaries and weakly-textured regions. Experimental results on DTU and Tanks & Temples datasets demonstrate its superior performance and generalization capabilities compared to state-of-the-art competitors. Code is available at https://github.com/Geo-Tell/DS-PMNet.

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. 

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Ranking aggregation (RA), the process of aggregating multiple rankings derived from multiple search strategies, has been proved effective in person re-identification (re-ID) because of a single re-ID method can not always achieve consistent superiority for different scenarios. Existing RA research mainly focus on unsupervised and fully-supervised methods. The former lack external supervision to optimize performance, while the latter are costly because of expensive labeling effort required for training. To address the above challenges, this paper proposes a quantum-inspired interactive ranking aggregation (QI-IRA) method, which (1) utilizes quantum theory to interpret and model the generation and aggregation of multiple basic rankings, (2) approximates or even exceeds the performance of fully-supervised RA methods with much less labeling cost, even as low as only two feedbacks per query on Market1501, MARS and DukeMTMC-VideoReID datasets. Comparative experiments conducted on six public re-ID datasets validate the superiority of the proposed QI-IRA method over existing unsupervised, interactive, and fully-supervised RA approaches.

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://github.com/LinQinLiang/DeCoWA.

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated when considering evolving dynamics between domains. While various approaches have been proposed to address this issue, a comprehensive understanding of the underlying generalization theory is still lacking. In this study, we contribute novel theoretic results that aligning conditional distribution leads to the reduction of generalization bounds. Our analysis serves as a key motivation for solving the Temporal Domain Generalization (TDG) problem through the application of Koopman Neural Operators, resulting in Temporal Koopman Networks (TKNets). By employing Koopman Neural Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains. Through empirical evaluations conducted on synthetic and real-world datasets, we validate the effectiveness of our proposed approach.

Generalizing across Temporal Domains with Koopman Operators

Class incremental learning (CIL) aims to solve the notorious forgetting problem, which refers to the fact that once the network is updated on a new task, its performance on previously-learned tasks degenerates catastrophically. Most successful CIL methods store exemplars (samples of learned tasks) to train a feature extractor incrementally, or store prototypes (features of learned tasks) to estimate the incremental feature distribution. However, the stored exemplars would violate the data privacy concerns, while the fixed prototypes might not reasonably be consistent with the incremental feature distribution, hindering the exploration of real-world CIL applications. In this paper, we propose a data-free CIL method with embedding distillation and Task-oriented generation (eTag), which requires neither exemplar nor prototype. Embedding distillation prevents the feature extractor from forgetting by distilling the outputs from the networks' intermediate blocks. Task-oriented generation enables a lightweight generator to produce dynamic features, fitting the needs of the top incremental classifier. Experimental results confirm that the proposed eTag considerably outperforms state-of-the-art methods on several benchmark datasets.

eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation

The shuffle model of local differential privacy is an advanced method of privacy amplification designed to enhance privacy protection with high utility. 
It achieves this by randomly shuffling  sensitive data, making linking individual data points to specific individuals more challenging.
However, 
most existing studies have focused on the shuffle model based on
$(\epsilon_0,0)$-Locally Differentially Private (LDP) randomizers, with limited consideration for complex scenarios such as $(\epsilon_0,\delta_0)$-LDP or personalized LDP. 
This hinders a comprehensive understanding of the shuffle model's potential and limits its application in various settings.
To bridge this research gap, we propose a generalized shuffle framework that can be applied to any
$(\epsilon_i,\delta_i)$-LDP setting. This generalization allows for a broader exploration of the privacy-utility trade-off and facilitates the design of privacy-preserving analyses in diverse contexts.
We prove that shuffled $(\epsilon_i,\delta_i)$-LDP process approximately preserves $\mu$-Gaussian Differential Privacy with $
\mu = \sqrt{\frac{2}{\sum_{i=1}^{n} \frac{1-\delta_i}{1+e^{\epsilon_i}}-\max_{i}{\frac{1-\delta_{i}}{1+e^{\epsilon_{i}}}}}}.
$
This approach allows us to avoid the limitations and potential inaccuracies associated with inequality estimations.
To strengthen the privacy guarantee, we improve the lower bound by utilizing \textit{hypothesis testing} instead of relying on rough estimations like the Chernoff bound or Hoeffding's inequality.
Furthermore, extensive comparative evaluations clearly show that our approach outperforms existing methods in achieving strong central privacy guarantees while preserving the utility of the global model.
We have also carefully designed corresponding algorithms for average function, frequency estimation, and stochastic gradient descent.

A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility

Spiking neural networks (SNNs) have revolutionized neural learning and are making remarkable strides in image analysis and robot control tasks with ultra-low power consumption advantages. Inspired by this success, we investigate the application of spiking neural networks to 3D point cloud processing. We present a point-to-spike residual learning network for point cloud classification, which operates on points with binary spikes rather than floating-point numbers. Specifically, we first design a spatial-aware kernel point spiking neuron to relate spiking generation to point position in 3D space. On this basis, we then design a 3D spiking residual block for effective feature learning based on spike sequences. By stacking the 3D spiking residual blocks, we build the point-to-spike residual classification network, which achieves low computation cost and low accuracy loss on two benchmark datasets, ModelNet40 and ScanObjectNN. Moreover, the classifier strikes a good balance between classification accuracy and biological characteristics, allowing us to explore the deployment of 3D processing to neuromorphic chips for developing energy-efficient 3D robotic perception systems.

Point-to-Spike Residual Learning for Energy-Efficient 3D Point Cloud Classification

As a neuromorphic camera with high temporal resolution, spike camera can capture dynamic scenes with high-speed motion. Recently, spike camera with a color filter array (CFA) has been developed for color imaging. There are some methods for spike camera demosaicing to reconstruct color images from Bayer-pattern spike streams. However, the demosaicing results are bothered by severe noise in spike streams, to which previous works pay less attention. In this paper, we propose an iterative joint demosaicing and denoising network (SJDD-Net) for spike cameras based on the observation model. Firstly, we design a color spike representation (CSR) to learn latent representation from Bayer-pattern spike streams. In CSR, we propose an offset-sharing deformable convolution module to align temporal features of color channels. Then we develop a spike noise estimator (SNE) to obtain features of the noise distribution. Finally, a color correlation prior (CCP) module is proposed to utilize the color correlation for better details. For training and evaluation, we designed a spike camera simulator to generate Bayer-pattern spike streams with synthesized noise. Besides, we captured some Bayer-pattern spike streams, building the first real-world captured dataset to our knowledge. Experimental results show that our method can restore clean images from Bayer-pattern spike streams. The source codes and dataset are available at https://github.com/csycdong/SJDD-Net.

Joint Demosaicing and Denoising for Spike Camera

Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects.
Specifically, we utilize a pre-trained diffusion model to fill in the hidden areas of 2D images. Then we use these in-painted images to optimize a neural implicit surface representation for each instance for 3D reconstruction.
Since creating the in-painting masks needed for this process is tricky, we adopt a human-in-the-loop strategy that involves very little human engagement to generate high-quality masks.
Moreover, some parts of objects can be totally hidden because the videos are usually shot from limited perspectives. To ensure recovering these invisible areas, we develop a cascaded network architecture for predicting signed distance field, making use of different frequency bands of positional encoding and maintaining overall smoothness.
Besides the commonly used rendering loss, Eikonal loss, and silhouette loss, we adopt a CLIP-based semantic consistency loss to guide the surface from unseen camera angles. 
Experiments on ScanNet scenes show that our proposed framework achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos. Code: https://github.com/THU-LYJ-Lab/O2-Recon.

O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model | VIDEO

Large-scale language-image pre-trained models have shown superior performances on many cross-modal retrieval tasks.
However, the problem of transferring the knowledge learned from such models (e.g., CLIP) to video-based person re-identification (ReID) has barely been explored.
In addition, there is a lack of decent text descriptions in current ReID benchmarks.
To address these issues, in this work, we propose a novel one-stage text-free CLIP-based learning framework named TF-CLIP for video-based person ReID.
More specifically, we extract the identity-specific sequence feature as the CLIP-Memory to replace the text feature.
Meanwhile, we design a Sequence-Specific Prompt (SSP) module to update the CLIP-Memory online.
To capture temporal information, we further propose a Temporal Memory Diffusion (TMD) module, which consists of two key components: Temporal Memory Construction (TMC) and Memory Diffusion (MD).
Technically, TMC allows the frame-level memories in a sequence to communicate with each other, and to extract temporal information based on the relations within the sequence.
MD further diffuses the temporal memories to each token in the original features to obtain more robust sequence features.
Extensive experiments demonstrate that our proposed method shows much better results than other state-of-the-art methods on MARS, LS-VID and iLIDS-VID.

Content not yet available

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo

Downloads

Next from AAAI 2024

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo

.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

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads