Tsun-Hsuan Wang, Hou-Ning Hu, Chieh Hubert Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths across LiDAR and stereo modalities, we take advantages of the stereo matching network with two enhanced techniques: Input Fusion and Conditional Cost Volume Normalization (CCVNorm) on the LiDAR information. The proposed framework is generic and closely integrated with the cost volume component that is commonly utilized in stereo matching neural networks. We experimentally verify the efficacy and robustness of our method on the KITTI Stereo and Depth Completion datasets, obtaining favorable performance against various fusion strategies. Moreover, we demonstrate that, with a hierarchical extension of CCVNorm, the proposed method brings only slight overhead to the stereo matching network in terms of computation time and model size. For project page, see https://zswang666.github.io/Stereo-LiDAR-CCVNorm-Project-Page/
Cheng-Sheng Chan, Shou-Zhong Chen, Pei-Xuan Xie, Chiung-Chih Chang, Min Sun
We revisit the study of a wrist-mounted camera system (referred to as HandCam) for recognizing activities of hands. HandCam has two unique properties as compared to egocentric systems (referred to as HeadCam): (1) it avoids the need to detect hands; (2) it more consistently observes the activities of hands. By taking advantage of these properties, we propose a deep-learning-based method to recognize hand states (free v.s. active hands, hand gestures, object categories), and discover object categories. Moreover, we propose a novel two-streams deep network to further take advantage of both HandCam and HeadCam. We have collected a new synchronized HandCam and HeadCam dataset with 20 videos captured in three scenes for hand states recognition. Experiments show that our HandCam system consistently outperforms a deep-learning-based HeadCam method (with estimated manipulation regions) and a dense-trajectory-based HeadCam method in all tasks. We also show that HandCam videos captured by different users can be easily aligned to improve free v.s. active recognition accuracy (3.3% improvement) in across-scenes use case. Moreover, we observe that finetuning Convolutional Neural Network consistently improves accuracy. Finally, our novel two-streams deep network combining HandCam and HeadCam features achieves the best performance in four out of five tasks. With more data, we believe a joint HandCam and HeadCam system can robustly log hand states in daily life.
An-Chieh Cheng, Chieh Hubert Lin, Da-Cheng Juan, Wei Wei, Min Sun
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we propose InstaNAS---an instance-aware NAS framework---that employs a controller trained to search for a "distribution of architectures" instead of a single architecture; This allows the model to use sophisticated architectures for the difficult samples, which usually comes with large architecture related cost, and shallow architectures for those easy samples. During the inference phase, the controller assigns each of the unseen input samples with a domain expert architecture that can achieve high accuracy with customized inference costs. Experiments within a search space inspired by MobileNetV2 show InstaNAS can achieve up to 48.8% latency reduction without compromising accuracy on a series of datasets against MobileNetV2.
Tsun-Hsuan Wang, Yen-Chi Cheng, Chieh Hubert Lin, Hwann-Tzong Chen, Min Sun
While image manipulation achieves tremendous breakthroughs (e.g., generating realistic faces) in recent years, video generation is much less explored and harder to control, which limits its applications in the real world. For instance, video editing requires temporal coherence across multiple clips and thus poses both start and end constraints within a video sequence. We introduce point-to-point video generation that controls the generation process with two control points: the targeted start- and end-frames. The task is challenging since the model not only generates a smooth transition of frames, but also plans ahead to ensure that the generated end-frame conforms to the targeted end-frame for videos of various length. We propose to maximize the modified variational lower bound of conditional data likelihood under a skip-frame training strategy. Our model can generate sequences such that their end-frame is consistent with the targeted end-frame without loss of quality and diversity. Extensive experiments are conducted on Stochastic Moving MNIST, Weizmann Human Action, and Human3.6M to evaluate the effectiveness of the proposed method. We demonstrate our method under a series of scenarios (e.g., dynamic length generation) and the qualitative results showcase the potential and merits of point-to-point generation. For project page, see https://zswang666.github.io/P2PVG-Project-Page/
Chi-Wei Hsiao, Cheng Sun, Min Sun, Hwann-Tzong Chen
This paper proposes a new approach, Flat2Layout, for estimating general indoor room layout from a single-view RGB image whereas existing methods can only produce layout topologies captured from the box-shaped room. The proposed flat representation encodes the layout information into row vectors which are treated as the training target of the deep model. A dynamic programming based postprocessing is employed to decode the estimated flat output from the deep model into the final room layout. Flat2Layout achieves state-of-the-art performance on existing room layout benchmark. This paper also constructs a benchmark for validating the performance on general layout topologies, where Flat2Layout achieves good performance on general room types. Flat2Layout is applicable on more scenario for layout estimation and would have an impact on applications of Scene Modeling, Robotics, and Augmented Reality.
Tsun-Hsuan Wang, Hung-Jui Huang, Juan-Ting Lin, Chan-Wei Hu, Kuo-Hao Zeng, Min Sun
$ $Visual place recognition is challenging, especially when only a few place exemplars are given. To mitigate the challenge, we consider place recognition method using omnidirectional cameras and propose a novel Omnidirectional Convolutional Neural Network (O-CNN) to handle severe camera pose variation. Given a visual input, the task of the O-CNN is not to retrieve the matched place exemplar, but to retrieve the closest place exemplar and estimate the relative distance between the input and the closest place. With the ability to estimate relative distance, a heuristic policy is proposed to navigate a robot to the retrieved closest place. Note that the network is designed to take advantage of the omnidirectional view by incorporating circular padding and rotation invariance. To train a powerful O-CNN, we build a virtual world for training on a large scale. We also propose a continuous lifted structured feature embedding loss to learn the concept of distance efficiently. Finally, our experimental results confirm that our method achieves state-of-the-art accuracy and speed with both the virtual world and real-world datasets.
Tsun-Hsuan Wang, Fu-En Wang, Juan-Ting Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice. For project page, see https://zswang666.github.io/PnP-Depth-Project-Page/
Min Sun, Federica Storti, Valentina Martino, Miguel Gonzalez-Andrades, Tony Kam-Thong
Many combinatorial optimisation problems hide algebraic structures that, once exposed, shrink the search space and improve the chance of finding the global optimal solution. We present a general framework that (i) identifies algebraic structure, (ii) formalises operations, (iii) constructs quotient spaces that collapse redundant representations, and (iv) optimises directly over these reduced spaces. Across a broad family of rule-combination tasks (e.g., patient subgroup discovery and rule-based molecular screening), conjunctive rules form a monoid. Via a characteristic-vector encoding, we prove an isomorphism to the Boolean hypercube $\{0,1\}^n$ with bitwise OR, so logical AND in rules becomes bitwise OR in the encoding. This yields a principled quotient-space formulation that groups functionally equivalent rules and guides structure-aware search. On real clinical data and synthetic benchmarks, quotient-space-aware genetic algorithms recover the global optimum in 48% to 77% of runs versus 35% to 37% for standard approaches, while maintaining diversity across equivalence classes. These results show that exposing and exploiting algebraic structure offers a simple, general route to more efficient combinatorial optimisation.
Kasra Moazzami, Seoyoun Son, John Lin, Sun Min Lee, Daniel Son, Hayeon Lee, Jeongho Lee, Seongji Lee
Endoscopic image classification plays a pivotal role in medical diagnostics by identifying anatomical landmarks and pathological findings. However, conventional closed-set classification frameworks are inherently limited in open-world clinical settings, where previously unseen conditions can arise andcompromise model reliability. To address this, we explore the application of Open Set Recognition (OSR) techniques on the Kvasir dataset, a publicly available and diverse endoscopic image collection. In this study, we evaluate and compare the OSR capabilities of several representative deep learning architectures, including ResNet-50, Swin Transformer, and a hybrid ResNet-Transformer model, under both closed-set and open-set conditions. OpenMax is adopted as a baseline OSR method to assess the ability of these models to distinguish known classes from previously unseen categories. This work represents one of the first efforts to apply open set recognition to the Kvasir dataset and provides a foundational benchmark for evaluating OSR performance in medical image analysis. Our results offer practical insights into model behavior in clinically realistic settings and highlight the importance of OSR techniques for the safe deployment of AI systems in endoscopy.
Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath, Xiao Xiao Sun, James Burgess, Yuhui Zhang, Kun Yuan, Robert Tibshirani, Sean Huver, Serena Yeung-Levy
Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale open source literature reveals that a huge portion of captions far exceed 77 tokens. To this end, we investigate the impact of pretraining on long-format biomedical captions by extending the context length of text encoders in VLMs. We find that longer context (thus, enabling additional supervision provided in long-format captions) correlates with better retrieval and classification performance. Given this finding, we introduce BIOMEDICA-LongCAP, a dataset of 1M image-caption pairs enriched with context-aware descriptions from full-text articles, providing longer and additional textual supervision. Using BIOMEDICA-LongCAP, we train BMC-LongCLIP, a long-context biomedical VLM with a text encoder supporting windows of up to 512 tokens. Our model extends context capacity by 6.6x, reducing token waste from 55% to just 2.2%. On long-caption retrieval benchmarks, BMC-LongCLIP achieves up to +30% absolute gains in Recall@1 and +2% average improvements in classification, while also converging faster than short-context. Our results demonstrate that long-context modeling is a promising direction for advancing biomedical VLMs.
Min Woo Sun, Robert Tibshirani
Cross-validation (CV) is one of the most widely used techniques in statistical learning for estimating the test error of a model, but its behavior is not yet fully understood. It has been shown that standard confidence intervals for test error using estimates from CV may have coverage below nominal levels. This phenomenon occurs because each sample is used in both the training and testing procedures during CV and as a result, the CV estimates of the errors become correlated. Without accounting for this correlation, the estimate of the variance is smaller than it should be. One way to mitigate this issue is by estimating the mean squared error of the prediction error instead using nested CV. This approach has been shown to achieve superior coverage compared to intervals derived from standard CV. In this work, we generalize the nested CV idea to the Cox proportional hazards model and explore various choices of test error for this setting.
Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu, Ting-Fan Wu, Min Sun
Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model $N$ times which results in $N$ times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone ($N=5$). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout's uncertainty estimation on pixel-level and frame-level metrics.
Wen-Yen Chang, Wen-Huan Chiang, Shao-Hao Lu, Tingfan Wu, Min Sun
The data efficiency of learning-based algorithms is more and more important since high-quality and clean data is expensive as well as hard to collect. In order to achieve high model performance with the least number of samples, active learning is a technique that queries the most important subset of data from the original dataset. In active learning domain, one of the mainstream research is the heuristic uncertainty-based method which is useful for the learning-based system. Recently, a few works propose to apply policy reinforcement learning (PRL) for querying important data. It seems more general than heuristic uncertainty-based method owing that PRL method depends on data feature which is reliable than human prior. However, there have two problems - sample inefficiency of policy learning and overconfidence, when applying PRL on active learning. To be more precise, sample inefficiency of policy learning occurs when sampling within a large action space, in the meanwhile, class imbalance can lead to the overconfidence. In this paper, we propose a bias-aware policy network called Heapified Active Learning (HAL), which prevents overconfidence, and improves sample efficiency of policy learning by heapified structure without ignoring global inforamtion(overview of the whole unlabeled set). In our experiment, HAL outperforms other baseline methods on MNIST dataset and duplicated MNIST. Last but not least, we investigate the generalization of the HAL policy learned on MNIST dataset by directly applying it on MNIST-M. We show that the agent can generalize and outperform directly-learned policy under constrained labeled sets.
Shih-Han Chou, Cheng Sun, Wen-Yen Chang, Wan-Ting Hsu, Min Sun, Jianlong Fu
While there are several widely used object detection datasets, current computer vision algorithms are still limited in conventional images. Such images narrow our vision in a restricted region. On the other hand, 360° images provide a thorough sight. In this paper, our goal is to provide a standard dataset to facilitate the vision and machine learning communities in 360° domain. To facilitate the research, we present a real-world 360° panoramic object detection dataset, 360-Indoor, which is a new benchmark for visual object detection and class recognition in 360° indoor images. It is achieved by gathering images of complex indoor scenes containing common objects and the intensive annotated bounding field-of-view. In addition, 360-Indoor has several distinct properties: (1) the largest category number (37 labels in total). (2) the most complete annotations on average (27 bounding boxes per image). The selected 37 objects are all common in indoor scene. With around 3k images and 90k labels in total, 360-Indoor achieves the largest dataset for detection in 360° images. In the end, extensive experiments on the state-of-the-art methods for both classification and detection are provided. We will release this dataset in the near future.
Yen-Chi Cheng, Hsin-Ying Lee, Min Sun, Ming-Hsuan Yang
Flexible user controls are desirable for content creation and image editing. A semantic map is commonly used intermediate representation for conditional image generation. Compared to the operation on raw RGB pixels, the semantic map enables simpler user modification. In this work, we specifically target at generating semantic maps given a label-set consisting of desired categories. The proposed framework, SegVAE, synthesizes semantic maps in an iterative manner using conditional variational autoencoder. Quantitative and qualitative experiments demonstrate that the proposed model can generate realistic and diverse semantic maps. We also apply an off-the-shelf image-to-image translation model to generate realistic RGB images to better understand the quality of the synthesized semantic maps. Furthermore, we showcase several real-world image-editing applications including object removal, object insertion, and object replacement.
Wei-Cheng Tseng, Po-Han Chi, Jia-Hua Wu, Min Sun
The capability of accurate prediction of protein functions and properties is essential in the biotechnology industry, e.g. drug development and artificial protein synthesis, etc. The main challenges of protein function prediction are the large label space and the lack of labeled training data. Our method leverages unsupervised sequence embedding and the success of deep convolutional neural network to overcome these challenges. In contrast, most of the existing methods delete the rare protein functions to reduce the label space. Furthermore, some existing methods require additional bio-information (e.g., the 3-dimensional structure of the proteins) which is difficult to be determined in biochemical experiments. Our proposed method significantly outperforms the other methods on the publicly available benchmark using only protein sequences as input. This allows the process of identifying protein functions to be sped up.
Wei-Cheng Tseng, Wei Wei, Da-Cheng Juan, Min Sun
Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios. To this end, a multi-agent framework needs to handle various scenarios of agents, in terms of both scales and dynamics, for being practical to real-world applications. We formulate the multi-agent environment with a different number of agents as a multi-tasking problem and propose a meta reinforcement learning (meta-RL) framework to tackle this problem. The proposed framework employs a meta-learned Communication Pattern Recognition (CPR) module to identify communication behavior and extract information that facilitates the training process. Experimental results are poised to demonstrate that the proposed framework (a) generalizes to an unseen larger number of agents and (b) allows the number of agents to change between episodes. The ablation study is also provided to reason the proposed CPR design and show such design is effective.
An-Chieh Cheng, Xueting Li, Sifei Liu, Min Sun, Ming-Hsuan Yang
With the capacity of modeling long-range dependencies in sequential data, transformers have shown remarkable performances in a variety of generative tasks such as image, audio, and text generation. Yet, taming them in generating less structured and voluminous data formats such as high-resolution point clouds have seldom been explored due to ambiguous sequentialization processes and infeasible computation burden. In this paper, we aim to further exploit the power of transformers and employ them for the task of 3D point cloud generation. The key idea is to decompose point clouds of one category into semantically aligned sequences of shape compositions, via a learned canonical space. These shape compositions can then be quantized and used to learn a context-rich composition codebook for point cloud generation. Experimental results on point cloud reconstruction and unconditional generation show that our model performs favorably against state-of-the-art approaches. Furthermore, our model can be easily extended to multi-modal shape completion as an application for conditional shape generation.
YuanFu Yang, Min Sun
With the rapid development of artificial intelligence and autonomous driving technology, the demand for semiconductors is projected to rise substantially. However, the massive expansion of semiconductor manufacturing and the development of new technology will bring many defect wafers. If these defect wafers have not been correctly inspected, the ineffective semiconductor processing on these defect wafers will cause additional impact to our environment, such as excessive carbon dioxide emission and energy consumption. In this paper, we utilize the information processing advantages of quantum computing to promote the defect learning defect review (DLDR). We propose a classical-quantum hybrid algorithm for deep learning on near-term quantum processors. By tuning parameters implemented on it, quantum circuit driven by our framework learns a given DLDR task, include of wafer defect map classification, defect pattern classification, and hotspot detection. In addition, we explore parametrized quantum circuits with different expressibility and entangling capacities. These results can be used to build a future roadmap to develop circuit-based quantum deep learning for semiconductor defect detection.
Ming-Feng Li, Min Sun
In modern fulfillment warehouses, agents traverse the map to complete endless tasks that arrive on the fly, which is formulated as a lifelong Multi-Agent Path Finding (lifelong MAPF) problem. The goal of tackling this challenging problem is to find the path for each agent in a finite runtime while maximizing the throughput. However, existing methods encounter exponential growth of runtime and undesirable phenomena of deadlocks and rerouting as the map size or agent density grows. To address these challenges in lifelong MAPF, we explore the idea of highways mainly studied for one-shot MAPF (i.e., finding paths at once beforehand), which reduces the complexity of the problem by encouraging agents to move in the same direction. We utilize two methods to incorporate the highway idea into the lifelong MAPF framework and discuss the properties that minimize the existing problems of deadlocks and rerouting. The experimental results demonstrate that the runtime is considerably reduced and the decay of throughput is gradually insignificant as the map size enlarges under the settings of the highway. Furthermore, when the density of agents increases, the phenomena of deadlocks and rerouting are significantly reduced by leveraging the highway.