Hang Zhao

Tianyuan Yuan, Yicheng Liu, Yue Wang et al.

High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on single-frame input. This approach limits their stability and performance in complex scenarios such as occlusions, largely due to the absence of temporal information. Moreover, their performance diminishes when applied to broader perception ranges. In this paper, we present StreamMapNet, a novel online mapping pipeline adept at long-sequence temporal modeling of videos. StreamMapNet employs multi-point attention and temporal information which empowers the construction of large-range local HD maps with high stability and further addresses the limitations of existing methods. Furthermore, we critically examine widely used online HD Map construction benchmark and datasets, Argoverse2 and nuScenes, revealing significant bias in the existing evaluation protocols. We propose to resplit the benchmarks according to geographical spans, promoting fair and precise evaluations. Experimental results validate that StreamMapNet significantly outperforms existing methods across all settings while maintaining an online inference speed of $14.2$ FPS. Our code is available at https://github.com/yuantianyuan01/StreamMapNet.

Simian Luo, Yiqin Tan, Suraj Patil et al.

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models (LDMs), requiring only ~32 A100 GPU training hours. This report further extends LCMs' potential in two aspects: First, by applying LoRA distillation to Stable-Diffusion models including SD-V1.5, SSD-1B, and SDXL, we have expanded LCM's scope to larger models with significantly less memory consumption, achieving superior image generation quality. Second, we identify the LoRA parameters obtained through LCM distillation as a universal Stable-Diffusion acceleration module, named LCM-LoRA. LCM-LoRA can be directly plugged into various Stable-Diffusion fine-tuned models or LoRAs without training, thus representing a universally applicable accelerator for diverse image generation tasks. Compared with previous numerical PF-ODE solvers such as DDIM, DPM-Solver, LCM-LoRA can be viewed as a plug-in neural PF-ODE solver that possesses strong generalization abilities. Project page: https://github.com/luosiallen/latent-consistency-model.

Zui Chen, Yansen Jing, Shengcheng Yuan et al.

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.

Xinhao Liu, Moonjun Gong, Qi Fang et al.

Scene completion and forecasting are two popular perception problems in research for mobile agents like autonomous vehicles. Existing approaches treat the two problems in isolation, resulting in a separate perception of the two aspects. In this paper, we introduce a novel LiDAR perception task of Occupancy Completion and Forecasting (OCF) in the context of autonomous driving to unify these aspects into a cohesive framework. This task requires new algorithms to address three challenges altogether: (1) sparse-to-dense reconstruction, (2) partial-to-complete hallucination, and (3) 3D-to-4D prediction. To enable supervision and evaluation, we curate a large-scale dataset termed OCFBench from public autonomous driving datasets. We analyze the performance of closely related existing baseline models and our own ones on our dataset. We envision that this research will inspire and call for further investigation in this evolving and crucial area of 4D perception. Our code for data curation and baseline implementation is available at https://github.com/ai4ce/Occ4cast.

Chenxu Hu, Jie Fu, Chenzhuang Du et al.

Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .

Tong Shao, Zhuotao Tian, Hang Zhao et al.

CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of "global" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase.

Simian Luo, Yiqin Tan, Longbo Huang et al.

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al). Viewing the guided reverse diffusion process as solving an augmented probability flow ODE (PF-ODE), LCMs are designed to directly predict the solution of such ODE in latent space, mitigating the need for numerous iterations and allowing rapid, high-fidelity sampling. Efficiently distilled from pre-trained classifier-free guided diffusion models, a high-quality 768 x 768 2~4-step LCM takes only 32 A100 GPU hours for training. Furthermore, we introduce Latent Consistency Fine-tuning (LCF), a novel method that is tailored for fine-tuning LCMs on customized image datasets. Evaluation on the LAION-5B-Aesthetics dataset demonstrates that LCMs achieve state-of-the-art text-to-image generation performance with few-step inference. Project Page: https://latent-consistency-models.github.io/

Tong Zhang, Yingdong Hu, Hanchen Cui et al.

Robots rely heavily on sensors, especially RGB and depth cameras, to perceive and interact with the world. RGB cameras record 2D images with rich semantic information while missing precise spatial information. On the other side, depth cameras offer critical 3D geometry data but capture limited semantics. Therefore, integrating both modalities is crucial for learning representations for robotic perception and control. However, current research predominantly focuses on only one of these modalities, neglecting the benefits of incorporating both. To this end, we present $\textbf{Semantic-Geometric Representation} (\textbf{SGR})$, a universal perception module for robotics that leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning. Our experiments demonstrate that SGR empowers the agent to successfully complete a diverse range of simulated and real-world robotic manipulation tasks, outperforming state-of-the-art methods significantly in both single-task and multi-task settings. Furthermore, SGR possesses the capability to generalize to novel semantic attributes, setting it apart from the other methods. Project website: https://semantic-geometric-representation.github.io.

Zenan Li, Fan Nie, Qiao Sun et al.

Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which, however, fails in stochastic environments with incorrect assumptions that identical actions can consistently achieve the same goal. In this paper, we introduce an UNcertainty-awaRE deciSion Transformer (UNREST) for planning in stochastic driving environments without introducing additional transition or complex generative models. Specifically, UNREST estimates uncertainties by conditional mutual information between transitions and returns. Discovering 'uncertainty accumulation' and 'temporal locality' properties of driving environments, we replace the global returns in decision transformers with truncated returns less affected by environments to learn from actual outcomes of actions rather than environment transitions. We also dynamically evaluate uncertainty at inference for cautious planning. Extensive experiments demonstrate UNREST's superior performance in various driving scenarios and the power of our uncertainty estimation strategy.

Wenyu Han, Congcong Wen, Lazarus Chok et al.

City modeling and generation have attracted an increased interest in various applications, including gaming, urban planning, and autonomous driving. Unlike previous works focused on the generation of single objects or indoor scenes, the huge volumes of spatial data in cities pose a challenge to the generative models. Furthermore, few publicly available 3D real-world city datasets also hinder the development of methods for city generation. In this paper, we first collect over 3,000,000 geo-referenced objects for the city of New York, Zurich, Tokyo, Berlin, Boston and several other large cities. Based on this dataset, we propose AETree, a tree-structured auto-encoder neural network, for city generation. Specifically, we first propose a novel Spatial-Geometric Distance (SGD) metric to measure the similarity between building layouts and then construct a binary tree over the raw geometric data of building based on the SGD metric. Next, we present a tree-structured network whose encoder learns to extract and merge spatial information from bottom-up iteratively. The resulting global representation is reversely decoded for reconstruction or generation. To address the issue of long-dependency as the level of the tree increases, a Long Short-Term Memory (LSTM) Cell is employed as a basic network element of the proposed AETree. Moreover, we introduce a novel metric, Overlapping Area Ratio (OAR), to quantitatively evaluate the generation results. Experiments on the collected dataset demonstrate the effectiveness of the proposed model on 2D and 3D city generation. Furthermore, the latent features learned by AETree can serve downstream urban planning applications.

Haoren Zhao, Tianyi Chen, Zhen Wang

Graphical User Interface (GUI) grounding models are crucial for enabling intelligent agents to understand and interact with complex visual interfaces. However, these models face significant robustness challenges in real-world scenarios due to natural noise and adversarial perturbations, and their robustness remains underexplored. In this study, we systematically evaluate the robustness of state-of-the-art GUI grounding models, such as UGround, under three conditions: natural noise, untargeted adversarial attacks, and targeted adversarial attacks. Our experiments, which were conducted across a wide range of GUI environments, including mobile, desktop, and web interfaces, have clearly demonstrated that GUI grounding models exhibit a high degree of sensitivity to adversarial perturbations and low-resolution conditions. These findings provide valuable insights into the vulnerabilities of GUI grounding models and establish a strong benchmark for future research aimed at enhancing their robustness in practical applications. Our code is available at https://github.com/ZZZhr-1/Robust_GUI_Grounding.

Zitong Wang, Hang Zhao, Qianyu Zhou et al.

Diffusion models have recently motivated great success in many generation tasks like object removal. Nevertheless, existing image decomposition methods struggle to disentangle semi-transparent or transparent layer occlusions due to mask prior dependencies, static object assumptions, and the lack of datasets. In this paper, we delve into a novel task: Layer-Wise Decomposition of Alpha-Composited Images, aiming to recover constituent layers from single overlapped images under the condition of semi-transparent/transparent alpha layer non-linear occlusion. To address challenges in layer ambiguity, generalization, and data scarcity, we first introduce AlphaBlend, the first large-scale and high-quality dataset for transparent and semi-transparent layer decomposition, supporting six real-world subtasks (e.g., translucent flare removal, semi-transparent cell decomposition, glassware decomposition). Building on this dataset, we present DiffDecompose, a diffusion Transformer-based framework that learns the posterior over possible layer decompositions conditioned on the input image, semantic prompts, and blending type. Rather than regressing alpha mattes directly, DiffDecompose performs In-Context Decomposition, enabling the model to predict one or multiple layers without per-layer supervision, and introduces Layer Position Encoding Cloning to maintain pixel-level correspondence across layers. Extensive experiments on the proposed AlphaBlend dataset and public LOGO dataset verify the effectiveness of DiffDecompose. The code and dataset will be available upon paper acceptance. Our code will be available at: https://github.com/Wangzt1121/DiffDecompose.

Xiaoyu Tian, Junru Gu, Bailin Li et al.

A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors. We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities. DriveVLM integrates a unique combination of reasoning modules for scene description, scene analysis, and hierarchical planning. Furthermore, recognizing the limitations of VLMs in spatial reasoning and heavy computational requirements, we propose DriveVLM-Dual, a hybrid system that synergizes the strengths of DriveVLM with the traditional autonomous driving pipeline. Experiments on both the nuScenes dataset and our SUP-AD dataset demonstrate the efficacy of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Finally, we deploy the DriveVLM-Dual on a production vehicle, verifying it is effective in real-world autonomous driving environments.

Chenyang Jiang, Zhengcen Li, Hang Zhao et al.

Dataset distillation has emerged as a promising paradigm that synthesizes compact, informative datasets capable of retaining the knowledge of large-scale counterparts, thereby addressing the substantial computational and storage burdens of modern model training. Conventional approaches typically rely on dense pixel-level representations, which introduce redundancy and are difficult to scale up. In this work, we propose GSDD, a novel and efficient sparse representation for dataset distillation based on 2D Gaussians. Instead of representing all pixels equally, GSDD encodes critical discriminative information in a distilled image using only a small number of Gaussian primitives. This sparse representation could improve dataset diversity under the same storage budget, enhancing coverage of difficult samples and boosting distillation performance. To ensure both efficiency and scalability, we adapt CUDA-based splatting operators for parallel inference and training, enabling high-quality rendering with minimal computational and memory overhead. Our method is simple yet effective, broadly applicable to different distillation pipelines, and highly scalable. Experiments show that GSDD achieves state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet subsets, while remaining highly efficient encoding and decoding cost. Our code is available at https://github.com/j-cyoung/GSDatasetDistillation.

Hanhan Li, Ariel Gordon, Hang Zhao et al.

We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including methods that require semantic input. Code is at https://github.com/google-research/google-research/tree/master/depth_and_motion_learning .

Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang et al. · microsoft-research

To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg.

Yijun Yuan, Zhuoguang Chen, Kenan Li et al.

We present SLAM-Former, a novel neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a backend that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and backend to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM-Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods.

Anna Min, Chenxu Hu, Yi Ren et al.

Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and attitudes in communication. To address this, our research introduces a novel, carefully curated multilingual dataset from various movie audio tracks. Each dataset pair is precisely matched for paralinguistic information and duration. We enhance this by integrating multiple prosody transfer techniques, aiming for translations that are accurate, natural-sounding, and rich in paralinguistic details. Our experimental results confirm that our model retains more paralinguistic information from the source speech while maintaining high standards of translation accuracy and naturalness.

Qi Li, Kaichun Mo, Yanchao Yang et al.

Building embodied intelligent agents that can interact with 3D indoor environments has received increasing research attention in recent years. While most works focus on single-object or agent-object visual functionality and affordances, our work proposes to study a new kind of visual relationship that is also important to perceive and model -- inter-object functional relationships (e.g., a switch on the wall turns on or off the light, a remote control operates the TV). Humans often spend little or no effort to infer these relationships, even when entering a new room, by using our strong prior knowledge (e.g., we know that buttons control electrical devices) or using only a few exploratory interactions in cases of uncertainty (e.g., multiple switches and lights in the same room). In this paper, we take the first step in building AI system learning inter-object functional relationships in 3D indoor environments with key technical contributions of modeling prior knowledge by training over large-scale scenes and designing interactive policies for effectively exploring the training scenes and quickly adapting to novel test scenes. We create a new benchmark based on the AI2Thor and PartNet datasets and perform extensive experiments that prove the effectiveness of our proposed method. Results show that our model successfully learns priors and fast-interactive-adaptation strategies for exploring inter-object functional relationships in complex 3D scenes. Several ablation studies further validate the usefulness of each proposed module.

Yue Wang, Vitor Guizilini, Tianyuan Zhang et al.

We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D information, our method manipulates predictions directly in 3D space. Our architecture extracts 2D features from multiple camera images and then uses a sparse set of 3D object queries to index into these 2D features, linking 3D positions to multi-view images using camera transformation matrices. Finally, our model makes a bounding box prediction per object query, using a set-to-set loss to measure the discrepancy between the ground-truth and the prediction. This top-down approach outperforms its bottom-up counterpart in which object bounding box prediction follows per-pixel depth estimation, since it does not suffer from the compounding error introduced by a depth prediction model. Moreover, our method does not require post-processing such as non-maximum suppression, dramatically improving inference speed. We achieve state-of-the-art performance on the nuScenes autonomous driving benchmark.

Lu Mi, Hang Zhao, Charlie Nash et al.

High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning. However, there are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack to generalize onto new unseen scenarios. To address this issue, we introduce a new challenging task to generate HD maps. In this work, we explore several autoregressive models using different data representations, including sequence, plain graph, and hierarchical graph. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps through a coarse-to-fine approach. Experiments on the Argoverse dataset and an in-house dataset show that HDMapGen significantly outperforms baseline methods. Additionally, we demonstrate that HDMapGen achieves high scalability and efficiency.

Sucheng Ren, Zhengqi Gao, Tianyu Hua et al.

Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an insufficient amount of training data (e.g., ImageNet). To make it into practical utility, we propose a novel distillation-based method to train vision transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, we introduce lightweight teachers with different architectural inductive biases (e.g., convolution and involution) to co-advise the student transformer. The key is that teachers with different inductive biases attain different knowledge despite that they are trained on the same dataset, and such different knowledge compounds and boosts the student's performance during distillation. Equipped with this cross inductive bias distillation method, our vision transformers (termed as CivT) outperform all previous transformers of the same architecture on ImageNet.

Chenzhuang Du, Tingle Li, Yichen Liu et al.

Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are mostly based on joint training, often suffer from learning inferior representations of each modality. We name this problem Modality Failure, and hypothesize that the imbalance of modalities and the implicit bias of common objectives in fusion method prevent encoders of each modality from sufficient feature learning. To this end, we propose a new multi-modal learning method, Uni-Modal Teacher, which combines the fusion objective and uni-modal distillation to tackle the modality failure problem. We show that our method not only drastically improves the representation of each modality, but also improves the overall multi-modal task performance. Our method can be effectively generalized to most multi-modal fusion approaches. We achieve more than 3% improvement on the VGGSound audio-visual classification task, as well as improving performance on the NYU depth V2 RGB-D image segmentation task.

Yu Huang, Chenzhuang Du, Zihui Xue et al.

The world provides us with data of multiple modalities. Intuitively, models fusing data from different modalities outperform their uni-modal counterparts, since more information is aggregated. Recently, joining the success of deep learning, there is an influential line of work on deep multi-modal learning, which has remarkable empirical results on various applications. However, theoretical justifications in this field are notably lacking. Can multi-modal learning provably perform better than uni-modal? In this paper, we answer this question under a most popular multi-modal fusion framework, which firstly encodes features from different modalities into a common latent space and seamlessly maps the latent representations into the task space. We prove that learning with multiple modalities achieves a smaller population risk than only using its subset of modalities. The main intuition is that the former has a more accurate estimate of the latent space representation. To the best of our knowledge, this is the first theoretical treatment to capture important qualitative phenomena observed in real multi-modal applications from the generalization perspective. Combining with experiment results, we show that multi-modal learning does possess an appealing formal guarantee.

Tingle Li, Yichen Liu, Chenxu Hu et al.

Cycle consistent generative adversarial network (CycleGAN) and variational autoencoder (VAE) based models have gained popularity in non-parallel voice conversion recently. However, they often suffer from difficult training process and unsatisfactory results. In this paper, we propose CVC, a contrastive learning-based adversarial approach for voice conversion. Compared to previous CycleGAN-based methods, CVC only requires an efficient one-way GAN training by taking the advantage of contrastive learning. When it comes to non-parallel one-to-one voice conversion, CVC is on par or better than CycleGAN and VAE while effectively reducing training time. CVC further demonstrates superior performance in many-to-one voice conversion, enabling the conversion from unseen speakers.

Jianren Wang, Yujie Lu, Hang Zhao

Developing agents that can perform complex control tasks from high dimensional observations such as pixels is challenging due to difficulties in learning dynamics efficiently. In this work, we propose to learn forward and inverse dynamics in a fully unsupervised manner via contrastive estimation. Specifically, we train a forward dynamics model and an inverse dynamics model in the feature space of states and actions with data collected from random exploration. Unlike most existing deterministic models, our energy-based model takes into account the stochastic nature of agent-environment interactions. We demonstrate the efficacy of our approach across a variety of tasks including goal-directed planning and imitation from observations. Project videos and code are at https://jianrenw.github.io/cloud/.

Yunchao Wei, Shuai Zheng, Ming-Ming Cheng et al.

Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotated datasets. The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training. A massive amount of user-generated data nowadays available on multiple internet services. How to leverage those and improve the machine learning models is a high impact problem. We organize the challenges in conjunction with the workshop. The goal of these challenges is to find the state-of-the-art approaches in the weakly supervised learning setting for object detection, semantic segmentation, and scene parsing. There are three tracks in the challenge, i.e., weakly supervised semantic segmentation (Track 1), weakly supervised scene parsing (Track 2), and weakly supervised object localization (Track 3). In Track 1, based on ILSVRC DET, we provide pixel-level annotations of 15K images from 200 categories for evaluation. In Track 2, we provide point-based annotations for the training set of ADE20K. In Track 3, based on ILSVRC CLS-LOC, we provide pixel-level annotations of 44,271 images for evaluation. Besides, we further introduce a new evaluation metric proposed by \cite{zhang2020rethinking}, i.e., IoU curve, to measure the quality of the generated object localization maps. This technical report summarizes the highlights from the challenge. The challenge submission server and the leaderboard will continue to open for the researchers who are interested in it. More details regarding the challenge and the benchmarks are available at https://lidchallenge.github.io

Hang Zhao, Yujing Wang, Juanyong Duan et al.

Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications. Recent approaches have achieved significant progress in this topic, but there is remaining limitations. One major limitation is that they do not capture the relationships between different time-series explicitly, resulting in inevitable false alarms. In this paper, we propose a novel self-supervised framework for multivariate time-series anomaly detection to address this issue. Our framework considers each univariate time-series as an individual feature and includes two graph attention layers in parallel to learn the complex dependencies of multivariate time-series in both temporal and feature dimensions. In addition, our approach jointly optimizes a forecasting-based model and are construction-based model, obtaining better time-series representations through a combination of single-timestamp prediction and reconstruction of the entire time-series. We demonstrate the efficacy of our model through extensive experiments. The proposed method outperforms other state-of-the-art models on three real-world datasets. Further analysis shows that our method has good interpretability and is useful for anomaly diagnosis.

Chuang Gan, Deng Huang, Hang Zhao et al.

Recent deep learning approaches have achieved impressive performance on visual sound separation tasks. However, these approaches are mostly built on appearance and optical flow like motion feature representations, which exhibit limited abilities to find the correlations between audio signals and visual points, especially when separating multiple instruments of the same types, such as multiple violins in a scene. To address this, we propose "Music Gesture," a keypoint-based structured representation to explicitly model the body and finger movements of musicians when they perform music. We first adopt a context-aware graph network to integrate visual semantic context with body dynamics, and then apply an audio-visual fusion model to associate body movements with the corresponding audio signals. Experimental results on three music performance datasets show: 1) strong improvements upon benchmark metrics for hetero-musical separation tasks (i.e. different instruments); 2) new ability for effective homo-musical separation for piano, flute, and trumpet duets, which to our best knowledge has never been achieved with alternative methods. Project page: http://music-gesture.csail.mit.edu.

Jianren Wang, Zhaoyuan Fang, Hang Zhao

We present AlignNet, a model that synchronizes videos with reference audios under non-uniform and irregular misalignments. AlignNet learns the end-to-end dense correspondence between each frame of a video and an audio. Our method is designed according to simple and well-established principles: attention, pyramidal processing, warping, and affinity function. Together with the model, we release a dancing dataset Dance50 for training and evaluation. Qualitative, quantitative and subjective evaluation results on dance-music alignment and speech-lip alignment demonstrate that our method far outperforms the state-of-the-art methods. Project video and code are available at https://jianrenw.github.io/AlignNet.

Chuang Gan, Hang Zhao, Peihao Chen et al.

Humans are able to localize objects in the environment using both visual and auditory cues, integrating information from multiple modalities into a common reference frame. We introduce a system that can leverage unlabeled audio-visual data to learn to localize objects (moving vehicles) in a visual reference frame, purely using stereo sound at inference time. Since it is labor-intensive to manually annotate the correspondences between audio and object bounding boxes, we achieve this goal by using the co-occurrence of visual and audio streams in unlabeled videos as a form of self-supervision, without resorting to the collection of ground-truth annotations. In particular, we propose a framework that consists of a vision "teacher" network and a stereo-sound "student" network. During training, knowledge embodied in a well-established visual vehicle detection model is transferred to the audio domain using unlabeled videos as a bridge. At test time, the stereo-sound student network can work independently to perform object localization us-ing just stereo audio and camera meta-data, without any visual input. Experimental results on a newly collected Au-ditory Vehicle Tracking dataset verify that our proposed approach outperforms several baseline approaches. We also demonstrate that our cross-modal auditory localization approach can assist in the visual localization of moving vehicles under poor lighting conditions.

Andrew Rouditchenko, Hang Zhao, Chuang Gan et al.

Segmenting objects in images and separating sound sources in audio are challenging tasks, in part because traditional approaches require large amounts of labeled data. In this paper we develop a neural network model for visual object segmentation and sound source separation that learns from natural videos through self-supervision. The model is an extension of recently proposed work that maps image pixels to sounds. Here, we introduce a learning approach to disentangle concepts in the neural networks, and assign semantic categories to network feature channels to enable independent image segmentation and sound source separation after audio-visual training on videos. Our evaluations show that the disentangled model outperforms several baselines in semantic segmentation and sound source separation.

Hang Zhao, Chuang Gan, Wei-Chiu Ma et al.

Sounds originate from object motions and vibrations of surrounding air. Inspired by the fact that humans is capable of interpreting sound sources from how objects move visually, we propose a novel system that explicitly captures such motion cues for the task of sound localization and separation. Our system is composed of an end-to-end learnable model called Deep Dense Trajectory (DDT), and a curriculum learning scheme. It exploits the inherent coherence of audio-visual signals from a large quantities of unlabeled videos. Quantitative and qualitative evaluations show that comparing to previous models that rely on visual appearance cues, our motion based system improves performance in separating musical instrument sounds. Furthermore, it separates sound components from duets of the same category of instruments, a challenging problem that has not been addressed before.

Hang Zhao, Antonio Torralba, Lorenzo Torresani et al.

This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and Segments). We leverage both consensus and disagreement among visual classifiers to automatically mine candidate short clips from unlabeled videos, which are subsequently validated by human annotators. The resulting dataset is dubbed HACS Clips. Through a separate process we also collect annotations defining action segment boundaries. This resulting dataset is called HACS Segments. Overall, HACS Clips consists of 1.5M annotated clips sampled from 504K untrimmed videos, and HACS Seg-ments contains 139K action segments densely annotatedin 50K untrimmed videos spanning 200 action categories. HACS Clips contains more labeled examples than any existing video benchmark. This renders our dataset both a large scale action recognition benchmark and an excellent source for spatiotemporal feature learning. In our transferlearning experiments on three target datasets, HACS Clips outperforms Kinetics-600, Moments-In-Time and Sports1Mas a pretraining source. On HACS Segments, we evaluate state-of-the-art methods of action proposal generation and action localization, and highlight the new challenges posed by our dense temporal annotations.

Hang Zhao, Xavier Puig, Bolei Zhou et al.

Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem. Our proposed approach to this problem is a joint image pixel and word concept embeddings framework, where word concepts are connected by semantic relations. We validate the open vocabulary prediction ability of our framework on ADE20K dataset which covers a wide variety of scenes and objects. We further explore the trained joint embedding space to show its interpretability.

Bolei Zhou, Hang Zhao, Xavier Puig et al.

Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the community's efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. A generic network design called Cascade Segmentation Module is then proposed to enable the segmentation networks to parse a scene into stuff, objects, and object parts in a cascade. We evaluate the proposed module integrated within two existing semantic segmentation networks, yielding significant improvements for scene parsing. We further show that the scene parsing networks trained on ADE20K can be applied to a wide variety of scenes and objects.

Hang Zhao, Orazio Gallo, Iuri Frosio et al.

Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much attention in the context of image processing: the default and virtually only choice is L2. In this paper, we bring attention to alternative choices for image restoration. In particular, we show the importance of perceptually-motivated losses when the resulting image is to be evaluated by a human observer. We compare the performance of several losses, and propose a novel, differentiable error function. We show that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged.