Canada

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model&#39;s generalization ability and enable more practical evaluation and comparison. The model&#39;s performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.

AAAI 2024

Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting

large scenes

supervised contribution weighting

multi-view pedestrian detection

adversarial domain adaptation

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.

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. 

Partial label learning (PLL) induces a multi-class classifier from training examples each associated with a set of candidate labels, among which only one is valid. The formation of real-world data typically arises from heterogeneous entanglement of series latent explanatory factors, which are considered intrinsic properties for discriminating between different patterns. Though learning disentangled representation is expected to facilitate label disambiguation for partial-label (PL) examples, few existing works were dedicated to addressing this issue. In this paper, we make the first attempt towards disentangled PLL and propose a novel approach named TERIAL, which makes predictions according to derived disentangled representation of instances and label embeddings. The TERIAL approach formulates the PL examples as an undirected bipartite graph where instances are only connected with their candidate labels, and employs a tailored neighborhood routing mechanism to yield disentangled representation of nodes in the graph. Specifically, the proposed routing mechanism progressively infers the explanatory factors that contribute to the edge between adjacent nodes and augments the representation of the central node with factor-aware embedding information propagated from specific neighbors simultaneously via iteratively analyzing the promising subspace clusters formed by the node and its neighbors. The estimated labeling confidence matrix is also introduced to accommodate unreliable links owing to the inherent ambiguity of PLL. Moreover, we theoretically prove that the neighborhood routing mechanism will converge to the point estimate that maximizes the marginal likelihood of observed PL training examples. Comprehensive experiments over various datasets demonstrate that our approach outperforms the state-of-the-art counterparts.

Disentangled Partial Label Learning

With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data scientists must prioritize ensuring privacy for individuals in these untapped datasets, especially for images or videos with faces, which are prime targets for identification methods. Proposed solutions to de-identify such images often compromise non-identifying facial attributes relevant to downstream tasks.
In this paper, we introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Unlike previous approaches, our solution is firmly grounded in the domains of differential privacy and ensemble-learning research. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. Additionally, we leverage supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.

Disguise without Disruption: Utility-Preserving Face De-identification

Despite significant progress in utilizing pre-trained text-to-image diffusion models to guide the creation of 3D scenes, these methods often struggle to generate scenes that are sufficiently realistic, leading to "neural scene degeneration". 
In this work, we propose a new 3D scene generation model called Real3D. 
Specifically, Real3D designs a pipeline from a NeRF-like implicit renderer to a tetrahedrons-based explicit renderer, greatly improving the neural network's ability to generate various neural scenes. 
Moreover, Real3D introduces an additional discriminator to prevent neural scenes from falling into undesirable local optima, thus avoiding the degeneration phenomenon.
Our experimental results demonstrate that Real3D outperforms all existing state-of-the-art text-to-3D generation methods, providing valuable insights to facilitate the development of learning-based 3D scene generation approaches.

Real3D the Curious Case of Neural Scene Degeneration

Deep neural networks are known to be vulnerable to security risks due to the inherent transferable nature of adversarial examples. Despite the success of recent generative model-based attacks demonstrating strong transferability, it still remains a challenge to design an efficient attack strategy in a real-world strict black-box setting, where both the target domain and model architectures are unknown. In this paper, we seek to explore a feature contrastive approach in the frequency domain to generate adversarial examples that are robust in both cross-domain and cross-model settings. With that goal in mind, we propose two modules that are only employed during the training phase: a Frequency-Aware Domain Randomization (FADR) module to randomize domain-variant low- and high-range frequency components and a Frequency-Augmented Contrastive Learning (FACL) module to effectively separate domain-invariant mid-frequency features of clean and perturbed image. We demonstrate strong transferability of our generated adversarial perturbations through extensive cross-domain and cross-model experiments, while keeping the inference time complexity.

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Document layout analysis is a crucial step for intelligent document understanding. However, many existing methods primarily focus on the visual aspects and overlook the textual features of documents. Although document pre-trained models utilize multi-modal features during the pre-training phase, they tend to operate as a unimodal pipeline when it comes to layout analysis tasks. Furthermore, current multi-modal methods perform worse than unimodal detectors on complex layout analysis datasets. To address these limitations, we propose an effective and pluggable multi-modal fusion approach named M2Doc, which fuses visual and textual features for better layout detection. M2Doc contains two pluggable multi-modal fusion modules, early-fusion and late-fusion, which align and fuse visual and textual features at the pixel level and block level. The early-fusion module leverages a gate-like mechanism to fuse visual and textual features extracted by the backbone, while the late-fusion module uses simple summation to fuse visual and textual features attributed to the candidate bounding boxes. Benefitting from the concision and effectiveness of M2Doc, it can be easily applied to various detectors for better layout detection, including two-stage and end-to-end object detectors. Our experimental results demonstrate significant performance improvements in detectors equipped with M2Doc on datasets such as DocLayNet (+11.3\% mAP) and M$^6$Doc (+1.9\% mAP). Furthermore, through the integration of the DINO detector with M2Doc, we achieve state-of-the-art results on DocLayNet (89.0\% mAP), M$^6$Doc (69.9\% mAP), and PubLayNet (95.5\% mAP). The code will be publicly released at https://github.com/johnning2333/M2Doc.

M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis

Recent advances in semi-supervised learning (SSL) have relied on the optimistic assumption that labeled and unlabeled data share the same class distribution. However, this assumption is often violated in real-world scenarios, where unlabeled data may contain out-of-class samples. SSL with such uncurated unlabeled data leads training models to be corrupted. In this paper, we propose a robust SSL method for learning from uncurated real-world data within the context of open-set semi-supervised learning (OSSL). Unlike previous works that rely on feature similarity distance, our method exploits uncertainty in logits. By leveraging task-dependent predictions of logits, our method is capable of robust learning even in the presence of highly correlated outliers. Our key contribution is to present an unknown-aware graph regularization (UAG), a novel technique that enhances the performance of uncertainty-based OSSL frameworks. The technique addresses not only the conflict between training objectives for inliers and outliers but also the limitation of applying the same training rule for all outlier classes, which are existed on previous uncertainty-based approaches. Extensive experiments demonstrate that UAG surpasses state-of-the-art OSSL methods by a large margin across various protocols. Codes are available at https://github.com/heejokong/UAGreg.

Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data

Data valuation is concerned with determining a fair valuation of data from data sources to compensate them or to identify training examples that are the most or least useful for predictions. With the rising interest in personal data ownership and data protection regulations, model owners will likely have to fulfil more data deletion requests. This raises issues that have not been addressed by existing works: Are the data valuation scores still fair with deletions? Must the scores be expensively recomputed? The answer is no. To avoid recomputations, we propose using our data valuation framework DeRDaVa upfront for valuing each data source's contribution to preserving robust model performance after anticipated data deletions. DeRDaVa can be efficiently approximated and will assign higher values to data that are more useful or less likely to be deleted. We further generalize DeRDaVa to Risk-DeRDaVa to cater to risk-averse/seeking model owners who are concerned with the worst/best-cases model utility. We also empirically demonstrate the practicality of our solutions.

DeRDaVa: Deletion-Robust Data Valuation for Machine Learning

Partial label learning (PLL) expands the applicability of supervised machine learning models by enabling effective learning from weakly annotated overcomplete labels. Existing PLL methods however focus on the standard centralized learning scenarios. In this paper, we expand PLL into the distributed computation setting by formalizing a new learning scenario named as federated partial label learning (FedPLL), where the training data with partial labels are distributed across multiple local clients with privacy constraints. To address this challenging problem, we propose a novel Federated PLL method with Local-Adaptive Augmentation and Regularization (FedPLL-LAAR). In addition to alleviating the partial label noise with moving-average label disambiguation, the proposed method performs MixUp-based local-adaptive data augmentation to mitigate the challenge posed by insufficient and imprecisely annotated local data, and dynamically incorporates the guidance of global model to minimize client drift through adaptive gradient alignment regularization between the global and local models. Extensive experiments conducted on multiple datasets under the FedPLL setting demonstrate the effectiveness of the proposed FedPLL-LAAR method for federated partial label learning.

Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization

Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, advancing the development of a universal embodied agent. In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). At each step, NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status, and makes the decision to approach the target. Through comprehensive experiments, we demonstrate NavGPT can explicitly perform high-level planning for navigation, including decomposing instruction into sub-goals, integrating commonsense knowledge relevant to navigation task resolution, identifying landmarks from observed scenes, tracking navigation progress, and adapting to exceptions with plan adjustment. Furthermore, we show that LLMs is capable of generating high-quality navigational instructions from observations and actions along a path, as well as drawing accurate top-down metric trajectory given the agent's navigation history. Despite the performance of using NavGPT to zero-shot R2R tasks still falling short of trained models, we suggest adapting multi-modality inputs for LLMs to use as visual navigation agents and applying the explicit reasoning of LLMs to benefit learning-based models. Code is available at: https://github.com/GengzeZhou/NavGPT.

NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models

Ensemble pruning that combines a subset of individual learners generated in parallel to make predictions is an important topic in ensemble learning. Past decades have developed a lot of pruning algorithms that focus on the external behavior of learners on samples, which may lead to over-fitting. In this paper, we conjecture that the generalization performance of an ensemble is not only related to its external behavior on samples but also dependent on the internal structure of individual learners. We propose the general MEPSI approach based on Kolmogorov complexity and the Minimum Description Length (MDL) principle, which formulates the ensemble pruning task as the two-objective optimization problem that comprises the empirical error and structural information among individual learners. We also provide a concrete implementation of MEPSI on decision trees. The theoretical results provide generalization bounds for both the general MEPSI approach and tree-based implementation. The comparative experiments conducted on multiple real-world data sets demonstrate the effectiveness of our proposed method.

Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting

Downloads

Next from AAAI 2024

Disentangled Partial Label Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES