arXiv subjects

Yi-Ting Chen

Publications and source records attributed to Yi-Ting Chen.

At least 55 records · Page 3Linked to original sources

arXiv2024

RiskBench: A Scenario-based Benchmark for Risk Identification

Intelligent driving systems aim to achieve a zero-collision mobility experience, requiring interdisciplinary efforts to enhance safety performance. This work focuses on risk identification, the process of identifying and analyzing risks stemming from dynamic traffic participants and unexpected events. While significant advances have been made in the community, the current evaluation of different risk identification algorithms uses independent datasets, leading to difficulty in direct comparison and hindering collective progress toward safety performance enhancement. To address this limitation, we introduce \textbf{RiskBench}, a large-scale scenario-based benchmark for risk identification. We design a scenario taxonomy and augmentation pipeline to enable a systematic collection of ground truth risks under diverse scenarios. We assess the ability of ten algorithms to (1) detect and locate risks, (2) anticipate risks, and (3) facilitate decision-making. We conduct extensive experiments and summarize future research on risk identification. Our aim is to encourage collaborative endeavors in achieving a society with zero collisions. We have made our dataset and benchmark toolkit publicly on the project page: https://hcis-lab.github.io/RiskBench/

cs.CV↗

arXiv2023

SKT-Hang: Hanging Everyday Objects via Object-Agnostic Semantic Keypoint Trajectory Generation

We study the problem of hanging a wide range of grasped objects on diverse supporting items. Hanging objects is a ubiquitous task that is encountered in numerous aspects of our everyday lives. However, both the objects and supporting items can exhibit substantial variations in their shapes and structures, bringing two challenging issues: (1) determining the task-relevant geometric structures across different objects and supporting items, and (2) identifying a robust action sequence to accommodate the shape variations of supporting items. To this end, we propose Semantic Keypoint Trajectory (SKT), an object-agnostic representation that is highly versatile and applicable to various everyday objects. We also propose Shape-conditioned Trajectory Deformation Network (SCTDN), a model that learns to generate SKT by deforming a template trajectory based on the task-relevant geometric structure features of the supporting items. We conduct extensive experiments and demonstrate substantial improvements in our framework over existing robot hanging methods in the success rate and inference time. Finally, our simulation-trained framework shows promising hanging results in the real world. For videos and supplementary materials, please visit our project webpage: https://hcis-lab.github.io/SKT-Hang/.

cs.RO↗

arXiv2023

Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings

AV-HuBERT, a multi-modal self-supervised learning model, has been shown to be effective for categorical problems such as automatic speech recognition and lip-reading. This suggests that useful audio-visual speech representations can be obtained via utilizing multi-modal self-supervised embeddings. Nevertheless, it is unclear if such representations can be generalized to solve real-world multi-modal AV regression tasks, such as audio-visual speech enhancement (AVSE) and audio-visual speech separation (AVSS). In this study, we leveraged the pre-trained AV-HuBERT model followed by an SE module for AVSE and AVSS. Comparative experimental results demonstrate that our proposed model performs better than the state-of-the-art AVSE and traditional audio-only SE models. In summary, our results confirm the effectiveness of our proposed model for the AVSS task with proper fine-tuning strategies, demonstrating that multi-modal self-supervised embeddings obtained from AV-HuBERT can be generalized to audio-visual regression tasks.

eess.AS↗

arXiv2023

Combined Scaling for Zero-shot Transfer Learning

We present a combined scaling method - named BASIC - that achieves 85.7% top-1 accuracy on the ImageNet ILSVRC-2012 validation set without learning from any labeled ImageNet example. This accuracy surpasses best published similar models - CLIP and ALIGN - by 9.3%. Our BASIC model also shows significant improvements in robustness benchmarks. For instance, on 5 test sets with natural distribution shifts such as ImageNet-{A,R,V2,Sketch} and ObjectNet, our model achieves 84.3% top-1 average accuracy, only a small drop from its original ImageNet accuracy. To achieve these results, we scale up the contrastive learning framework of CLIP and ALIGN in three dimensions: data size, model size, and batch size. Our dataset has 6.6B noisy image-text pairs, which is 4x larger than ALIGN, and 16x larger than CLIP. Our largest model has 3B weights, which is 3.75x larger in parameters and 8x larger in FLOPs than ALIGN and CLIP. Finally, our batch size is 65536 which is 2x more than CLIP and 4x more than ALIGN. We encountered two main challenges with the scaling rules of BASIC. First, the main challenge with implementing the combined scaling rules of BASIC is the limited memory of accelerators, such as GPUs and TPUs. To overcome the memory limit, we propose two simple methods which make use of gradient checkpointing and model parallelism. Second, while increasing the dataset size and the model size has been the defacto method to improve the performance of deep learning models like BASIC, the effect of a large contrastive batch size on such contrastive-trained image-text models is not well-understood. To shed light on the benefits of large contrastive batch sizes, we develop a theoretical framework which shows that larger contrastive batch sizes lead to smaller generalization gaps for image-text models such as BASIC.

cs.LG↗

arXiv2023

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this temporal reasoning with a graph neural network, where edges represent the relationship between candidate detections in different time frames. After semi-supervised learning, our method achieves state-of-the-art detection performance on the challenging nuScenes and H3D benchmarks, compared to baselines trained on the same amount of labeled data. Project and code are released at https://www.jianrenw.com/SOD-TGNN/.

cs.CV↗

arXiv2023

DROID: Driver-centric Risk Object Identification

Identification of high-risk driving situations is generally approached through collision risk estimation or accident pattern recognition. In this work, we approach the problem from the perspective of subjective risk. We operationalize subjective risk assessment by predicting driver behavior changes and identifying the cause of changes. To this end, we introduce a new task called driver-centric risk object identification (DROID), which uses egocentric video to identify object(s) influencing a driver's behavior, given only the driver's response as the supervision signal. We formulate the task as a cause-effect problem and present a novel two-stage DROID framework, taking inspiration from models of situation awareness and causal inference. A subset of data constructed from the Honda Research Institute Driving Dataset (HDD) is used to evaluate DROID. We demonstrate state-of-the-art DROID performance, even compared with strong baseline models using this dataset. Additionally, we conduct extensive ablative studies to justify our design choices. Moreover, we demonstrate the applicability of DROID for risk assessment.

cs.CV↗

arXiv2023

CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping

Point cloud data plays an essential role in robotics and self-driving applications. Yet, annotating point cloud data is time-consuming and nontrivial while they enable learning discriminative 3D representations that empower downstream tasks, such as classification and segmentation. Recently, contrastive learning-based frameworks have shown promising results for learning 3D representations in a self-supervised manner. However, existing contrastive learning methods cannot precisely encode and associate structural features and search the higher dimensional augmentation space efficiently. In this paper, we present CLR-GAM, a novel contrastive learning-based framework with Guided Augmentation (GA) for efficient dynamic exploration strategy and Guided Feature Mapping (GFM) for similar structural feature association between augmented point clouds. We empirically demonstrate that the proposed approach achieves state-of-the-art performance on both simulated and real-world 3D point cloud datasets for three different downstream tasks, i.e., 3D point cloud classification, few-shot learning, and object part segmentation.

cs.CV↗

arXiv2023

Learning Road Scene-level Representations via Semantic Region Prediction

In this work, we tackle two vital tasks in automated driving systems, i.e., driver intent prediction and risk object identification from egocentric images. Mainly, we investigate the question: what would be good road scene-level representations for these two tasks? We contend that a scene-level representation must capture higher-level semantic and geometric representations of traffic scenes around ego-vehicle while performing actions to their destinations. To this end, we introduce the representation of semantic regions, which are areas where ego-vehicles visit while taking an afforded action (e.g., left-turn at 4-way intersections). We propose to learn scene-level representations via a novel semantic region prediction task and an automatic semantic region labeling algorithm. Extensive evaluations are conducted on the HDD and nuScenes datasets, and the learned representations lead to state-of-the-art performance for driver intention prediction and risk object identification.

cs.CV↗

arXiv2023

Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping

A spatial AI that can perform complex tasks through visual signals and cooperate with humans is highly anticipated. To achieve this, we need a visual SLAM that easily adapts to new scenes without pre-training and generates dense maps for downstream tasks in real-time. None of the previous learning-based and non-learning-based visual SLAMs satisfy all needs due to the intrinsic limitations of their components. In this work, we develop a visual SLAM named Orbeez-SLAM, which successfully collaborates with implicit neural representation and visual odometry to achieve our goals. Moreover, Orbeez-SLAM can work with the monocular camera since it only needs RGB inputs, making it widely applicable to the real world. Results show that our SLAM is up to 800x faster than the strong baseline with superior rendering outcomes. Code link: https://github.com/MarvinChung/Orbeez-SLAM.

cs.RO↗

arXiv2023

Shape-aware Text-driven Layered Video Editing

Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than object shape changes due to the limitation of using a fixed UV mapping field for texture atlas. We present a shape-aware, text-driven video editing method to tackle this challenge. To handle shape changes in video editing, we first propagate the deformation field between the input and edited keyframe to all frames. We then leverage a pre-trained text-conditioned diffusion model as guidance for refining shape distortion and completing unseen regions. The experimental results demonstrate that our method can achieve shape-aware consistent video editing and compare favorably with the state-of-the-art.

cs.CV↗

arXiv2022

MetaDIP: Accelerating Deep Image Prior with Meta Learning

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant computational cost. In this work we use meta-learning to massively accelerate DIP-based reconstructions. By learning a proper initialization for the DIP weights, we demonstrate a 10x improvement in runtimes across a range of inverse imaging tasks. Moreover, we demonstrate that a network trained to quickly reconstruct faces also generalizes to reconstructing natural image patches.

cs.CV↗

arXiv2022

Multimodal Object Detection via Probabilistic Ensembling

Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study multimodal object detection with RGB and thermal cameras, since the latter provides much stronger object signatures under poor illumination. We explore strategies for fusing information from different modalities. Our key contribution is a probabilistic ensembling technique, ProbEn, a simple non-learned method that fuses together detections from multi-modalities. We derive ProbEn from Bayes' rule and first principles that assume conditional independence across modalities. Through probabilistic marginalization, ProbEn elegantly handles missing modalities when detectors do not fire on the same object. Importantly, ProbEn also notably improves multimodal detection even when the conditional independence assumption does not hold, e.g., fusing outputs from other fusion methods (both off-the-shelf and trained in-house). We validate ProbEn on two benchmarks containing both aligned (KAIST) and unaligned (FLIR) multimodal images, showing that ProbEn outperforms prior work by more than 13% in relative performance!

cs.CV↗

arXiv2022

ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images

Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models.

eess.IV↗

arXiv2022

High-Performance Microwave Frequency Standard Based on Sympathetically Cooled Ions

The ion microwave frequency standard is a candidate for the next generation of microwave frequency standard with the potential for very wide applications. The Dick effect and second-order Doppler frequency shift (SODFS) limit the performance of ion microwave frequency standards. The introduction of sympathetic cooling technology can suppress the Dick effect and SODFS and improve the stability and accuracy of the frequency standard. However, the sympathetically-cooled ion microwave frequency standard has seldom been studied before. This paper reports the first sympathetically-cooled ion microwave frequency standard in a Paul trap. Using laser-cooled ${}^{40}\mathrm{Ca}^{+}$ as coolant ions, ${}^{113}\mathrm{Cd}^{+}$ ion crystal is cooled to below 100 mK and has a coherence lifetime of over 40 s. The short-term frequency stability reached $3.48 \times 10^{-13}/τ^{1/2}$, which is comparable to that of the mercury ion frequency standard. Its uncertainty is $1.5\times 10^{-14}$, which is better than that of directly laser-cooled cadmium ion frequency standard.

physics.atom-ph↗

arXiv2021

Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabilities are essential in robotics applications: (1) Behaving in compound tasks that contain multiple stages. (2) Retrieving knowledge from few length-variant and misalignment demonstrations. (3) Learning from a different expert. No previous work can achieve these abilities at the same time. In this work, we conduct FSIL problem under the union of above settings and introduce a novel stage conscious attention network (SCAN) to retrieve knowledge from few demonstrations simultaneously. SCAN uses an attention module to identify each stage in length-variant demonstrations. Moreover, it is designed under demonstration-conditioned policy that learns the relationship between experts and agents. Experiment results show that SCAN can learn from different experts without fine-tuning and outperform baselines in complicated compound tasks with explainable visualization.

cs.RO↗

arXiv2021

Nanoscale electronic transparency of wafer-scale hexagonal boron nitride

Monolayer hBN has attracted interest as a potentially weakly interacting 2D insulating layer in heterostructures. Recently, wafer-scale hBN growth on Cu(111) has been demonstrated for semiconductor chip fabrication processes and transistor action. For all these applications, the perturbation on the underlying electronically active layers is critical. For example, while hBN on Cu(111) has been shown to preserve the Cu(111) surface state 2D electron gas, it was previously unknown how this varies over the sample and how it is affected by local electronic corrugation. Here, we demonstrate that the Cu(111) surface state under wafer-scale hBN is robustly homogeneous in energy and spectral weight over nanometer length scales and over atomic terraces. We contrast this with a benchmark spectral feature associated with interaction between BN atoms and the Cu surface, which varies with the Moiré pattern of the hBN/Cu(111) sample and is dependent on atomic registry. This work demonstrates that fragile 2D electron systems and interface states are largely unperturbed by local variations created by the hBN due to atomic-scale interactions with the substrate, thus providing a remarkably transparent window on low-energy electronic structure below the hBN monolayer.

cond-mat.mtrl-sci↗

arXiv2021

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) process. This costly curation process limits the size of datasets and hence hinders the scaling of trained models. In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme. Our visual representation achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations enables zero-shot image classification and also set new state-of-the-art results on Flickr30K and MSCOCO image-text retrieval benchmarks, even when compared with more sophisticated cross-attention models. The representations also enable cross-modality search with complex text and text + image queries.

cs.CV↗

arXiv2021

CARLS: Cross-platform Asynchronous Representation Learning System

In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms. The proposed CARLS is particularly suitable for learning paradigms where model training benefits from additional knowledge inferred or discovered during training, such as node embeddings for graph neural networks or reliable pseudo labels from model predictions. We also describe three learning paradigms -- semi-supervised learning, curriculum learning and multimodal learning -- as examples that can be scaled up efficiently by CARLS. One version of CARLS has been open-sourced and available for download at: https://github.com/tensorflow/neural-structured-learning/tree/master/research/carls

cs.LG↗