论文检索

Applications/Health

Andre Vauvelle, Benjamin Wild, Roland Eils, Spiros Denaxas

Survival analysis is a crucial semi-supervised task in machine learning with significant real-world applications, especially in healthcare. The most common approach to survival analysis, Cox’s partial likelihood, can be interpreted as a ranking model optimized on a lower bound of the concordance index. We follow these connections further, with listwise ranking losses that allow for a relaxation of the pairwise independence assumption. Given the inherent transitivity of ranking, we explore differentiable sorting networks as a means to introduce a stronger transitive inductive bias during optimization. Despite their potential, current differentiable sorting methods cannot account for censoring, a crucial aspect of many real-world datasets. We propose a novel method, Diffsurv, to overcome this limitation by extending differentiable sorting methods to handle censored tasks. Diffsurv predicts matrices of possible permutations that accommodate the label uncertainty introduced by censored samples. Our experiments reveal that Diffsurv outperforms established baselines in various simulated and real-world risk prediction scenarios. Furthermore, we demonstrate the algorithmic advantages of Diffsurv by presenting a novel method for top-k risk prediction that surpasses current methods.

Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, Dacheng Tao

Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of tasks. To better predict the control signals and enhance user safety, an end-to-end approach that benefits from joint spatial-temporal feature learning is desirable. While there are some pioneering works on LiDAR-based input or implicit design, in this paper we formulate the problem in an interpretable vision-based setting. In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3. Specifically, an egocentric-aligned accumulation technique is proposed to preserve geometry information in 3D space before the bird’s eye view transformation for perception; a dual pathway modeling is devised to take past motion variations into account for future prediction; a temporal-based refinement unit is introduced to compensate for recognizing vision-based elements for planning. To the best of our knowledge, we are the first to systematically investigate each part of an interpretable end-to-end vision-based autonomous driving system. We benchmark our approach against previous state-of-the-arts on both open-loop nuScenes dataset as well as closed-loop CARLA simulation. The results show the effectiveness of our method. Source code, model and protocol details are made publicly available at https://github.com/OpenPerceptionX/ST-P3.

Taotao Jing, Haifeng Xia, Renran Tian, Haoran Ding, Xiao Luo, Joshua Domeyer, Rini Sherony, Zhengming Ding

Autonomous driving has attracted interest for interpretable action decision models that mimic human cognition. Existing interpretable autonomous driving models explore static human explanations, which ignore the implicit visual semantics that are not explicitly annotated or even consistent across annotators. In this paper, we propose a novel Interpretable Action decision making (InAction) model to provide an enriched explanation from both explicit human annotation and implicit visual semantics. First, a proposed visual-semantic module captures the region-based action-inducing components from the visual inputs, which learns the implicit visual semantics to provide a human-understandable explanation in action decision making. Second, an explicit reasoning module is developed by incorporating global visual features and action-inducing visual semantics, which aims to jointly align the human-annotated explanation and action decision making. Experimental results on two autonomous driving benchmarks demonstrate the effectiveness of our InAction model for explaining both implicitly and explicitly by comparing it to existing interpretable autonomous driving models.

Mingyu Yang, Yu Chen, Hun-Seok Kim

In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods. Yet, all existing methods use both the visual and inertial measurements for every pose estimation incurring potential computational redundancy. While visual data processing is much more expensive than that for the inertial measurement unit (IMU), it may not always contribute to improving the pose estimation accuracy. In this paper, we propose an adaptive deep-learning based VIO method that reduces computational redundancy by opportunistically disabling the visual modality. Specifically, we train a policy network that learns to deactivate the visual feature extractor on the fly based on the current motion state and IMU readings. A Gumbel-Softmax trick is adopted to train the policy network to make the decision process differentiable for end-to-end system training. The learned strategy is interpretable, and it shows scenario-dependent decision patterns for adaptive complexity reduction. Experiment results show that our method achieves a similar or even better performance than the full-modality baseline with up to 78.8% computational complexity reduction for KITTI dataset evaluation. The code is available at https://github.com/mingyuyng/Visual-Selective-VIO.

Ruocheng Wang, Yunzhi Zhang, Jiayuan Mao, Chin-Yi Cheng, Jiajun Wu

We study the problem of translating an image-based, step-by-step assembly manual created by human designers into machine-interpretable instructions. We formulate this problem as a sequential prediction task: at each step, our model reads the manual, locates the components to be added to the current shape, and infers their 3D poses. This task poses the challenge of establishing a 2D-3D correspondence between the manual image and the real 3D object, and 3D pose estimation for unseen 3D objects, since a new component to be added in a step can be an object built from previous steps. To address these two challenges, we present a novel learning-based framework, the Manual-to-Executable-Plan Network (MEPNet), which reconstructs the assembly steps from a sequence of manual images. The key idea is to integrate neural 2D keypoint detection modules and 2D-3D projection algorithms for high-precision prediction and strong generalization to unseen components. The MEPNet outperforms existing methods on three newly collected LEGO manual datasets and a Minecraft house dataset.

Kengo Nakata, Youyang Ng, Daisuke Miyashita, Asuka Maki, Yu-Chieh Lin, Jun Deguchi

In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model parameters. Moreover, users cannot verify the validity of inference results or evaluate the contribution of knowledge to the results. In this paper, we investigate a system that stores knowledge for image classification, such as image feature maps, labels, and original images, not in model parameters but in external storage. Our system refers to the storage like a database when classifying input images. To increase knowledge, our system updates the database instead of fine-tuning model parameters, which avoids catastrophic forgetting in incremental learning scenarios. We revisit a kNN (k-nearest neighbor) classifier and employ it in our system. By analyzing the neighborhood samples referred by the kNN algorithm, we can interpret how knowledge learned in the past is used for inference results. Our system achieves 79.8% top-1 accuracy on the ImageNet dataset without fine-tuning model parameters after pretraining, and 90.8% accuracy on the Split CIFAR-100 dataset in the task incremental learning setting.

Karren Yang, Michael Firman, Eric Brachmann, Clément Godard

In this work, we show how to estimate a device’s position and orientation indoors by echolocation, i.e., by interpreting the echoes of an audio signal that the device itself emits. Established visual localization methods rely on the device’s camera and yield excellent accuracy if unique visual features are in view and depicted clearly. We argue that audio sensing can offer complementary information to vision for device localization, since audio is invariant to adverse visual conditions and can reveal scene information beyond a camera’s field of view. We first propose a strategy for learning an audio representation that captures the scene geometry around a device using supervision transfer from vision. Subsequently, we leverage this audio representation to complement vision in three device localization tasks: relative pose estimation, place recognition, and absolute pose regression. Our proposed methods outperform state-of-the-art vision models on new audio-visual benchmarks for the Replica and Matterport3D datasets.

Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Faisal Ahmed, Zicheng Liu, Yumao Lu, Lijuan Wang

We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text description and align predicted words with object regions. To achieve this, models must generate desired text and box outputs together, and meanwhile indicate the alignments between words and boxes. In contrast to existing solutions that use multiple separate modules for different outputs, UniTAB represents both text and box outputs with a shared token sequence, and introduces a special token to naturally indicate word-box alignments in the sequence. UniTAB thus could provide a more comprehensive and interpretable image description, by freely grounding generated words to object regions. On grounded captioning, UniTAB presents a simpler solution with a single output head, and significantly outperforms state of the art in both grounding and captioning evaluations. On general VL tasks that have different desired output formats (i.e., text, box, or their combination), UniTAB with a single network achieves better or comparable performance than task-specific state of the art. Experiments cover 7 VL benchmarks, including grounded captioning, visual grounding, image captioning, and visual question answering. Furthermore, UniTAB’s unified multi-task network and the task-agnostic output sequence design make the model parameter efficient and generalizable to new tasks.

Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D. Yoo

Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal interactions between query and video. This retrieval bias stems from learning frequent co-occurrence patterns between query and moments, which spuriously correlate objects (e.g., a pencil) referred in the query with moments (e.g., scene of writing with a pencil) where the objects frequently appear in the video, such that they converge into biased moment predictions. Although recent debiasing methods have focused on removing this retrieval bias, we argue that these biased predictions sometimes should be preserved because there are many queries where biased predictions are rather helpful. To conjugate this retrieval bias, we propose a Selective Query-guided Debiasing network (SQuiDNet), which incorporates the following two main properties: (1) Biased Moment Retrieval that intentionally uncovers the biased moments inherent in objects of the query and (2) Selective Query-guided Debiasing that performs selective debiasing guided by the meaning of the query. Our experimental results on three moment retrieval benchmarks (i.e., TVR, ActivityNet, DiDeMo) show the effectiveness of SQuiDNet and qualitative analysis shows improved interpretability.

Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Stephanie Hyland, Maria Wetscherek, Tristan Naumann, Aditya Nori, Javier Alvarez-Valle 等

Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision-language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision-language processing. We release a language model that achieves state-of-the-art results in radiology natural-language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiology reports. Further, we propose a self-supervised joint vision-language approach with a focus on better text modelling. It establishes new state of the art results on a wide range of publicly available benchmarks, in part by leveraging our new domain-specific language model. We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision-language processing. A broad evaluation, including on this new dataset, shows that our contrastive learning approach, aided by textual-semantic modelling, outperforms prior methods in segmentation tasks, despite only using a global-alignment objective.

Liliane Momeni, Hannah Bull, K R Prajwal, Samuel Albanie, Gül Varol, Andrew Zisserman

Recently, sign language researchers have turned to sign language interpreted TV broadcasts, comprising (i) a video of continuous signing and (ii) subtitles corresponding to the audio content, as a readily available and large-scale source of training data. One key challenge in the usability of such data is the lack of sign annotations. Previous work exploiting such weakly-aligned data only found sparse correspondences between keywords in the subtitle and individual signs. In this work, we propose a simple, scalable framework to vastly increase the density of automatic annotations. Our contributions are the following: (1) we significantly improve previous annotation methods by making use of synonyms and subtitle-signing alignment; (2) we show the value of pseudo-labelling from a sign recognition model as a way of sign spotting; (3) we propose a novel approach for increasing our annotations of known and unknown classes based on in domain exemplars; (4) on the BOBSL BSL sign language corpus, we increase the number of confident automatic annotations from 670K to 5M. We make these annotations publicly available to support the sign language research community.

Jiafei Duan, Samson Yu, Soujanya Poria, Bihan Wen, Cheston Tan

Accurate prediction of physical interaction outcomes is a crucial component of human intelligence and is important for safe and efficient deployments of robots in the real world. While there are existing vision-based intuitive physics models that learn to predict physical interaction outcomes, they mostly focus on generating short sequences of future frames based on physical properties (e.g. mass, friction and velocity) extracted from visual inputs or a latent space. However, there is a lack of intuitive physics models that are tested on long physical interaction sequences with multiple interactions among different objects. We hypothesize that selective temporal attention during approximate mental simulations helps humans in physical interaction outcome prediction. With these motivations, we propose a novel scheme: \textbf{P}hysical \textbf{I}nteraction \textbf{P}rediction via Mental Simulation with Span Selection (PIP). It utilizes a deep generative model to model approximate mental simulations by generating future frames of physical interactions before employing selective temporal attention in the form of span selection for predicting physical interaction outcomes. To the best of our knowledge, attention has not been used with deep learning to tackle intuitive physics. For model evaluation, we further propose the large-scale SPACE+ dataset of synthetic videos with long sequences of three prime physical interactions in a 3D environment. Our experiments show that PIP outperforms human, baseline, and related intuitive physics models that utilize mental simulation. Furthermore, PIP’s span selection module effectively identifies the frames indicating key physical interactions among objects, allowing for added interpretability, and does not require labor-intensive frame annotations. PIP is available on https://sites.google.com/view/piphysics.

Honglu Zhou, Asim Kadav, Aviv Shamsian, Shijie Geng, Farley Lai, Long Zhao, Ting Liu, Mubbasir Kapadia, Hans Peter Graf

Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects. We approach the task by modeling the video as tokens that represent the multi-scale semantic concepts in the video. We propose COMPOSER, a Multiscale Transformer based architecture that performs attention-based reasoning over tokens at each scale and learns group activity compositionally. In addition, prior works suffer from scene biases with privacy and ethical concerns. We only use the keypoint modality which reduces scene biases and prevents acquiring detailed visual data that may contain private or biased information of users. We improve the multiscale representations in COMPOSER by clustering the intermediate scale representations, while maintaining consistent cluster assignments between scales. Finally, we use techniques such as auxiliary prediction and data augmentations tailored to the keypoint signals to aid model training. We demonstrate the model’s strength and interpretability on two widely-used datasets (Volleyball and Collective Activity). COMPOSER achieves up to +5.4% improvement with just the keypoint modality.

Jiabo Huang, Hailin Jin, Shaogang Gong, Yang Liu

Current methods for video activity localisation over time assume implicitly that activity temporal boundaries labelled for model training are determined and precise. However, in unscripted natural videos, different activities mostly transit smoothly, so that it is intrinsically ambiguous to determine in labelling precisely when an activity starts and ends over time. Such uncertainties in temporal labelling are currently ignored in model training, resulting in learning mis-matched video-text correlation with poor generalisation in test. In this work, we solve this problem by introducing Elastic Moment Bounding (EMB) to accommodate flexible and adaptive activity temporal boundaries towards modelling universally interpretable video-text correlation with tolerance to underlying temporal uncertainties in pre-fixed annotations. Specifically, we construct elastic boundaries adaptively by mining and discovering frame-wise temporal endpoints that can maximise the alignment between video segments and query sentences. To enable both more accurate matching (segment content attention) and more robust localisation (segment elastic boundaries), we optimise the selection of frame-wise endpoints subject to segment-wise contents by a novel Guided Attention mechanism. Extensive experiments on three video activity localisation benchmarks demonstrate compellingly the EMB’s advantages over existing methods without modelling uncertainty.

Yawen Huang, Feng Zheng, Xu Sun, Yuexiang Li, Ling Shao, Yefeng Zheng

High inter-equipment variability and expensive examination costs of brain imaging remain key challenges in leveraging the heterogeneous scans effectively. Despite rapid growth in image-to-image translation with deep learning models, the target brain data may not always be achievable due to the specific attributes of brain imaging. In this paper, we present a novel generalized brain image synthesis method, powered by our transferable convolutional sparse coding networks, to address the lack of interpretable cross-modal medical image representation learning. The proposed approach masters the ability to imitate the machine-like anatomically meaningful imaging by translating features directly under a series of mathematical processings, leading to the reduced domain discrepancy while enhancing model transferability. Specifically, we first embed the globally normalized features into a domain discrepancy metric to learn the domain-invariant representations, then optimally preserve domain-specific geometrical property to reflect the intrinsic graph structures, and further penalize their subspace mismatching to reduce the generalization error. The overall framework is cast in a minimax setting, and the extensive experiments show that the proposed method yields state-of-the-art results on multiple datasets.

Xingyi Yang, Jingwen Ye, Xinchao Wang

In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization (KF). The core idea of KF lies in the modularization and assemblability of knowledge: given a pretrained network model as input, KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-specific knowledge factorized from the source network. Such factor networks are task-wise disentangled and can be directly assembled, without any fine-tuning, to produce the more competent combined-task networks. In other words, the factor networks serve as Lego-brick-like building blocks, allowing us to construct customized networks in a plug-and-play manner. Specifically, each factor network comprises two modules, a common-knowledge module that is task-agnostic and shared by all factor networks, alongside with a task-specific module dedicated to the factor network itself. We introduce an information-theoretic objective, InfoMax-Bottleneck (IMB), to carry out KF by optimizing the mutual information between the learned representations and input. Experiments across various benchmarks demonstrate that, the derived factor networks yield gratifying performances on not only the dedicated tasks but also disentanglement, while enjoying much better interpretability and modularity. Moreover, the learned common-knowledge representations give rise to impressive results on transfer learning. Our code is available at https://github.com/Adamdad/KnowledgeFactor.

Xinhao Li, Jingjing Li, Zhekai Du, Lei Zhu, Wen Li

Open-set Domain Adaptation (OSDA) aims to recognize classes in the target domain that are seen in the source domain while rejecting other unseen target-exclusive classes into an unknown class, which ignores the diversity of the latter and is therefore incapable of their interpretation. The recently-proposed Semantic Recovery OSDA (SR-OSDA) brings in semantic attributes and attacks the challenge via partial alignment and visual-semantic projection, marking the first step towards interpretable OSDA. Following that line, in this work, we propose a representation learning framework termed Angular Margin Separation (AMS) that unveils the power of discriminative and robust representation for both open-set domain adaptation and cross-domain semantic recovery. Our core idea is to exploit an additive angular margin with regularization for both robust feature fine-tuning and discriminative joint feature alignment, which turns out advantageous to learning an accurate and less biased visual-semantic projection. Further, we propose a post-training re-projection that boosts the performance of seen classes interpretation without deterioration on unseen classes. Verified by extensive experiments, AMS achieves a notable improvement over the existing SR-OSDA baseline, with an average 7.6% increment in semantic recovery accuracy of unseen classes in multiple transfer tasks. Our code is available at https://github.com/LeoXinhaoLee/AMS.

Xuran Pan, Zihang Lai, Shiji Song, Gao Huang

Recently, Neural Radiance Fields (NeRF) has shown promising performances on reconstructing 3D scenes and synthesizing novel views from a sparse set of 2D images. Albeit effective, the performance of NeRF is highly influenced by the quality of training samples. With limited posed images from the scene, NeRF fails to generalize well to novel views and may collapse to trivial solutions in unobserved regions. This makes NeRF impractical under resource-constrained scenarios. In this paper, we present a novel learning framework, \textit{ActiveNeRF}, aiming to model a 3D scene with a constrained input budget. Specifically, we first incorporate uncertainty estimation into a NeRF model, which ensures robustness under few observations and provides an interpretation of how NeRF understands the scene. On this basis, we propose to supplement the existing training set with newly captured samples based on an active learning scheme. By evaluating the reduction of uncertainty given new inputs, we select the samples that bring the most information gain. In this way, the quality of novel view synthesis can be improved with minimal additional resources. Extensive experiments validate the performance of our model on both realistic and synthetic scenes, especially with scarcer training data.

Leonid Keselman, Martial Hebert

Differentiable renderers provide a direct mathematical link between an object’s 3D representation and images of that object. In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs. Our approximate renderer focuses on rendering shapes via depth maps and silhouettes. It sacrifices fidelity for utility, producing fast runtimes and high-quality gradient information that can be used to solve vision tasks. Compared to mesh-based differentiable renderers, our method has forward passes that are 5x faster and backwards passes that are 30x faster. The depth maps and silhouette images generated by our method are smooth and defined everywhere. In our evaluation of differentiable renderers for pose estimation, we show that our method is the only one comparable to classic techniques. In shape from silhouette, our method performs well using only gradient descent and a per-pixel loss, without any surrogate losses or regularization. These reconstructions work well even on natural video sequences with segmentation artifacts.

Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due to its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increased attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most popular state-of-the-art methods are unable to consistently outperform a simple anomaly detector based on pre-trained features and the Mahalanobis distance (MahaAD). A key reason for the inconsistencies of these methods is the lack of a formal description of U-OOD. Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset. We show how this characterization is unknowingly embodied in the top-scoring MahaAD method, thereby explaining its quality. Furthermore, our approach can be used to interpret predictions of U-OOD detectors and provides insights into good practices for evaluating future U-OOD methods.