United States

Self-Supervised Video Hashing (SSVH) models learn to generate short binary representations for videos without ground-truth supervision, facilitating large-scale video retrieval efficiency and attracting increasing research attention. The success of SSVH lies in the understanding of video content and the ability to capture the semantic relation among unlabeled videos. Typically, state-of-the-art SSVH methods consider these two points in a two-stage training pipeline, where they firstly train an auxiliary network by instance-wise mask-and-predict tasks and secondly train a hashing model to preserve the pseudo-neighborhood structure transferred from the auxiliary network. This consecutive training strategy is inflexible and also unnecessary. In this paper, we propose a simple yet effective one-stage SSVH method called ConMH, which incorporates video semantic information and video similarity relationship understanding in a single stage. To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames. Particularly, we find that a higher masking ratio helps video understanding. Besides, we fully exploit the similarity relationship between videos by maximizing agreement between two augmented views of a video, which contributes to more discriminative and robust hash codes. Extensive experiments on three large-scale video datasets (\ie, FCVID, ActivityNet and YFCC) indicate that ConMH achieves state-of-the-art results. 

AAAI 2023

Contrastive Masked Autoencoders for Self-Supervised Video Hashing

video retrieval

hashing

self-supervised learning

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

poster

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised pretraining framework where users may flexibly combine the modalities of vision, speech, and language into unified and general-purpose vector representations. In this framework, data from each modality are first given to pretrained single-modality encoders. The encoder outputs are then integrated with a multimodal fusion network, which uses novel merge- and co-attention mechanisms to effectively combine information from the different modalities. The entire system is pretrained end-to-end with new objectives including masked modality unit modeling and cross-modality contrastive learning. Unlike previous research using only video for pretraining, the i-Code framework can dynamically process single, dual, and triple-modality data during training and inference, flexibly projecting different combinations of modalities into a single representation space. Experimental results demonstrate how i-Code can outperform state-of-the-art techniques on five multimodal understanding tasks and single-modality benchmarks, improving by as much as 11\% and demonstrating the power of integrative multimodal pretraining.

i-Code: An Integrative and Composable Multimodal Learning Framework

Unsupervised meta-learning aims to learn the meta knowledge from unlabeled data and rapidly adapt to novel tasks. However, existing approaches may be misled by the  context-bias (e.g. background) from the training data. In this paper, we abstract the unsupervised meta-learning problem into a Structural Causal Model (SCM) and point out that such bias arises due to hidden confounders. To eliminate the confounders, we define the priors are \textit{conditionally} independent, learn the relationships between priors and intervene on them with casual factorization. Furthermore, we propose Causal Meta VAE (CMVAE) that encodes the priors into latent codes in the causal space and learns their relationships simultaneously to achieve the downstream few-shot image classification task. Results on toy datasets and three benchmark datasets demonstrate that our method can remove the context-bias and it outperforms other state-of-the-art unsupervised meta-learning algorithms because of bias-removal. Code is available at \url{https://github.com/GuodongQi/CMVAE}.

CMVAE: Causal Meta VAE for Unsupervised Meta-Learning

Automatic assembly is a promising research topic in 3D computer vision and robotics. Existing works focus on generating assembly (e.g., IKEA furniture) from scratch with a set of parts, namely 3D part assembly. In practice, there are higher demands for the robot to take over and finish an incomplete assembly (e.g., a half-assembled IKEA furniture) with an off-the-shelf toolkit, especially in human-robot and multi-agent collaborations. Compared to 3D part assembly, it is more complicated in nature and remains unexplored yet. The robot must understand the incomplete structure, infer what parts are missing, single out the correct parts from the toolkit and finally, assemble them with appropriate poses to finish the incomplete assembly. Geometrically similar parts in the toolkit can interfere, and this problem will be exacerbated with more missing parts. To tackle this issue, we propose a novel task called 3D assembly completion. Given an incomplete assembly, it aims to find its missing parts from a toolkit and predict the 6-DoF poses to make the assembly complete. To this end, we propose FiT, a framework for Finishing the incomplete 3D assembly with Transformer. We employ the encoder to model the incomplete assembly into memories. Candidate parts interact with memories in a memory-query paradigm for final candidate classification and pose prediction. Bipartite part matching and symmetric transformation consistency are embedded to refine the completion. For reasonable evaluation and further reference, we design two standard toolkits of different difficulty, containing different compositions of candidate parts. We conduct extensive comparisons with several baseline methods and ablation studies, demonstrating the effectiveness of the proposed method.

3D Assembly Completion

Simulating physical network paths (e.g., Internet) is a cornerstone research problem in the emerging sub-field of AI-for-networking. We seek a model that generates end-to-end packet delay values in response to the time-varying load offered by a sender, which is typically a function of the previously output delays. We formulate a novel ML problem at the intersection of dynamical systems, sequential decision making, and time-series generative modeling. The problem setting is unique, and renders the state-of-the-art neural generative modeling work in the text and time-series domains inapplicable, or ineffective. We propose a novel grey-box approach to network simulation that embeds the semantics of physical network path in a new RNN-style architecture called Recurrent Buffering Unit, providing the interpretability of standard network simulator tools, the power of neural models, the efficiency of SGD-based techniques for learning, and yielding promising results on synthetic and real-world network traces.

Simulating Network Paths with Recurrent Buffering Units

Incorporating sequence-to-sequence models into history-based Reinforcement Learning (RL) provides a general way to extend RL to partially-observable tasks. This method compresses history spaces according to the correlations between historical observations and the rewards. However, they do not adjust for the confounding correlations caused by data sampling and assign high beliefs to uninformative historical observations, leading to limited compression of history spaces. Counterfactual Inference (CI), which estimates causal effects by single-variable intervention, is a promising way to adjust for confounding. However, it is computationally infeasible to directly apply the single-variable intervention to a huge number of historical observations. This paper proposes to perform CI on observation sub-spaces instead of single observations and develop a coarse-to-fine CI algorithm, called Tree-based History Counterfactual Inference (T-HCI), to reduce the number of interventions exponentially. We show that T-HCI is computationally feasible in practice and brings significant sample efficiency gains in various challenging partially-observable tasks, including Maze, BabyAI, and robot manipulation tasks.

Fast Counterfactual Inference for History-Based Reinforcement Learning

Voxel grid representation of 3D scene properties has been widely used to improve the training or rendering speed of the Neural Radiance Fields (NeRF) while at the same time achieving high synthesis quality. However, these methods accelerate the original NeRF at the expense of extra storage demand, which hinders their applications in many scenarios. To solve this limitation, we present TinyNeRF, a three-stage pipeline: frequency domain transformation, pruning and quantization that work together to reduce the storage demand of the voxel grids with little to no effects on their speed and synthesis quality. Based on the prior knowledge of visual signals sparsity in the frequency domain, we convert the original voxel grids in the frequency domain via block-wise discrete cosine transformation (DCT). Next, we apply pruning and quantization to enforce the DCT coefficients to be sparse and low-bit. Our method can be optimized from scratch in an end-to-end manner, and can typically compress the original models by 2 orders of magnitude with minimal sacrifice on speed and synthesis quality.

TinyNeRF: Towards $100\times$ Compression of Voxel Radiance Fields

3D object detection received increasing attention in autonomous driving recently. Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not explicitly model the variations of rotation and reflection transformations. Consequently, large networks and extensive data augmentation are required for robust detection. Recent equivariant networks explicitly model the transformation variations by applying shared networks on multiple transformed point clouds, showing great potential in object geometry modeling. However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed. In this work, we present TED, an efficient Transformation-Equivariant 3D Detector to overcome the computation cost and speed issues. TED first applies a sparse convolution backbone to extract multi-channel transformation-equivariant voxel features; and then aligns and aggregates these equivariant features into lightweight and compact representations for high-performance 3D object detection. On the highly competitive KITTI 3D car detection leaderboard, TED ranked 1st among all submissions with competitive efficiency.

Transformation-Equivariant 3D Object Detection for Autonomous Driving

Positive-unlabeled learning is an essential problem in many real-world applications with only labeled positive and unlabeled data, especially when the negative samples are difficult to identify. Most existing positive-unlabeled learning methods will inevitably overfit the positive class to some extent due to the existence of unidentified positive samples. This paper first analyzes the overfitting problem and proposes to bound the generalization errors via Wasserstein distances. Based on that, we develop a simple yet effective positive-unlabeled learning method, GradPU, which consists of two key ingredients: A gradient-based regularizer that penalizes the gradient norms in the interpolated data region, which improves the generalization of positive class; An unnormalized upweighting mechanism that assigns larger weights to those positive samples that are hard, not-well-fitted and less frequently labeled. It enforces the training error of each positive sample to be small and increases the robustness to the labeling bias. We evaluate our proposed GradPU on three datasets: MNIST, FashionMNIST, and CIFAR10. The results demonstrate that GradPU achieves state-of-the-art performance on both unbiased and biased positive labeling scenarios.

GradPU: Positive-Unlabeled Learning via Gradient Penalty and Positive Upweighting

We study convex Constrained Markov Decision Processes (CMDPs) in which the objective is concave and the constraints are convex in the state-action occupancy measure. We propose a policy-based primal-dual algorithm that updates the primal variable via policy gradient ascent and updates the dual variable via projected sub-gradient descent. Despite the loss of additivity structure and the nonconvex nature, we establish the global convergence of the proposed algorithm by leveraging a hidden convexity in the problem, and prove the $O(T^{-1/3})$ convergence rate in terms of both optimality gap and constraint violation. When the objective is strongly concave in the occupancy measure, we prove an improved convergence rate of $O(T^{-1/2})$. By introducing a pessimistic term to the constraint, we further show that a zero constraint violation can be achieved while preserving the same convergence rate for the optimality gap. This work is the first one in the literature that establishes non-asymptotic convergence guarantees for policy-based primal-dual methods for solving infinite-horizon discounted convex CMDPs.

Policy-based Primal-Dual Methods for Convex Constrained Markov Decision Processes

In this work, we propose a real-time monocular 3D video reconstruction approach named Flora for reconstructing delicate and complete 3D scenes from RGB video sequences in an end-to-end manner. Specifically, we introduce a novel method with two main contributions. Firstly, the proposed feature aggregation module retains both color and reliability in a dual-frequency form. Secondly, the loss compensation module solves missing structure by correcting losses for falsely pruned voxels. The dual-frequency feature aggregation module enhances reconstruction quality in both precision and recall, and the loss compensation module benefits the recall. Notably, both proposed contributions achieve great results with negligible inferencing overhead. Our state-of-the-art experimental results on real-world datasets demonstrate Flora's leading performance in both effectiveness and efficiency. The code is available at https://github.com/NoOneUST/Flora.

Premium content

Contrastive Masked Autoencoders for Self-Supervised Video Hashing

Downloads

Next from AAAI 2023

i-Code: An Integrative and Composable Multimodal Learning Framework

Similar lecture

Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning