Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with visual processing. Similar to humans, recent artificial models jointly trained on texts and images, e.g., OpenAI CLIP, show language-biased image classification. Exploring whether the bias leads to interference similar to those observed in humans can contribute to understanding how much the model acquires hierarchical semantic representations from joint learning of language and vision. The present study introduces methodological tools from the cognitive science literature to assess the biases of artificial models. Specifically, we introduce a benchmark task to test whether words superimposed on images can distort the image classification across different category levels and, if it can, whether the perturbation is due to the shared semantic representation between language and vision. Our dataset is a set of word-embedded images and consists of a mixture of natural image datasets and hierarchical word labels with superordinate/basic category levels. Using this benchmark test, we evaluate the CLIP model. We show that presenting words distorts the image classification by the model across different category levels, but the effect does not depend on the semantic relationship between images and embedded words. This suggests that the semantic word representation in the CLIP visual processing is not shared with the image representation, although the word representation strongly dominates for word-embedded images.
L3S Research Center（L3S研究中心）；Leibniz University of Hannover（莱布尼茨汉诺威大学）
Biased language commonly occurs around topics which are of controversial nature, thus, stirring disagreement between the different involved parties of a discussion. This is due to the fact that for language and its use, specifically, the understanding and use of phrases, the stances are cohesive within the particular groups. However, such cohesiveness does not hold across groups. In collaborative environments or environments where impartial language is desired (e.g. Wikipedia, news media), statements and the language therein should represent equally the involved parties and be neutrally phrase…
Tokyo Institute of Technology（东京工业大学）；Microsoft STCA（微软STCA）；Nanjing University（南京大学）；Microsoft Research Asia（微软亚洲研究院）
The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits (classification scores) and empirically observe the biased margins and the biased logits are positively correlated. We propose MARC, a simple ye…
Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence. While state-of-the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue of robustness. Particularly in two common scenarios: when domains of test and training data are different (out-of-domain scenario) or test data is adversarially perturbed (adversarial scenario), ASC models may attend to irrelevant words and neglect opinion expressions that truly describe diverse aspects. To tackle the challenge, in this paper, we hypothesiz…
INRIA RITS（法国国家信息与自动化研究所RITS）；LANDING AI（澜舟科技）；Signal Ocean（信号海洋）；Philips Research（飞利浦研究院）；Eindhoven University of Technology（埃因霍温理工大学）；U2IS ENSTA Institut Polytechnique Paris（巴黎综合理工学院ENSTA U2IS实验室）；INRIA Flowers（法国国家信息与自动化研究所Flowers实验室）
Image captioning models have been able to generate grammatically correct and human understandable sentences. However most of the captions convey limited information as the model used is trained on datasets that do not caption all possible objects existing in everyday life. Due to this lack of prior information most of the captions are biased to only a few objects present in the scene, hence limiting their usage in daily life. In this paper, we attempt to show the biased nature of the currently existing image captioning models and present a new image captioning dataset, Egoshots, consisting of …
A character-level convolutional neural network (CNN) motivated by applications in "automated machine learning" (AutoML) is proposed to semantically classify columns in tabular data. Simulated data containing a set of base classes is first used to learn an initial set of weights. Hand-labeled data from the CKAN repository is then used in a transfer-learning paradigm to adapt the initial weights to a more sophisticated representation of the problem (e.g., including more classes). In doing so, realistic data imperfections are learned and the set of classes handled can be expanded from the base se…
Univ. of Electronic Science and Technology of China（电子科技大学）
This paper proposes a classification network to image semantic retrieval (NIST) framework to counter the image retrieval challenge. Our approach leverages the successful classification network GoogleNet based on Convolutional Neural Networks to obtain the semantic feature matrix which contains the serial number of classes and corresponding probabilities. Compared with traditional image retrieval using feature matching to compute the similarity between two images, NIST leverages the semantic information to construct semantic feature matrix and uses the semantic distance algorithm to compute the…
Compared with single-label image classification, multi-label image classification is more practical and challenging. Some recent studies attempted to leverage the semantic information of categories for improving multi-label image classification performance. However, these semantic-based methods only take semantic information as type of complements for visual representation without further exploitation. In this paper, we present an innovative path towards the solution of the multi-label image classification which considers it as a dictionary learning task. A novel end-to-end model named Deep Se…
Semantic Meta-Split Learning: A TinyML Scheme for Few-Shot Wireless Image Classification
Centre for Wireless Communications (CWC), University of Oulu（奥卢大学无线通信中心）；CEMSE Division, King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学CEMSE学部）
Singapore Management University（新加坡管理大学）；Institute for Infocomm Research（资讯通信研究院）；Australia National University（澳大利亚国立大学）
Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model …
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
In this paper, we propose SemanticAC, a semantics-assisted framework for Audio Classification to better leverage the semantic information. Unlike conventional audio classification methods that treat class labels as discrete vectors, we employ a language model to extract abundant semantics from labels and optimize the semantic consistency between audio signals and their labels. We verify that simple textual information from labels and advanced pretraining models enable more abundant semantic supervision for better performance. Specifically, we design a text encoder to capture the semantic infor…
This paper presents Semantic SentenceRank (SSR), an unsupervised scheme for automatically ranking sentences in a single document according to their relative importance. In particular, SSR extracts essential words and phrases from a text document, and uses semantic measures to construct, respectively, a semantic phrase graph over phrases and words, and a semantic sentence graph over sentences. It applies two variants of article-structure-biased PageRank to score phrases and words on the first graph and sentences on the second graph. It then combines these scores to generate the final score for …
For polarimetric SAR (PolSAR) image classification, it is a challenge to classify the aggregated terrain types, such as the urban area, into semantic homogenous regions due to sharp bright-dark variations in intensity. The aggregated terrain type is formulated by the similar ground objects aggregated together. In this paper, a polarimetric hierarchical semantic model (PHSM) is firstly proposed to overcome this disadvantage based on the constructions of a primal-level and a middle-level semantic. The primal-level semantic is a polarimetric sketch map which consists of sketch segments as the spa…
Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification
School of Mathematics and Information Science（数学与信息科学学院）；Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition（江西省图像处理与模式识别重点实验室）
With the development of medical imaging technology and machine learning, computer-assisted diagnosis which can provide impressive reference to pathologists, attracts extensive research interests. The exponential growth of medical images and uninterpretability of traditional classification models have hindered the applications of computer-assisted diagnosis. To address these issues, we propose a novel method for Learning Binary Semantic Embedding (LBSE). Based on the efficient and effective embedding, classification and retrieval are performed to provide interpretable computer-assisted diagnosi…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this problem. We first pinpoint task-aware regions over the input image by a lightweight patch proposal network called AnchorNet. We then feed these localized semantic patches with much smaller spatial redundancy into a general classification network. Unlike the popular design of deep CNN, we aim to carefully design the Receptive Field of AnchorNet without intermedia…
Zhejiang University（浙江大学）；University of Michigan（密歇根大学）
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made available in a consecutive manner, leading to a problem called Continual Semantic Segmentation (CSS). Typically, CSS faces the forgetting problem since previous training images are unavailable, and the semantic shift problem of the background class. Considering the semantic segmentation as a context-dependent pixel-level classification task, we explore CSS from a new perspective of …
The University of Hong Kong（香港大学）；Zhejiang University（浙江大学）
While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes. In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data. Besides, we also contribute a progressive data augmentation and labeling strategy to facilitate model training with pseudo-labeled data. Experi…
Deep learning (DL) models are widely used to provide a more convenient and smarter life. However, biased algorithms will negatively influence us. For instance, groups targeted by biased algorithms will feel unfairly treated and even fearful of negative consequences of these biases. This work targets biased generative models' behaviors, identifying the cause of the biases and eliminating them. We can (as expected) conclude that biased data causes biased predictions of face frontalization models. Varying the proportions of male and female faces in the training data can have a substantial effect …
Confidence Scores in Open-Vocabulary Detection Are a Biased Mixture of Scale and Semantics
Institute of Intelligence Systems, National Yang Ming Chiao Tung University（国立阳明交通大学智能系统研究所）；College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University（国立阳明交通大学人工智能与绿色能源学院）
Bosch Center for Artificial Intelligence（博世人工智能中心）
Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we introduce a novel augmentation scheme designed specifically for GAN-based semantic image synthesis models. We propose to randomly warp object shapes in the semantic label maps used as an input to the generator. The local shape discrepancies between the warped and non-warped label maps and images enable the GAN to learn better the structural and geometric details…
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve s…
In this paper we propose a non-metric ranking-based representation of semantic similarity that allows natural aggregation of semantic information from multiple heterogeneous sources. We apply the ranking-based representation to zero-shot learning problems, and present deterministic and probabilistic zero-shot classifiers which can be built from pre-trained classifiers without retraining. We demonstrate their the advantages on two large real-world image datasets. In particular, we show that aggregating different sources of semantic information, including crowd-sourcing, leads to more accurate c…
University of Science and Technology of China（中国科学技术大学）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem. In this paper, we propose a novel Domain-aware Visual Bias Eliminating (DVBE) network that constructs two complementary visual representations, i.e., semantic-free and semantic-aligned, to treat seen and unseen domains separately. Specifically, we explore cross-attentive second-order visual statistics to compact the semantic-free representation, and design an a…
Cerebral hematoma grows rapidly in 6-24 hours and misprediction of the growth can be fatal if it is not operated by a brain surgeon. There are two types of cerebral hematomas: one that grows rapidly and the other that does not grow rapidly. We are developing the technique of artificial intelligence to determine whether the CT image includes the cerebral hematoma which leads to the rapid growth. This problem has various difficulties: the few positive cases in this classification problem of cerebral hematoma and the targeted hematoma has deformable object. Other difficulties include the imbalanc…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated with each class. This semantic-descriptor space is generally shared by both seen and unseen categories. However, ZSL suffers from hubness, domain discrepancy and biased-ness towards seen classes. To tackle these problems, we propose a three-step approach to zero-shot learning. Firstly, a mapping is learned from the semantic-descriptor space to the image-feature…
Military Institute of Science & Technology（军事科学技术研究院）；Independent University, Bangladesh（孟加拉国独立大学）
This paper analyses how well a Fast Fully Convolutional Network (FastFCN) semantically segments satellite images and thus classifies Land Use/Land Cover(LULC) classes. Fast-FCN was used on Gaofen-2 Image Dataset (GID-2) to segment them in five different classes: BuiltUp, Meadow, Farmland, Water and Forest. The results showed better accuracy (0.93), precision (0.99), recall (0.98) and mean Intersection over Union (mIoU)(0.97) than other approaches like using FCN-8 or eCognition, a readily available software. We presented a comparison between the results. We propose FastFCN to be both faster and…
Facebook AI Research（Facebook人工智能研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask class…
Hyperspectral signature classification is a quantitative analysis approach for hyperspectral imagery which performs detection and classification of the constituent materials at the pixel level in the scene. The classification procedure can be operated directly on hyperspectral data or performed by using some features extracted from the corresponding hyperspectral signatures containing information like the signature's energy or shape. In this paper, we describe a technique that applies non-homogeneous hidden Markov chain (NHMC) models to hyperspectral signature classification. The basic idea is…
University of Science and Technology of China（中国科学技术大学）
Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning image representations with corresponding semantic labels, the semantic-aligned representations can be transferred to unseen categories. However, supervised by only seen category labels, the learned semantic knowledge is highly task-specific, which makes image representations biased towards seen categories. In this paper, we propose a novel Dual-Contrastive Embedding Network (DCEN) that simultaneously learns task-specific and task-indep…
We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for each class. Motivated by the binary relevance method for multi-label classification, we propose to inversely learn the mapping between an image and a semantic classifier. Given an input image, the proposed Image-Guided Semantic Classification (IGSC) method creates a label classifier, being applied to all label embeddings to determine whether a label belongs …
Movie genre classification is an active research area in machine learning. However, due to the limited labels available, there can be large semantic variations between movies within a single genre definition. We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies. By leveraging pre-trained 'expert' networks, we learn the influence of different combinations of modes for multi-label genre classification. Using a contrastive loss, we continue to fine-tune this 'coarse' genre classification network to identify high-level in…
Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevance Flow, to interpret the hidden semantics of 3D point cloud classification neural networks. It delivers the class Relevance to the activated neurons in the intermediate layers in a back-propagation manner, and associates the activation of neurons with the input points to visualize the hidden semantics of each layer. Specially, we reveal that the 3D point cloud classification n…
Ohio State University（俄亥俄州立大学）；Air Force Research Laboratory（空军研究实验室）
Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The proposed strategy is contingent upon computing the classifier confusion probabilities for a given dataset and estimating a relevant prior on the object classes present in the image to be classified. We provide a procedure to robustly estimate the confusion probabilities and explore multiple prior definitions. Experiments are shown comparing performances on multi…
Shahid Bahonar University of Kerman（克尔曼沙希德·巴霍纳尔大学）；University of Manitoba（曼尼托巴大学）
It is known that, without awareness of the process, our brain appears to focus on the general shape of objects rather than superficial statistics of context. On the other hand, learning autonomously allows discovering invariant regularities which help generalization. In this work, we propose a learning framework to improve the shape bias property of self-supervised methods. Our method learns semantic and shape biased representations by integrating domain diversification and jigsaw puzzles. The first module enables the model to create a dynamic environment across arbitrary domains and provides …
Mines ParisTech（巴黎高等矿业学院）；PSL Research University（巴黎文理研究大学）
This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the computation of features with a consistent geometrical meaning, which is not the case when using k-nearest neighbors. With an appropriate learning strategy, the proposed features can be used in a random forest to classify 3D points. In this semantic classification task, we show that our multiscale features outperform state-of-the-art features using the same experimental conditions. Furthermore, their classification powe…
ScSAM: Debiasing Morphology and Distributional Variability in Subcellular Semantic Segmentation
School of Computer Science, University of Sydney, Australia（悉尼大学计算机科学学院）；Lawrence Berkeley National Laboratory, USA（伯克利国家实验室）；School of Medical Sciences (Molecular and Cellular Biomedicine), University of Sydney, Australia（悉尼大学医学学院）；Australian Centre for Microscopy and Microanalysis, University of Sydney, Australia（悉尼大学显微镜与显微分析中心）
针对亚细胞结构形态与分布变异导致的分割偏差，本文提出 ScSAM，融合预训练 SAM 与 MAE 细胞先验，并通过特征对齐融合和类别提示编码提升性能。
State Key Lab. LIESMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Given an aerial image, aerial scene parsing (ASP) targets to interpret the semantic structure of the image content, e.g., by assigning a semantic label to every pixel of the image. With the popularization of data-driven methods, the past decades have witnessed promising progress on ASP by approaching the problem with the schemes of tile-level scene classification or segmentation-based image analysis, when using high-resolution aerial images. However, the former scheme often produces results with tile-wise boundaries, while the latter one needs to handle the complex modeling process from pixels…
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our nove…
ReGIM (Research Group on Intelligent Machine)（智能机器研究组）；National Engineering School of Sfax, Tunisia（斯法克斯国家工程学院）；University of Sfax, Tunisia（斯法克斯大学）
We present in this paper an intelligent video data visualization tool, based on semantic classification, for retrieving and exploring a large scale corpus of videos. Our work is based on semantic classification resulting from semantic analysis of video. The obtained classes will be projected in the visualization space. The graph is represented by nodes and edges, the nodes are the keyframes of video documents and the edges are the relation between documents and the classes of documents. Finally, we construct the user's profile, based on the interaction with the system, to render the system mor…
Medical Image Debiasing by Learning Adaptive Agreement from a Biased Council
The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong Polytechnic University（香港理工大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳-香港协同创新研究院）
Single-branch object detection methods use shared features for localization and classification, yet the shared features are not fit for the two different tasks simultaneously. Multi-branch object detection methods usually use different features for localization and classification separately, ignoring the relevance between different tasks. Therefore, we propose multi-semantic interactive learning (MSIL) to mine the semantic relevance between different branches and extract multi-semantic enhanced features of objects. MSIL first performs semantic alignment of regression and classification branche…
Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation. For both non-novel and novel image classes we compare multiple formulations of the problem, starting with deep universal features in each case. We investigate the effect of using different posterior probabilities as inputs to the hierarchical classifier, comparing the performances of posteriors derived from distances to SVM classifier boundaries with those of posteriors based on semantic attribute estimation. Using a dataset consist…
