Impressive advances in acquisition and sharing technologies have made the growth of multimedia collections and their applications almost unlimited. However, the opposite is true for the availability of labeled data, which is needed for supervised training, since such data is often expensive and time-consuming to obtain. While there is a pressing need for the development of effective retrieval and classification methods, the difficulties faced by supervised approaches highlight the relevance of methods capable of operating with few or no labeled data. In this work, we propose a novel manifold learning algorithm named Rank Flow Embedding (RFE) for unsupervised and semi-supervised scenarios. The proposed method is based on ideas recently exploited by manifold learning approaches, which include hypergraphs, Cartesian products, and connected components. The algorithm computes context-sensitive embeddings, which are refined following a rank-based processing flow, while complementary contextual information is incorporated. The generated embeddings can be exploited for more effective unsupervised retrieval or semi-supervised classification based on Graph Convolutional Networks. Experimental results were conducted on 10 different collections. Various features were considered, including the ones obtained with recent Convolutional Neural Networks (CNN) and Vision Transformer (ViT) models. High effective results demonstrate the effectiveness of the proposed method on different tasks: unsupervised image retrieval, semi-supervised classification, and person Re-ID. The results demonstrate that RFE is competitive or superior to the state-of-the-art in diverse evaluated scenarios.
Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation or task diversity improvement while neglecting the phenomenon that deep networks tend to rely more on high-frequency cues to make the classification decision, which thus degenerates the robustness of learned inductive bias since high-frequency information is vulnerable and easy to be disturbed by noisy information. Hence in this paper, we make one of the first attempts to propose a Frequency-Aware Prompting method with mutual attention for Cross-Domain Few-Shot classification, which can let networks simulate the human visual perception of selecting different frequency cues when facing new recognition tasks. Specifically, a frequency-aware prompting mechanism is first proposed, in which high-frequency components of the decomposed source image are switched either with normal distribution sampling or zeroing to get frequency-aware augment samples. Then, a mutual attention module is designed to learn generalizable inductive bias under CD-FSL settings. More importantly, the proposed method is a plug-and-play module that can be directly applied to most off-the-shelf CD-FLS methods. Experimental results on CD-FSL benchmarks demonstrate the effectiveness of our proposed method as well as robustly improve the performance of existing CD-FLS methods. Resources at https://github.com/tinkez/FAP_CDFSC.
Low-quality or scarce data has posed significant challenges for training deep neural networks in practice. While classical data augmentation cannot contribute very different new data, diffusion models opens up a new door to build self-evolving AI by generating high-quality and diverse synthetic data through text-guided prompts. However, text-only guidance cannot control synthetic images' proximity to the original images, resulting in out-of-distribution data detrimental to the model performance. To overcome the limitation, we study image guidance to achieve a spectrum of interpolations between synthetic and real images. With stronger image guidance, the generated images are similar to the training data but hard to learn. While with weaker image guidance, the synthetic images will be easier for model but contribute to a larger distribution gap with the original data. The generated full spectrum of data enables us to build a novel "Diffusion Curriculum (DisCL)". DisCL adjusts the image guidance level of image synthesis for each training stage: It identifies and focuses on hard samples for the model and assesses the most effective guidance level of synthetic images to improve hard data learning. We apply DisCL to two challenging tasks: long-tail (LT) classification and learning from low-quality data. It focuses on lower-guidance images of high-quality to learn prototypical features as a warm-up of learning higher-guidance images that might be weak on diversity or quality. Extensive experiments showcase a gain of 2.7% and 2.1% in OOD and ID macro-accuracy when applying DisCL to iWildCam dataset. On ImageNet-LT, DisCL improves the base model's tail-class accuracy from 4.4% to 23.64% and leads to a 4.02% improvement in all-class accuracy.
Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant for a specific application, however, usually differs from publicly available datasets since it is sampled from a different domain. While domain adaptation methods compensate for such a domain shift, they assume that all categories in the target domain are known and match the categories in the source domain. Since this assumption is violated under real-world conditions, we propose an approach for open set domain adaptation where the target domain contains instances of categories that are not present in the source domain. The proposed approach achieves state-of-the-art results on various datasets for image classification and action recognition. Since the approach can be used for open set and closed set domain adaptation, as well as unsupervised and semi-supervised domain adaptation, it is a versatile tool for many applications.
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify elements within an image and increase the accuracy and robustness of vision-based recognition systems. Following this rationale, we propose a novel residual attention learning method for improving ViT-based architectures, increasing their visual feature diversity and model robustness. In this way, the proposed network can capture and preserve significant low-level features, providing more details about the elements within the scene being analyzed. The effectiveness and robustness of the presented method are evaluated on five image classification benchmarks, including ImageNet1k, CIFAR10, CIFAR100, Oxford Flowers-102, and Oxford-IIIT Pet, achieving improved performances. Additionally, experiments on the COCO2017 dataset show that the devised approach discovers and incorporates semantic and spatial relationships for object detection and instance segmentation when implemented into spatial-aware transformer models.
In this study, we introduce a novel method, called MamT$^4$, which is used for simultaneous analysis of four mammography images. A decision is made based on one image of a breast, with attention also devoted to three additional images: another view of the same breast and two images of the other breast. This approach enables the algorithm to closely replicate the practice of a radiologist who reviews the entire set of mammograms for a patient. Furthermore, this paper emphasizes the preprocessing of images, specifically proposing a cropping model (U-Net based on ResNet-34) to help the method remove image artifacts and focus on the breast region. To the best of our knowledge, this study is the first to achieve a ROC-AUC of 84.0 $\pm$ 1.7 and an F1 score of 56.0 $\pm$ 1.3 on an independent test dataset of Vietnam digital mammography (VinDr-Mammo), which is preprocessed with the cropping model.
Automatic neural architecture design has shown its potential in discovering powerful neural network architectures. Existing methods, no matter based on reinforcement learning or evolutionary algorithms (EA), conduct architecture search in a discrete space, which is highly inefficient. In this paper, we propose a simple and efficient method to automatic neural architecture design based on continuous optimization. We call this new approach neural architecture optimization (NAO). There are three key components in our proposed approach: (1) An encoder embeds/maps neural network architectures into a continuous space. (2) A predictor takes the continuous representation of a network as input and predicts its accuracy. (3) A decoder maps a continuous representation of a network back to its architecture. The performance predictor and the encoder enable us to perform gradient based optimization in the continuous space to find the embedding of a new architecture with potentially better accuracy. Such a better embedding is then decoded to a network by the decoder. Experiments show that the architecture discovered by our method is very competitive for image classification task on CIFAR-10 and language modeling task on PTB, outperforming or on par with the best results of previous architecture search methods with a significantly reduction of computational resources. Specifically we obtain 1.93% test set error rate for CIFAR-10 image classification task and 56.0 test set perplexity of PTB language modeling task. Furthermore, combined with the recent proposed weight sharing mechanism, we discover powerful architecture on CIFAR-10 (with error rate 2.93%) and on PTB (with test set perplexity 56.6), with very limited computational resources (less than 10 GPU hours) for both tasks.
Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is that while they might work well on one input type, such as images, their performance drops when applied to others, such as text or time-series. In this paper, we introduce Proportional Progressive Pseudo Labeling (PPPL), a simple, yet effective technique that can be implemented in a few lines of code to build a more general domain adaptation technique that can be applied on several different input types. At the beginning of the training phase, PPPL progressively reduces target domain classification error, by training the model directly with pseudo-labeled target domain samples, while excluding samples with more likely wrong pseudo-labels from the training set and also postponing training on such samples. Experiments on 6 different datasets that include tasks such as anomaly detection, text sentiment analysis and image classification demonstrate that PPPL can beat other baselines and generalize better.
Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis. However, limited by the significant data imbalance and obvious extraneous artifacts, i.e., the hair and ruler markings, discriminative feature extraction from dermoscopic images is very challenging. In this study, we seek to resolve these problems respectively towards better representation learning for lesion features. Specifically, a GAN-based data augmentation (GDA) strategy is adapted to generate synthetic melanoma-positive images, in conjunction with the proposed implicit hair denoising (IHD) strategy. Wherein the hair-related representations are implicitly disentangled via an auxiliary classifier network and reversely sent to the melanoma-feature extraction backbone for better melanoma-specific representation learning. Furthermore, to train the IHD module, the hair noises are additionally labeled on the ISIC2020 dataset, making it the first large-scale dermoscopic dataset with annotation of hair-like artifacts. Extensive experiments demonstrate the superiority of the proposed framework as well as the effectiveness of each component. The improved dataset publicly avaliable at https://github.com/kirtsy/DermoscopicDataset.
The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer's disease classification, Parkinson's disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks.
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are diverging. Generally, network structures designed specifically for image classification are directly used as default backbone structure for other tasks including detection and segmentation, but there is seldom backbone structure designed under the consideration of unifying the advantages of networks designed for pixel-level or region-level predicting tasks, which may require very deep features with high resolution. Towards this goal, we design a fish-like network, called FishNet. In FishNet, the information of all resolutions is preserved and refined for the final task. Besides, we observe that existing works still cannot \emph{directly} propagate the gradient information from deep layers to shallow layers. Our design can better handle this problem. Extensive experiments have been conducted to demonstrate the remarkable performance of the FishNet. In particular, on ImageNet-1k, the accuracy of FishNet is able to surpass the performance of DenseNet and ResNet with fewer parameters. FishNet was applied as one of the modules in the winning entry of the COCO Detection 2018 challenge. The code is available at https://github.com/kevin-ssy/FishNet.
Recent advancements in graph-based approaches for multiplexed immunofluorescence (mIF) images have significantly propelled the field forward, offering deeper insights into patient-level phenotyping. However, current graph-based methodologies encounter two primary challenges: (1) Cellular Heterogeneity, where existing approaches fail to adequately address the inductive biases inherent in graphs, particularly the homophily characteristic observed in cellular connectivity and; (2) Scalability, where handling cellular graphs from high-dimensional images faces difficulties in managing a high number of cells. To overcome these limitations, we introduce Mew, a novel framework designed to efficiently process mIF images through the lens of multiplex network. Mew innovatively constructs a multiplex network comprising two distinct layers: a Voronoi network for geometric information and a Cell-type network for capturing cell-wise homogeneity. This framework equips a scalable and efficient Graph Neural Network (GNN), capable of processing the entire graph during training. Furthermore, Mew integrates an interpretable attention module that autonomously identifies relevant layers for image classification. Extensive experiments on a real-world patient dataset from various institutions highlight Mew's remarkable efficacy and efficiency, marking a significant advancement in mIF image analysis. The source code of Mew can be found here: \url{https://github.com/UNITES-Lab/Mew}
Vision-Language models like CLIP have been shown to be highly effective at linking visual perception and natural language understanding, enabling sophisticated image-text capabilities, including strong retrieval and zero-shot classification performance. Their widespread use, as well as the fact that CLIP models are trained on image-text pairs from the web, make them both a worthwhile and relatively easy target for backdoor attacks. As training foundational models, such as CLIP, from scratch is very expensive, this paper focuses on cleaning potentially poisoned models via fine-tuning. We first show that existing cleaning techniques are not effective against simple structured triggers used in Blended or BadNet backdoor attacks, exposing a critical vulnerability for potential real-world deployment of these models. Then, we introduce PAR, Perturb and Recover, a surprisingly simple yet effective mechanism to remove backdoors from CLIP models. Through extensive experiments across different encoders and types of backdoor attacks, we show that PAR achieves high backdoor removal rate while preserving good standard performance. Finally, we illustrate that our approach is effective even only with synthetic text-image pairs, i.e. without access to real training data. The code and models are available at https://github.com/nmndeep/PerturbAndRecover.
We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs than image captions while having minimal impact on training and inference efficiency. ViLT, importantly, enables efficient training and inference in VL tasks, achieved by encoding images using a linear projection of patches instead of an object detector. However, it is pretrained on captioning datasets, where the language input is simple, literal, and descriptive, therefore lacking linguistic diversity. So, when working with multimedia data in the wild, such as multimodal social media data, there is a notable shift from captioning language data, as well as diversity of tasks. We indeed find evidence that the language capacity of ViLT is lacking. The key insight and novelty of VAuLT is to propagate the output representations of a large language model (LM) like BERT to the language input of ViLT. We show that joint training of the LM and ViLT can yield relative improvements up to 20% over ViLT and achieve state-of-the-art or comparable performance on VL tasks involving richer language inputs and affective constructs, such as for Target-Oriented Sentiment Classification in TWITTER-2015 and TWITTER-2017, and Sentiment Classification in MVSA-Single and MVSA-Multiple. Our code is available at https://github.com/gchochla/VAuLT.
Multiple instance learning (MIL) stands as a powerful approach in weakly supervised learning, regularly employed in histological whole slide image (WSI) classification for detecting tumorous lesions. However, existing mainstream MIL methods focus on modeling correlation between instances while overlooking the inherent diversity among instances. However, few MIL methods have aimed at diversity modeling, which empirically show inferior performance but with a high computational cost. To bridge this gap, we propose a novel MIL aggregation method based on diverse global representation (DGR-MIL), by modeling diversity among instances through a set of global vectors that serve as a summary of all instances. First, we turn the instance correlation into the similarity between instance embeddings and the predefined global vectors through a cross-attention mechanism. This stems from the fact that similar instance embeddings typically would result in a higher correlation with a certain global vector. Second, we propose two mechanisms to enforce the diversity among the global vectors to be more descriptive of the entire bag: (i) positive instance alignment and (ii) a novel, efficient, and theoretically guaranteed diversification learning paradigm. Specifically, the positive instance alignment module encourages the global vectors to align with the center of positive instances (e.g., instances containing tumors in WSI). To further diversify the global representations, we propose a novel diversification learning paradigm leveraging the determinantal point process. The proposed model outperforms the state-of-the-art MIL aggregation models by a substantial margin on the CAMELYON-16 and the TCGA-lung cancer datasets. The code is available at \url{https://github.com/ChongQingNoSubway/DGR-MIL}.
Domain adaptive image retrieval includes single-domain retrieval and cross-domain retrieval. Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and queries are similar. However, in practical application, the discrepancies between retrieval databases often taken in ideal illumination/pose/background/camera conditions and queries usually obtained in uncontrolled conditions are very large. In this paper, considering the practical application, we focus on challenging cross-domain retrieval. To address the problem, we propose an effective method named Probability Weighted Compact Feature Learning (PWCF), which provides inter-domain correlation guidance to promote cross-domain retrieval accuracy and learns a series of compact binary codes to improve the retrieval speed. First, we derive our loss function through the Maximum A Posteriori Estimation (MAP): Bayesian Perspective (BP) induced focal-triplet loss, BP induced quantization loss and BP induced classification loss. Second, we propose a common manifold structure between domains to explore the potential correlation across domains. Considering the original feature representation is biased due to the inter-domain discrepancy, the manifold structure is difficult to be constructed. Therefore, we propose a new feature named Histogram Feature of Neighbors (HFON) from the sample statistics perspective. Extensive experiments on various benchmark databases validate that our method outperforms many state-of-the-art image retrieval methods for domain adaptive image retrieval. The source code is available at https://github.com/fuxianghuang1/PWCF
Advances in brain decoding, particularly visual image reconstruction, have sparked discussions about the societal implications and ethical considerations of neurotechnology. As these methods aim to recover visual experiences from brain activity and achieve prediction beyond training samples (zero-shot prediction), it is crucial to assess their capabilities and limitations to inform public expectations and regulations. Our case study of recent text-guided reconstruction methods, which leverage a large-scale dataset (Natural Scene Dataset, NSD) and text-to-image diffusion models, reveals limitations in their generalizability. We found poor performance when applying these methods to a different dataset designed to prevent category overlaps between training and test sets. UMAP visualization of the text features with NSD images showed a limited diversity of semantic and visual clusters, with overlap between training and test sets. Formal analysis and simulations demonstrated that clustered training samples can lead to "output dimension collapse," restricting predictable output feature dimensions. Simulations further showed that diversifying the training set improved generalizability. However, text features alone are insufficient for mapping to the visual space. We argue that recent realistic reconstructions may primarily be a blend of classification into trained categories and generation of inauthentic images through text-to-image diffusion (hallucination). Diverse datasets and compositional representations spanning the image space are essential for genuine zero-shot prediction. Interdisciplinary discussions grounded in understanding the current capabilities and limitations, as well as ethical considerations, of the technology are crucial for its responsible development.
In this paper we present the design and evaluation of an end-to-end trainable, deep neural network with a visual attention mechanism for memorability estimation in still images. We analyze the suitability of transfer learning of deep models from image classification to the memorability task. Further on we study the impact of the attention mechanism on the memorability estimation and evaluate our network on the SUN Memorability and the LaMem datasets. Our network outperforms the existing state of the art models on both datasets in terms of the Spearman's rank correlation as well as the mean squared error, closely matching human consistency.
NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions. Particularly, AutoCV challenges mainly focused on classification tasks on visual domain. In this paper, we introduce the winning method in the competition, AutoCLINT. The proposed method implements an autonomous training strategy, including efficient code optimization, and applies an automated data augmentation to achieve the fast adaptation of pretrained networks. We implement a light version of Fast AutoAugment to search for data augmentation policies efficiently for the arbitrarily given image domains. We also empirically analyze the components of the proposed method and provide ablation studies focusing on AutoCV datasets.
Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model should be invariant to a given symmetry group. We show how to \emph{learn} invariances and equivariances by parameterizing a distribution over augmentations and optimizing the training loss simultaneously with respect to the network parameters and augmentation parameters. With this simple procedure we can recover the correct set and extent of invariances on image classification, regression, segmentation, and molecular property prediction from a large space of augmentations, on training data alone.