AAAI 2024 Papers

Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation related researches. To deal with this challenge, we propose a fine-grained incremental evolution centered pose generation framework, rather than traditional direct one-to-one in a rush. Since proposed approach actually bypasses the theoretical difficulty of directly modeling dramatic non-linear variation, the incurred content distortion and blurring could be effectively constrained, at the same time the various individual pose details, especially clothes texture, could be precisely maintained. In order to systematically guide the evolution course, both global and incremental evolution constraints are elaborately designed and merged into the overall framework. And a novel triple-path knowledge fusion structure is worked out to take full advantage of all available valuable knowledge to conduct high-quality pose synthesis. In addition, our framework could generate a series of valuable by-products, namely the various intermediate poses. Extensive experiments have been conducted to verify the effectiveness of the proposed approach. Code is available at https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.

We introduce a new amortized likelihood ratio estimator for likelihood-free simulation-based inference (SBI). Our estimator is simple to train and estimates the likelihood ratio using a single forward pass of the neural estimator. Our approach directly computes the likelihood ratio between two competing parameter sets which is different from the previous approach of comparing two neural network output values. We refer to our model as the direct neural ratio estimator (DNRE). As part of introducing the DNRE, we derive a corresponding Monte Carlo estimate of the posterior. We benchmark our new ratio estimator and compare to previous ratio estimators in the literature. We show that our new ratio estimator often outperforms these previous approaches. As a further contribution, we introduce a new derivative estimator for likelihood ratio estimators that enables us to compare likelihood-free Hamiltonian Monte Carlo (HMC) with random-walk Metropolis-Hastings (MH). We show that HMC is equally competitive, which has not been previously shown. Finally, we include a novel real-world application of SBI by using our neural ratio estimator to design a quadcopter. Code is available at https://github.com/SRI-CSL/dnre.

Dairy owners invest heavily to keep their animals healthy. There is good reason to hope that technologies such as computer vision and artificial intelligence (AI) could reduce costs, yet obstacles arise when adapting these advanced tools to farming environments. In this work, we applied AI tools to dairy cow teat localization and teat shape classification, obtaining a model that achieves a mean average precision of 0.783. This digital twin-driven approach is intended as a first step towards automating and accelerating the detection and treatment of hyperkeratosis, mastitis, and other medical conditions that significantly burden the dairy industry.

Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and DanceTrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods. Code is available at https://github.com/RainBowLuoCS/DiffusionTrack.

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we found it is especially suitable for accurate and crisp edge detection since the denoising process is directly applied to the original image size. Therefore, we propose the first diffusion model for the task of general edge detection, which we call DiffusionEdge. To avoid expensive computational resources while retaining the final performance, we apply DPM in the latent space and enable the classic cross-entropy loss which is uncertainty-aware in pixel level to directly optimize the parameters in latent space in a distillation manner. We also adopt a decoupled architecture to speed up the denoising process and propose a corresponding adaptive Fourier filter to adjust the latent features of specific frequencies. With all the technical designs, DiffusionEdge can be stably trained with limited resources, predicting crisp and accurate edge maps with much fewer augmentation strategies. Extensive experiments on four edge detection benchmarks demonstrate the superiority of DiffusionEdge both in correctness and crispness. On the NYUDv2 dataset, compared to the second best, we increase the ODS, OIS (without post-processing) and AC by 30.2%, 28.1% and 65.1%, respectively. Code: https://github.com/GuHuangAI/DiffusionEdge.

Semi-supervised time-series classification could effectively alleviate the issue of lacking labeled data. However, existing approaches usually ignore model interpretability, making it difficult for humans to understand the principles behind the predictions of a model. Shapelets are a set of discriminative subsequences that show high interpretability in time series classification tasks. Shapelet learning-based methods have demonstrated promising classification performance. Unfortunately, without enough labeled data, the shapelets learned by existing methods are often poorly discriminative, and even dissimilar to any subsequence of the original time series. To address this issue, we propose the Diffusion Language-Shapelets model (DiffShape) for semi-supervised time series classification. In DiffShape, a self-supervised diffusion learning mechanism is designed, which uses real subsequences as a condition. This helps to increase the similarity between the learned shapelets and real subsequences by using a large amount of unlabeled data. Furthermore, we introduce a contrastive language-shapelets learning strategy that improves the discriminability of the learned shapelets by incorporating the natural language descriptions of the time series. Experiments have been conducted on the UCR time series archive, and the results reveal that the proposed DiffShape method achieves state-of-the-art performance and exhibits superior interpretability over baselines.

Sketch re-identification (Re-ID) seeks to match pedestrians' photos from surveillance videos with corresponding sketches. However, we observe that existing works still have two critical limitations: (i) cross- and intra-modality discrepancies hinder the extraction of modality-shared features, (ii) standard triplet loss fails to constrain latent feature distribution in each modality with inadequate samples. To overcome the above issues, we propose a differentiable auxiliary learning network (DALNet) to explore a robust auxiliary modality for Sketch Re-ID. Specifically, for (i) we construct an auxiliary modality by using a dynamic auxiliary generator (DAG) to bridge the gap between sketch and photo modalities. The auxiliary modality highlights the described person in photos to mitigate background clutter and learns sketch style through style refinement. Moreover, a modality interactive attention module (MIA) is presented to align the features and learn the invariant patterns of two modalities by auxiliary modality. To address (ii), we propose a multi-modality collaborative learning scheme (MMCL) to align the latent distribution of three modalities. An intra-modality circle loss in MMCL brings learned global and modality-shared features of the same identity closer in the case of insufficient samples within each modality. Extensive experiments verify the superior performance of our DALNet over the state-of-the-art methods for Sketch Re-ID, and the generalization in sketch-based image retrieval and sketch-photo face recognition tasks.

Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the split-and-classify (i.e., frame-level) strategy or the more principled event-level modeling approach, all existing methods consider the SED problem from the discriminative learning perspective. In this work, we reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process, conditioned on a target audio sample. During training, our model learns to reverse the noising process by converting noisy latent queries to the ground-truth versions in the elegant Transformer decoder framework. Doing so enables the model generate accurate event boundaries from even noisy queries during inference. Extensive experiments on the Urban-SED and EPIC-Sounds datasets demonstrate that our model significantly outperforms existing alternatives, with 40+% faster convergence in training. Code: https://github.com/Surrey-UPLab/DiffSED

Deriving DSLR-quality sRGB images from smartphone RAW images has become a compelling challenge due to discernible detail disparity, color mapping instability, and spatial misalignment in RAW-sRGB data pairs. We present DiffRAW, a novel method that incorporates the diffusion model for the first time in learning RAW-to-sRGB mappings. By leveraging the diffusion model, our approach effectively learns the high-quality detail distribution of DSLR images, thereby enhancing the details of output images. Simultaneously, we use the RAW image as a diffusion condition to maintain image structure information such as contours and textures. To mitigate the interference caused by the color and spatial misalignment in training data pairs, we embed a color-position preserving condition within DiffRAW, ensuring that the output images do not exhibit color biases and pixel shift issues. To accelerate the inference process of DiffRAW, we designed the Domain Transform Diffusion Method, an efficient diffusion process with its corresponding reverse process. The Domain Transform Diffusion Method can reduce the required inference steps for diffusion model-based image restoration/enhancement algorithms while enhancing the quality of the generated images. Through evaluations on the ZRR dataset, DiffRAW consistently demonstrates state-of-the-art performance across all perceptual quality metrics (e.g., LPIPS, FID, MUSIQ), while achieving comparable results in PSNR and SSIM.

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.

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy measures to obtain a surrogate reward for forward reinforcement learning. However, the traditional discriminator is a simple binary classifier and doesn't learn an accurate distribution, which may result in failing to identify expert-level state-action pairs induced by the policy interacting with the environment. To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework. Specifically, DiffAIL models the state-action pairs as unconditional diffusion models and uses diffusion loss as part of the discriminator's learning objective, which enables the discriminator to capture better expert demonstrations and improve generalization. Experimentally, the results show that our method achieves state-of-the-art performance and significantly surpasses expert demonstration on two benchmark tasks, including the standard state-action setting and state-only settings.

This work investigates efficient score-based black-box adversarial attacks with high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called DifAttack, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack firstly disentangles an image's latent feature into an adversarial feature and a visual feature, where the former dominates the adversarial capability of an image, while the latter largely determines its visual appearance. We train an autoencoder for the disentanglement by using pairs of clean images and their Adversarial Examples (AEs) generated from available surrogate models via white-box attack methods. Eventually, DifAttack iteratively optimizes the adversarial feature according to the query feedback from the victim model until a successful AE is generated, while keeping the visual feature unaltered. In addition, due to the avoidance of using surrogate models' gradient information when optimizing AEs for black-box models, our proposed DifAttack inherently possesses better attack capability in the open-set scenario, where the training dataset of the victim model is unknown. Extensive experimental results demonstrate that our method achieves significant improvements in ASR and query efficiency simultaneously, especially in the targeted attack and open-set scenarios. The code is available The code is available at https://github.com/csjunjun/DifAttack.git.

The generation of logically coherent dialogues by humans relies on underlying cognitive abilities. Based on this, we redefine the dialogue coherence evaluation process, combining cognitive judgment with the basic text to achieve a more human-like evaluation. We propose a novel dialogue evaluation framework based on Dialogue Cognition Graph (DCGEval) to implement the fusion by in-depth interaction between cognition modeling and text modeling. The proposed Abstract Meaning Representation (AMR) based graph structure called DCG aims to uniformly model four dialogue cognitive abilities. Specifically, core-semantic cognition is modeled by converting the utterance into an AMR graph, which can extract essential semantic information without redundancy. The temporal and role cognition are modeled by establishing logical relationships among the different AMR graphs. Finally, the commonsense knowledge from ConceptNet is fused to express commonsense cognition. Experiments demonstrate the necessity of modeling human cognition for dialogue evaluation, and our DCGEval presents stronger correlations with human judgments compared to other state-of-the-art evaluation metrics.

Prompt-based pre-trained language models (PLMs) paradigm has succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimization methods require expert knowledge to design the base prompt set and identify high-quality prompts, which is costly, inefficient, and subjective. Meanwhile, existing continuous prompt optimization methods improve the performance by learning the ideal prompts through the gradient information of PLMs, whose high computational cost, and low readability and generalizability are often concerning. To address the research gap, we propose a Dialogue-comprised Policy-gradient-based Discrete Prompt Optimization (DP_2O) method. We first design a multi-round dialogue alignment strategy for readability prompt set generation based on GPT-4. Furthermore, we propose an efficient prompt screening metric to identify high-quality prompts with linear complexity. Finally, we construct a reinforcement learning (RL) framework based on policy gradients to match the prompts to inputs optimally. By training a policy network with only 0.62M parameters on the tasks in the few-shot setting, DP_2O outperforms the state-of-the-art (SOTA) method by 1.52% in accuracy on average on four open-source datasets. Moreover, subsequent experiments also demonstrate that DP_2O has good universality, robustness and generalization ability.

Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels deconfounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization. Despite spotlights around, recent theoretical result verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. The fake invariance severely endangers OOD generalization since the trustful objective can not be diagnosed and existing causal remedies are invalid to rectify. In this paper, we review a IRL family (InvRat) under the Partially and Fully Informative Invariant Feature Structural Causal Models (PIIF SCM /FIIF SCM) respectively, to certify their weaknesses in representing fake invariant features, then, unify their causal diagrams to propose ReStructured SCM (RS-SCM). RS-SCM can ideally rebuild the spurious and the fake invariant features simultaneously. Given this, we further develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects. It can be easily implemented by a small feature selection subnet introduced in the IRL family, which is alternatively optimized to achieve our goal. Experiments verified the superiority of our approach to fight against the fake invariant issue across a variety of OOD generalization benchmarks.

The generation of energetically optimal 3D molecular conformers is crucial in cheminformatics and drug discovery. While deep generative models have been utilized for direct generation in Euclidean space, this approach encounters challenges, including the complexity of navigating a vast search space. Recent generative models that implement simplifications to circumvent these challenges have achieved state-of-the-art results, but this simplified approach unavoidably creates a gap between the generated conformers and the ground-truth conformational landscape. To bridge this gap, we introduce DiSCO: Diffusion Schrödinger Bridge for Molecular Conformer Optimization, a novel diffusion framework that enables direct learning of nonlinear diffusion processes in prior-constrained Euclidean space for the optimization of 3D molecular conformers. Through the incorporation of an SE(3)-equivariant Schrödinger bridge, we establish the roto-translational equivariance of the generated conformers. Our framework is model-agnostic and offers an easily implementable solution for the post hoc optimization of conformers produced by any generation method. Through comprehensive evaluations and analyses, we establish the strengths of our framework, substantiating the application of the Schrödinger bridge for molecular conformer optimization. First, our approach consistently outperforms four baseline approaches, producing conformers with higher diversity and improved quality. Then, we show that the intermediate conformers generated during our diffusion process exhibit valid and chemically meaningful characteristics. We also demonstrate the robustness of our method when starting from conformers of diverse quality, including those unseen during training. Lastly, we show that the precise generation of low-energy conformers via our framework helps in enhancing the downstream prediction of molecular properties. The code is available at https://github.com/Danyeong-Lee/DiSCO.

Fraud detection on multi-relation graphs aims to identify fraudsters in graphs. Graph Neural Network (GNN) models leverage graph structures to pass messages from neighbors to the target nodes, thereby enriching the representations of those target nodes. However, feature and structural inconsistency in the graph, owing to fraudsters' camouflage behaviors, diminish the suspiciousness of fraud nodes which hinders the effectiveness of GNN-based models. In this work, we propose DiG-In-GNN, Discriminative Feature Guided GNN against Inconsistency, to dig into graphs for fraudsters. Specifically, we use multi-scale contrastive learning from the perspective of the neighborhood subgraph where the target node is located to generate guidance nodes to cope with the feature inconsistency. Then, guided by the guidance nodes, we conduct fine-grained neighbor selection through reinforcement learning for each neighbor node to precisely filter nodes that can enhance the message passing and therefore alleviate structural inconsistency. Finally, the two modules are integrated together to obtain discriminable representations of the nodes. Experiments on three fraud detection datasets demonstrate the superiority of the proposed method DiG-In-GNN, which obtains up to 20.73% improvement over previous state-of-the-art methods. Our code can be found at https://github.com/GraphBerry/DiG-In-GNN.

Driven by generative AI and the Internet, there is an increasing availability of a wide variety of images, leading to the significant and popular task of cross-domain image retrieval. To reduce annotation costs and increase performance, this paper focuses on an untouched but challenging problem, i.e., cross-domain image retrieval with partial labels (PCIR). Specifically, PCIR faces great challenges due to the ambiguous supervision signal and the domain gap. To address these challenges, we propose a novel method called disambiguated domain alignment (DiDA) for cross-domain retrieval with partial labels. In detail, DiDA elaborates a novel prototype-score unitization learning mechanism (PSUL) to extract common discriminative representations by simultaneously disambiguating the partial labels and narrowing the domain gap. Additionally, DiDA proposes a prototype-based domain alignment mechanism (PBDA) to further bridge the inherent cross-domain discrepancy. Attributed to PSUL and PBDA, our DiDA effectively excavates domain-invariant discrimination for cross-domain image retrieval. We demonstrate the effectiveness of DiDA through comprehensive experiments on three benchmarks, comparing it to existing state-of-the-art methods. Code available: https://github.com/lhrrrrrr/DiDA.

Robot grasp dataset is the basis of designing the robot's grasp generation model. Compared with the building grasp dataset for Low-DOF grippers, it is harder for High-DOF dexterous robot hand. Most current datasets meet the needs of generating stable grasps, but they are not suitable for dexterous hands to complete human-like functional grasp, such as grasp the handle of a cup or pressing the button of a flashlight, so as to enable robots to complete subsequent functional manipulation action autonomously, and there is no dataset with functional grasp pose annotations at present. This paper develops a unique Cost-Effective Real-Simulation Annotation System by leveraging natural hand's actions. The system is able to capture a functional grasp of a dexterous hand in a simulated environment assisted by human demonstration in real world. By using this system, dexterous grasp data can be collected efficiently as well as cost-effective. Finally, we construct the first dexterous functional grasp dataset with rich pose annotations. A Functional Grasp Synthesis Model is also provided to validate the effectiveness of the proposed system and dataset. Our project page is: https://hjlllll.github.io/DFG/.