Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image. However, because standard GAN training is not dependent on the classifier, it may not represent these attributes which are important for the classifier decision, and the dimensions of StyleSpace may represent irrelevant attributes. To overcome this, we propose a training procedure for a StyleGAN, which incorporates the classifier model, in order to learn a classifier-specific StyleSpace. Explanatory attributes are then selected from this space. These can be used to visualize the effect of changing multiple attributes per image, thus providing image-specific explanations. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.
Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input image, and thus biased perception of partial local details of the image. To solve this problem, we propose a Visual Content Refinement (VCR) before the adaptation calculation during the test stage. Specifically, we first decompose the test image into different scales to shift the feature extractor's attention to the details of the image. Then, we select the image view with the max prediction margin in each scale to filter out the noisy image views, where the prediction margins are calculated from the pre-trained CLIP model. Finally, we merge the content of the aforementioned selected image views based on their scales to construct a new robust representation. Thus, the merged content can be directly used to help the adapter focus on both global and local parts without any extra training parameters. We apply our method to 3 popular low-shot benchmark tasks with 13 datasets and achieve a significant improvement over state-of-the-art methods. For example, compared to the baseline (Tip-Adapter) on the few-shot classification task, our method achieves about 2\% average improvement for both training-free and training-need settings.
Recent few-shot learning works focus on training a model with prior meta-knowledge to fast adapt to new tasks with unseen classes and samples. However, conventional time-series classification algorithms fail to tackle the few-shot scenario. Existing few-shot learning methods are proposed to tackle image or text data, and most of them are neural-based models that lack interpretability. This paper proposes an interpretable neural-based framework, namely \textit{Dual Prototypical Shapelet Networks (DPSN)} for few-shot time-series classification, which not only trains a neural network-based model but also interprets the model from dual granularity: 1) global overview using representative time series samples, and 2) local highlights using discriminative shapelets. In particular, the generated dual prototypical shapelets consist of representative samples that can mostly demonstrate the overall shapes of all samples in the class and discriminative partial-length shapelets that can be used to distinguish different classes. We have derived 18 few-shot TSC datasets from public benchmark datasets and evaluated the proposed method by comparing with baselines. The DPSN framework outperforms state-of-the-art time-series classification methods, especially when training with limited amounts of data. Several case studies have been given to demonstrate the interpret ability of our model.
We propose, analyze and realize a variational multiclass segmentation scheme that partitions a given image into multiple regions exhibiting specific properties. Our method determines multiple functions that encode the segmentation regions by minimizing an energy functional combining information from different channels. Multichannel image data can be obtained by lifting the image into a higher dimensional feature space using specific multichannel filtering or may already be provided by the imaging modality under consideration, such as an RGB image or multimodal medical data. Experimental results show that the proposed method performs well in various scenarios. In particular, promising results are presented for two medical applications involving classification of brain abscess and tumor growth, respectively. As main theoretical contributions, we prove the existence of global minimizers of the proposed energy functional and show its stability and convergence with respect to noisy inputs. In particular, these results also apply to the special case of binary segmentation, and these results are also novel in this particular situation.
The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts. Contrastive learning, an unsupervised learning technique, has been proved powerful in learning image-level representations from unlabeled data. The learned encoder can then be transferred or fine-tuned to improve the performance of downstream tasks with limited labels. A critical step in contrastive learning is the generation of contrastive data pairs, which is relatively simple for natural image classification but quite challenging for medical image segmentation due to the existence of the same tissue or organ across the dataset. As a result, when applied to medical image segmentation, most state-of-the-art contrastive learning frameworks inevitably introduce a lot of false-negative pairs and result in degraded segmentation quality. To address this issue, we propose a novel positional contrastive learning (PCL) framework to generate contrastive data pairs by leveraging the position information in volumetric medical images. Experimental results on CT and MRI datasets demonstrate that the proposed PCL method can substantially improve the segmentation performance compared to existing methods in both semi-supervised setting and transfer learning setting.
Existing temporal action detection (TAD) methods rely on large training data including segment-level annotations, limited to recognizing previously seen classes alone during inference. Collecting and annotating a large training set for each class of interest is costly and hence unscalable. Zero-shot TAD (ZS-TAD) resolves this obstacle by enabling a pre-trained model to recognize any unseen action classes. Meanwhile, ZS-TAD is also much more challenging with significantly less investigation. Inspired by the success of zero-shot image classification aided by vision-language (ViL) models such as CLIP, we aim to tackle the more complex TAD task. An intuitive method is to integrate an off-the-shelf proposal detector with CLIP style classification. However, due to the sequential localization (e.g, proposal generation) and classification design, it is prone to localization error propagation. To overcome this problem, in this paper we propose a novel zero-Shot Temporal Action detection model via Vision-LanguagE prompting (STALE). Such a novel design effectively eliminates the dependence between localization and classification by breaking the route for error propagation in-between. We further introduce an interaction mechanism between classification and localization for improved optimization. Extensive experiments on standard ZS-TAD video benchmarks show that our STALE significantly outperforms state-of-the-art alternatives. Besides, our model also yields superior results on supervised TAD over recent strong competitors. The PyTorch implementation of STALE is available at https://github.com/sauradip/STALE.
We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call "cardinality" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.
Multiple Instance Learning (MIL) has demonstrated promise in Whole Slide Image (WSI) classification. However, a major challenge persists due to the high computational cost associated with processing these gigapixel images. Existing methods generally adopt a two-stage approach, comprising a non-learnable feature embedding stage and a classifier training stage. Though it can greatly reduce the memory consumption by using a fixed feature embedder pre-trained on other domains, such scheme also results in a disparity between the two stages, leading to suboptimal classification accuracy. To address this issue, we propose that a bag-level classifier can be a good instance-level teacher. Based on this idea, we design Iteratively Coupled Multiple Instance Learning (ICMIL) to couple the embedder and the bag classifier at a low cost. ICMIL initially fix the patch embedder to train the bag classifier, followed by fixing the bag classifier to fine-tune the patch embedder. The refined embedder can then generate better representations in return, leading to a more accurate classifier for the next iteration. To realize more flexible and more effective embedder fine-tuning, we also introduce a teacher-student framework to efficiently distill the category knowledge in the bag classifier to help the instance-level embedder fine-tuning. Thorough experiments were conducted on four distinct datasets to validate the effectiveness of ICMIL. The experimental results consistently demonstrate that our method significantly improves the performance of existing MIL backbones, achieving state-of-the-art results. The code is available at: https://github.com/Dootmaan/ICMIL/tree/confidence_based
To generalize well, classifiers must learn to be invariant to nuisance transformations that do not alter an input's class. Many problems have "class-agnostic" nuisance transformations that apply similarly to all classes, such as lighting and background changes for image classification. Neural networks can learn these invariances given sufficient data, but many real-world datasets are heavily class imbalanced and contain only a few examples for most of the classes. We therefore pose the question: how well do neural networks transfer class-agnostic invariances learned from the large classes to the small ones? Through careful experimentation, we observe that invariance to class-agnostic transformations is still heavily dependent on class size, with the networks being much less invariant on smaller classes. This result holds even when using data balancing techniques, and suggests poor invariance transfer across classes. Our results provide one explanation for why classifiers generalize poorly on unbalanced and long-tailed distributions. Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks. Source code for our experiments is available at https://github.com/AllanYangZhou/generative-invariance-transfer.
Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopathology tissues under different magnifications, most methods do not incorporate multiple resolutions of the WSIs, hierarchically and attentively, thereby leading to a loss of focus on the WSIs and information from other resolutions. To resolve this issue, we propose a Hierarchical Attention-Guided Multiple Instance Learning framework to fully exploit the WSIs. This framework can dynamically and attentively discover the discriminative regions across multiple resolutions of the WSIs. Within this framework, an Integrated Attention Transformer is proposed to further enhance the performance of the transformer and obtain a more holistic WSI (bag) representation. This transformer consists of multiple Integrated Attention Modules, which is the combination of a transformer layer and an aggregation module that produces a bag representation based on every instance representation in that bag. The experimental results show that our method achieved state-of-the-art performances on multiple datasets, including Camelyon16, TCGA-RCC, TCGA-NSCLC, and an in-house IMGC dataset. The code is available at https://github.com/BearCleverProud/HAG-MIL.
The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of unlabeled images. In contrast, we aim to learn high-quality visual representations from fewer images. To this end, we revisit supervised pretraining, and seek data-efficient alternatives to classification-based pretraining. We propose VirTex -- a pretraining approach using semantically dense captions to learn visual representations. We train convolutional networks from scratch on COCO Captions, and transfer them to downstream recognition tasks including image classification, object detection, and instance segmentation. On all tasks, VirTex yields features that match or exceed those learned on ImageNet -- supervised or unsupervised -- despite using up to ten times fewer images.
Consistently high data quality is essential for the development of novel loss functions and architectures in the field of deep learning. The existence of such data and labels is usually presumed, while acquiring high-quality datasets is still a major issue in many cases. In real-world datasets we often encounter ambiguous labels due to subjective annotations by annotators. In our data-centric approach, we propose a method to relabel such ambiguous labels instead of implementing the handling of this issue in a neural network. A hard classification is by definition not enough to capture the real-world ambiguity of the data. Therefore, we propose our method "Data-Centric Classification & Clustering (DC3)" which combines semi-supervised classification and clustering. It automatically estimates the ambiguity of an image and performs a classification or clustering depending on that ambiguity. DC3 is general in nature so that it can be used in addition to many Semi-Supervised Learning (SSL) algorithms. On average, this results in a 7.6% better F1-Score for classifications and 7.9% lower inner distance of clusters across multiple evaluated SSL algorithms and datasets. Most importantly, we give a proof-of-concept that the classifications and clusterings from DC3 are beneficial as proposals for the manual refinement of such ambiguous labels. Overall, a combination of SSL with our method DC3 can lead to better handling of ambiguous labels during the annotation process.
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt image features between video frames using a keypoint bottleneck. The discovered keypoints track objects and object parts across long time-horizons more accurately than recent similar methods. Furthermore, consistent long-term tracking enables two notable results in control domains -- (1) using the keypoint co-ordinates and corresponding image features as inputs enables highly sample-efficient reinforcement learning; (2) learning to explore by controlling keypoint locations drastically reduces the search space, enabling deep exploration (leading to states unreachable through random action exploration) without any extrinsic rewards.
The long-tailed distribution is a common phenomenon in the real world. Extracted large scale image datasets inevitably demonstrate the long-tailed property and models trained with imbalanced data can obtain high performance for the over-represented categories, but struggle for the under-represented categories, leading to biased predictions and performance degradation. To address this challenge, we propose a novel de-biasing method named Inverse Image Frequency (IIF). IIF is a multiplicative margin adjustment transformation of the logits in the classification layer of a convolutional neural network. Our method achieves stronger performance than similar works and it is especially useful for downstream tasks such as long-tailed instance segmentation as it produces fewer false positive detections. Our extensive experiments show that IIF surpasses the state of the art on many long-tailed benchmarks such as ImageNet-LT, CIFAR-LT, Places-LT and LVIS, reaching 55.8% top-1 accuracy with ResNet50 on ImageNet-LT and 26.2% segmentation AP with MaskRCNN on LVIS. Code available at https://github.com/kostas1515/iif
Hyperspectral images provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands) with continuous spectral information that can accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to the conventional techniques (the so-called curse of dimensionality) for accurate analysis of hyperspectral images. Feature extraction, as a vibrant field of research in the hyperspectral community, evolved through decades of research to address this issue and extract informative features suitable for data representation and classification. The advances in feature extraction have been inspired by two fields of research, including the popularization of image and signal processing as well as machine (deep) learning, leading to two types of feature extraction approaches named shallow and deep techniques. This article outlines the advances in feature extraction approaches for hyperspectral imagery by providing a technical overview of the state-of-the-art techniques, providing useful entry points for researchers at different levels, including students, researchers, and senior researchers, willing to explore novel investigations on this challenging topic. In more detail, this paper provides a bird's eye view over shallow (both supervised and unsupervised) and deep feature extraction approaches specifically dedicated to the topic of hyperspectral feature extraction and its application on hyperspectral image classification. Additionally, this paper compares 15 advanced techniques with an emphasis on their methodological foundations in terms of classification accuracies. Furthermore, the codes and libraries are shared at https://github.com/BehnoodRasti/HyFTech-Hyperspectral-Shallow-Deep-Feature-Extraction-Toolbox.
Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the input. To understand how a network manages to solve a problem we must look at the articulated decisions in entirety. If we could capture the actions of non-linear units for a particular input, we would be able to replay the whole system back and forth as if it was always linear. It would also reveal the actions of non-linearities because the resulting linear system, a Linear Interpreter, depends on the input image. We introduce a hooking layer, called a LinearScope, which allows us to run the network and the linear interpreter in parallel. Its implementation is simple, flexible and efficient. From here we can make many curious inquiries: how do these linear systems look like? When the rows and columns of the transformation matrix are images, how do they look like? What type of basis do these linear transformations rely on? The answers depend on the problems presented, through which we take a tour to some popular architectures used for classification, super-resolution (SR) and image-to-image translation (I2I). For classification we observe that popular networks use a pixel-wise vote per class strategy and heavily rely on bias parameters. For SR and I2I we find that CNNs use wavelet-type basis similar to the human visual system. For I2I we reveal copy-move and template-creation strategies to generate outputs.
Deep Learning as a field has been successfully used to solve a plethora of complex problems, the likes of which we could not have imagined a few decades back. But as many benefits as it brings, there are still ways in which it can be used to bring harm to our society. Deep fakes have been proven to be one such problem, and now more than ever, when any individual can create a fake image or video simply using an application on the smartphone, there need to be some countermeasures, with which we can detect if the image or video is a fake or real and dispose of the problem threatening the trustworthiness of online information. Although the Deep fakes created by neural networks, may seem to be as real as a real image or video, it still leaves behind spatial and temporal traces or signatures after moderation, these signatures while being invisible to a human eye can be detected with the help of a neural network trained to specialize in Deep fake detection. In this paper, we analyze several such states of the art neural networks (MesoNet, ResNet-50, VGG-19, and Xception Net) and compare them against each other, to find an optimal solution for various scenarios like real-time deep fake detection to be deployed in online social media platforms where the classification should be made as fast as possible or for a small news agency where the classification need not be in real-time but requires utmost accuracy.
This paper proposes a novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial feature from hyperspectral images (HSIs). In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it. Meanwhile, inspired from the widely used convolutional neural network (CNN), a convolution operator across the spatial domain is incorporated into the network to extract the spatial feature. Besides, to sufficiently capture the spectral information, a bidirectional recurrent connection is proposed. In the classification phase, the learned features are concatenated into a vector and fed to a softmax classifier via a fully-connected operator. To validate the effectiveness of the proposed Bi-CLSTM framework, we compare it with several state-of-the-art methods, including the CNN framework, on three widely used HSIs. The obtained results show that Bi-CLSTM can improve the classification performance as compared to other methods.
Visual (re)localization addresses the problem of estimating the 6-DoF (Degree of Freedom) camera pose of a query image captured in a known scene, which is a key building block of many computer vision and robotics applications. Recent advances in structure-based localization solve this problem by memorizing the mapping from image pixels to scene coordinates with neural networks to build 2D-3D correspondences for camera pose optimization. However, such memorization requires training by amounts of posed images in each scene, which is heavy and inefficient. On the contrary, few-shot images are usually sufficient to cover the main regions of a scene for a human operator to perform visual localization. In this paper, we propose a scene region classification approach to achieve fast and effective scene memorization with few-shot images. Our insight is leveraging a) pre-learned feature extractor, b) scene region classifier, and c) meta-learning strategy to accelerate training while mitigating overfitting. We evaluate our method on both indoor and outdoor benchmarks. The experiments validate the effectiveness of our method in the few-shot setting, and the training time is significantly reduced to only a few minutes. Code available at: \url{https://github.com/siyandong/SRC}
Transferring knowledge from a source domain to a target domain can be crucial for whole slide image classification, since the number of samples in a dataset is often limited due to high annotation costs. However, domain shift and task discrepancy between datasets can hinder effective knowledge transfer. In this paper, we propose a Target-Aware Knowledge Transfer framework, employing a teacher-student paradigm. Our framework enables the teacher model to learn common knowledge from the source and target domains by actively incorporating unlabelled target images into the training of the teacher model. The teacher bag features are subsequently adapted to supervise the training of the student model on the target domain. Despite incorporating the target features during training, the teacher model tends to overlook them under the inherent domain shift and task discrepancy. To alleviate this, we introduce a target-aware feature alignment module to establish a transferable latent relationship between the source and target features by solving the optimal transport problem. Experimental results show that models employing knowledge transfer outperform those trained from scratch, and our method achieves state-of-the-art performance among other knowledge transfer methods on various datasets, including TCGA-RCC, TCGA-NSCLC, and Camelyon16.