Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution data through joint representation learning and statistical modeling. We learn a mixture of Gaussian models for each in-distribution category. There are many Gaussian mixture models to model different visual categories. With these Gaussian models, we design an in-distribution score function by aggregating multiple Mahalanobis-based metrics. We don't use any auxiliary outlier data as training samples, which may hurt the generalization ability of out-of-distribution detection algorithms. We split the ImageNet-1k dataset into ten folds randomly. We use one fold as the in-distribution dataset and the others as out-of-distribution datasets to evaluate the proposed method. We also conduct experiments on seven popular benchmarks, including CIFAR, iNaturalist, SUN, Places, Textures, ImageNet-O, and OpenImage-O. Extensive experiments indicate that the proposed method outperforms state-of-the-art algorithms clearly. Meanwhile, we find that our visual representation has a competitive performance when compared with features learned by classical methods. These results demonstrate that the proposed method hasn't weakened the discriminative ability of visual recognition models and keeps high efficiency in detecting out-of-distribution samples.
Sun Yat-sen University（中山大学）；South China Agricultural University（华南农业大学）；University of Electronic Science and Technology of China（电子科技大学）；Guilin University of Electronic Technology（桂林电子科技大学）
Object categories inherently form a hierarchy with different levels of concept abstraction, especially for fine-grained categories. For example, birds (Aves) can be categorized according to a four-level hierarchy of order, family, genus, and species. This hierarchy encodes rich correlations among various categories across different levels, which can effectively regularize the semantic space and thus make prediction less ambiguous. However, previous studies of fine-grained image recognition primarily focus on categories of one certain level and usually overlook this correlation information. In …
University of Liverpool（利物浦大学）；Xi'an Jiaotong-Liverpool University（西交利物浦大学）
Recently, the soft attention mechanism, which was originally proposed in language processing, has been applied in computer vision tasks like image captioning. This paper presents improvements to the soft attention model by combining a convolutional LSTM with a hierarchical system architecture to recognize action categories in videos. We call this model the Convolutional Hierarchical Attention Model (CHAM). The model applies a convolutional operation inside the LSTM cell and an attention map generation process to recognize actions. The hierarchical architecture of this model is able to explicit…
Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarc…
Fudan University（复旦大学）；Tongji University（同济大学）；Huaiyin Normal University（淮阴师范学院）；Tencent AI Lab（腾讯人工智能实验室）
Few-shot object detection (FSOD) is to detect objects with a few examples. However, existing FSOD methods do not consider hierarchical fine-grained category structures of objects that exist widely in real life. For example, animals are taxonomically classified into orders, families, genera and species etc. In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm. To this end, on the one hand, we build the first large-scale and high-quality Hi-FSOD benchmark dataset H…
Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information
University of Colorado Boulder（科罗拉多大学博尔德分校）；Pennsylvania State University（宾夕法尼亚州立大学）；University of Washington（华盛顿大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Over the past decade, deep neural networks have proven to be adept in image classification tasks, often surpassing humans in terms of accuracy. However, standard neural networks often fail to understand the concept of hierarchical structures and dependencies among different classes for vision related tasks. Humans on the other hand, seem to intuitively learn categories conceptually, progressively growing from understanding high-level concepts down to granular levels of categories. One of the issues arising from the inability of neural networks to encode such dependencies within its learned str…
Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning
Information Materials and Intelligent Sensing Laboratory of Anhui Province（安徽省信息材料与智能感知实验室）；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）
Most deep architectures for image classification--even those that are trained to classify a large number of diverse categories--learn shared image representations with a single model. Intuitively, however, categories that are more similar should share more information than those that are very different. While hierarchical deep networks address this problem by learning separate features for subsets of related categories, current implementations require simplified models using fixed architectures specified via heuristic clustering methods. Instead, we propose Blockout, a method for regularizatio…
Harbin Institute of Technology（哈尔滨工业大学）；JD AI Research（京东AI研究院）
Merchandise categories inherently form a semantic hierarchy with different levels of concept abstraction, especially for fine-grained categories. This hierarchy encodes rich correlations among various categories across different levels, which can effectively regularize the semantic space and thus make predictions less ambiguous. However, previous studies of fine-grained image retrieval primarily focus on semantic similarities or visual similarities. In a real application, merely using visual similarity may not satisfy the need of consumers to search merchandise with real-life images, e.g., giv…
Xiamen University（厦门大学）；University of Electric Science and technology of China（电子科技大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Technology Sydney（悉尼科技大学）
We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching …
Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images. In addition, meta-learning does not distinguish the categories well because it determines whether the support and query images match. In other words, metric-based learning for classification is ineffective because it does not work directly. Thus,…
University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）；Tsinghua University（清华大学）
Video summarization aims to automatically generate a summary (storyboard or video skim) of a video, which can facilitate large-scale video retrieval and browsing. Most of the existing methods perform video summarization on individual videos, which neglects the correlations among similar videos. Such correlations, however, are also informative for video understanding and video summarization. To address this limitation, we propose Video Joint Modelling based on Hierarchical Transformer (VJMHT) for co-summarization, which takes into consideration the semantic dependencies across videos. Specifica…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Beijing Institute of Basic Medical Sciences（北京基础医学研究所）；Nanchang Hangkong University（南昌航空大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the visual space of the detector with the semantic space of the Pre-trained Visual-Language Model (PVLM). However, in the more efficient one-stage detector, the absence of class-agnostic object proposals hinders the knowledge distillation on unseen objects, leading to severe performance degradation. In this paper, we propose a hierarchical visual-language knowledge distillation me…
DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；School of Engineering, Westlake University（西湖大学工程学院）；School of Electronic Engineering, Beijing University of Posts and Telecommunications（北京邮电大学电子工程学院）；School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications（北京邮电大学现代邮政学院（自动化学院））
HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction
The HongKong University of Science and Technology（香港科技大学）；The HongKong University of Science and Technology (Guangzhou)（香港科技大学（广州））；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深港协同创新研究院）
FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training
Shanghai Jiao Tong University（上海交通大学）；KlingAI；The Hong Kong University of Science and Technology（香港科技大学）；South China University of Technology（华南理工大学）；The University of Hong Kong（香港大学）
University of Toulouse（图卢兹大学）；IRIT/INP-ENSEEIHT（图卢兹国立综合理工学院国立高等电子技术、电子学、计算机、水力学院/图卢兹信息学研究所）；IRIT, CNRS UMR 5505（法国国家科学研究中心联合研究单位5505 图卢兹信息学研究所）
This paper proposes a joint segmentation and deconvolution Bayesian method for medical ultrasound (US) images. Contrary to piecewise homogeneous images, US images exhibit heavy characteristic speckle patterns correlated with the tissue structures. The generalized Gaussian distribution (GGD) has been shown to be one of the most relevant distributions for characterizing the speckle in US images. Thus, we propose a GGD-Potts model defined by a label map coupling US image segmentation and deconvolution. The Bayesian estimators of the unknown model parameters, including the US image, the label map …
Food recognition is one of the most important components in image-based dietary assessment. However, due to the different complexity level of food images and inter-class similarity of food categories, it is challenging for an image-based food recognition system to achieve high accuracy for a variety of publicly available datasets. In this work, we propose a new two-step food recognition system that includes food localization and hierarchical food classification using Convolutional Neural Networks (CNNs) as the backbone architecture. The food localization step is based on an implementation of t…
Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or signs, not both, which makes them unsuitable for real-life deployment due to the limited graphics processing unit (GPU) memory and power available on embedded systems. The root cause of this issue is that no public dataset contains both traffic light and sign labels, which leads to difficulties in developing a joint detection framework. We present a deep hierarchical architecture in conjunction with a mini-batch proposal…
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Electronic Information, Wuhan University（武汉大学电子信息学院）
School of Computer Science（计算机学院）；Northwestern Polytechnical University（西北工业大学）；Chinese Academy of Sciences（中国科学院）
Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities. However, previous methods mainly focus on fusing the shallow features or high-level representations generated by unimodal deep networks, which only capture part of the hierarchical correlations across modalities. In this paper, we propose to densely integrate the representations by greedily stacking multiple shared layers between different modality-specific …
Hierarchical Approach for Joint Semantic, Plant Instance, and Leaf Instance Segmentation in the Agricultural Domain
University of Bonn（波恩大学）；University of Oxford（牛津大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）；La Sapienza University of Rome（罗马第一大学）
Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combined with an entropy model, a prior on the latent representation that can be used with standard arithmetic coding algorithms to yield a compressed bitstream. Recently, hierarchical entropy models have been introduced as a way to exploit more structure in the latents than simple fully factorized priors, improving compression performance while maintaining end-to-end optimization. Inspired by the success of autoregressive…
Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation
Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学）；Hunan University（湖南大学）；University of Trento（特伦托大学）；Zhejiang University（浙江大学）；Fudan University（复旦大学）；Australian National University（澳大利亚国立大学）；Linköping University（利乌波尔特大学）
Zhejiang University（浙江大学）；University of Technology Sydney（悉尼科技大学）；Université de Montréal（蒙特利尔大学）
Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this paper, we study how to address three critical challenges for this task: judging the global correctness of the statement involved multiple semantic meanings, joint reasoning over video and subtitles, and modeling long-range relationships and complex social interactions. First, we propose an adaptive hierarchical graph network that achieves in-depth understan…
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie in two aspects: the intra-frame representation for joint co-occurrences and the inter-frame representation for skeletons' temporal evolutions. In this paper we propose an end-to-end convolutional co-occurrence feature learning framework. The co-occurrence features are learned with a hierarchical methodology, in which different levels of contextual information are aggregated gradually. Firstly point-level information …
We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video clip and a language sentence). Our multimodal matching network consists of two key components. First, the Joint Semantic Tensor composes a dense pairwise representation of two sequence data into a 3D tensor. Then, the Convolutional Hierarchical Decoder computes their similarity score by discovering hidden hierarchical matches between the two sequence modalities. Both modules leverage hierarchical attention mechanisms that learn to promot…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；eBay Research Lab（eBay研究实验室）；The University of Hong Kong（香港大学）
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifiers, and few efforts have been made to leverage the hierarchical structure of categories. In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy. An HD-CNN separates easy classes using a coarse category classifier while disti…
Building successful recommender systems requires uncovering the underlying dimensions that describe the properties of items as well as users' preferences toward them. In domains like clothing recommendation, explaining users' preferences requires modeling the visual appearance of the items in question. This makes recommendation especially challenging, due to both the complexity and subtlety of people's 'visual preferences,' as well as the scale and dimensionality of the data and features involved. Ultimately, a successful model should be capable of capturing considerable variance across differ…
University of Birmingham（伯明翰大学）；Poznan University of Technology（波兹南理工大学）
We propose a joint object pose estimation and categorization approach which extracts information about object poses and categories from the object parts and compositions constructed at different layers of a hierarchical object representation algorithm, namely Learned Hierarchy of Parts (LHOP). In the proposed approach, we first employ the LHOP to learn hierarchical part libraries which represent entity parts and compositions across different object categories and views. Then, we extract statistical and geometric features from the part realizations of the objects in the images in order to repre…
Deep convolutional networks (DCNs) learn meaningful representations where data that share the same abstract characteristics are positioned closer and closer. Understanding these representations and how they are generated is of unquestioned practical and theoretical interest. In this work we study the evolution of the probability density of the ImageNet dataset across the hidden layers in some state-of-the-art DCNs. We find that the initial layers generate a unimodal probability density getting rid of any structure irrelevant for classification. In subsequent layers density peaks arise in a hie…
The explosion of video data on the internet requires effective and efficient technology to generate captions automatically for people who are not able to watch the videos. Despite the great progress of video captioning research, particularly on video feature encoding, the language decoder is still largely based on the prevailing RNN decoder such as LSTM, which tends to prefer the frequent word that aligns with the video. In this paper, we propose a boundary-aware hierarchical language decoder for video captioning, which consists of a high-level GRU based language decoder, working as a global (…
The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SketchParse, the first deep-network architecture for fully automatic parsing of freehand object sketches. SketchParse is configured as a two-level fully convolutional network. The first level contains shared layers common to all object categories. The second level contains a number of expert sub-networks. Each expert specializes in parsing sketches from object categories which contain structurally similar parts. Effectively, the two-level conf…
Yonsei University（延世大学）；NAVER AI Lab（NAVER人工智能实验室）
Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like other vision tasks, most recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling long-range dependencies due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To overcome this issu…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Electronic Science and Technology of China（电子科技大学）
The main question we address in this paper is how to scale up visual recognition of unseen classes, also known as zero-shot learning, to tens of thousands of categories as in the ImageNet-21K benchmark. At this scale, especially with many fine-grained categories included in ImageNet-21K, it is critical to learn quality visual semantic representations that are discriminative enough to recognize unseen classes and distinguish them from seen ones. We propose a \emph{H}ierarchical \emph{G}raphical knowledge \emph{R}epresentation framework for the confidence-based classification method, dubbed as H…
Target detection in hyperspectral imagery is the process of locating pixels from an image which are likely to contain target, typically done by comparing one or more spectra for the desired target material to each pixel in the image. Target identification is the process of target detection incorporating an additional process to identify more specifically the material that is present in each pixel that scored high in detection. Detection is generally a 2-class problem of target vs. background, and identification is a many class problem including target, background, and additional know materials…
United Imaging Intelligence（联影智能）；George Mason University（乔治梅森大学）
We consider the problem of estimating a parametric model of 3D human mesh from a single image. While there has been substantial recent progress in this area with direct regression of model parameters, these methods only implicitly exploit the human body kinematic structure, leading to sub-optimal use of the model prior. In this work, we address this gap by proposing a new technique for regression of human parametric model that is explicitly informed by the known hierarchical structure, including joint interdependencies of the model. This results in a strong prior-informed design of the regress…
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；University of Rochester（罗切斯特大学）；Nanyang Technological University（南洋理工大学）
