Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of this issue. We found that a neural network tends to first under-fit the minor classes by classifying most of their data into the major classes in early training epochs. To correct these wrong predictions, the neural network then must focus on pushing features of minor class data across the decision boundaries between major and minor classes, leading to much larger gradients for features of minor classes. We argue that such an under-fitting phase over-emphasizes the competition between major and minor classes, hinders the neural network from learning the discriminative knowledge that can be generalized to test data, and eventually results in over-fitting. To address this issue, we propose a novel learning strategy to equalize the training progress across classes. We mix features of the major class data with those of other data in a mini-batch, intentionally weakening their features to prevent a neural network from fitting them first. We show that this strategy can largely balance the training accuracy and feature gradients across classes, effectively mitigating the under-fitting then over-fitting problem for minor class data. On several benchmark datasets, our approach achieves the state-of-the-art accuracy, especially for the challenging step-imbalanced cases.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task by introducing time-channel importance maps and exploiting the importance maps for learning the representations of incoming examples via knowledge distillation. We also incorporate a regularization scheme in our objective function, which encourages individual features obtained from different time steps in a video to be uncorrelated and eventually improves accuracy by alleviating catastrophic forgetting. We evaluate the proposed approach on brand-new splits of class-incremental action recognition benchmarks constructed upon the UCF101, HMDB51, and Something-Something V2 datasets, and demonstrate the effectiveness of our algorithm in comparison to the existing continual learning methods that are originally designed for image data.
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds Through Instance Multi-Level Contextual Referring
PDF ↗Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding through the grounding-by-matching strategy. In practice, our model first predicts the target category from the language descriptions using a simple language classification model. Then based on the category, our model sifts out a small number of instance candidates (usually less than 20) from the panoptic segmentation on point clouds. Thus, the non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals. Subsequently, for each candidate, we perform the multi-level contextual inference, i.e., referring from instance attribute perception, instance-to-instance relation perception, and instance-to-background global localization perception, respectively. Eventually, the most relevant candidate is selected and localized by ranking confidence scores, which are obtained by the cooperative holistic visual-language feature matching. Experiments confirm that our method outperforms previous state-of-the-arts on ScanRefer online benchmark (ranked 1st place) and Nr3D/Sr3D datasets.
Being able to learn dense semantic representations of images without supervision is an important problem in computer vision. However, despite its significance, this problem remains rather unexplored, with a few exceptions that considered unsupervised semantic segmentation on small-scale datasets with a narrow visual domain. In this paper, we make a first attempt to tackle the problem on datasets that have been traditionally utilized for the supervised case. To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings. This marks a large deviation from existing works that relied on proxy tasks or end-to-end clustering. Additionally, we argue about the importance of having a prior that contains information about objects, or their parts, and discuss several possibilities to obtain such a prior in an unsupervised manner. Experimental evaluation shows that our method comes with key advantages over existing works. First, the learned pixel embeddings can be directly clustered in semantic groups using K-Means on PASCAL. Under the fully unsupervised setting, there is no precedent in solving the semantic segmentation task on such a challenging benchmark. Second, our representations can improve over strong baselines when transferred to new datasets, e.g. COCO and DAVIS. The code is available.
Visual storytelling and story comprehension are uniquely human skills that play a central role in how we learn about and experience the world. Despite remarkable progress in recent years in synthesis of visual and textual content in isolation and learning effective joint visual-linguistic representations, existing systems still operate only at a superficial, factual level. With the goal of developing systems that are able to comprehend rich human-generated narratives, and co-create new stories, we introduce AESOP: a new dataset that captures the creative process associated with visual storytelling. Visual panels are composed of clip-art objects with specific attributes enabling a broad range of creative expression. Using AESOP, we propose foundational storytelling tasks that are generative variants of story cloze tests, to better measure the creative and causal reasoning ability required for visual storytelling. We further develop a generalized story completion framework that models stories as the co-evolution of visual and textual concepts. We benchmark the proposed approach with human baselines and evaluate using comprehensive qualitative and quantitative metrics. Our results highlight key insights related to the dataset, modelling and evaluation of visual storytelling for future research in this promising field of study.
Person re-identification (Re-ID) aims to match pedestrians under dis-joint cameras. Most Re-ID methods formulate it as visual representation learning and image search, and its accuracy is consequently affected greatly by the search space. Spatial-temporal information has been proven to be efficient to filter irrelevant negative samples and significantly improve Re-ID accuracy. However, existing spatial-temporal person Re-ID methods are still rough and do not exploit spatial-temporal information sufficiently. In this paper, we propose a novel instance-level and spatial-temporal disentangled Re-ID method (InSTD), to improve Re-ID accuracy. In our proposed framework, personalized information such as moving direction is explicitly considered to further narrow down the search space. Besides, the spatial-temporal transferring probability is disentangled from joint distribution to marginal distribution, so that outliers can also be well modeled. Abundant experimental analyses on two datasets are presented, which demonstrates the superiority and provides more insights into our method. The proposed method achieves mAP of 90.8% on Market-1501 and 89.1% on DukeMTMC-reID, improving from the baseline 82.2% and 72.7%, respectively. Besides, in order to provide a better benchmark for person re-identification, we release a cleaned data list of DukeMTMC-reID with this paper: https://github.com/RenMin1991/cleaned-DukeMTMC-reID.
As a representative of multiple kernel clustering (MKC), simple multiple kernel k-means (SimpleMKKM) is recently put forward to boosting the clustering performance by optimally fusing a group of pre-specified kernel matrices. Despite achieving significant improvement in a variety of applications, we find out that SimpleMKKM could indiscriminately force all sample pairs to be equally aligned with the same ideal similarity. As a result, it does not sufficiently take the variation of samples into consideration, leading to unsatisfying clustering performance. To address these issues, this paper proposes a novel MKC algorithm with a "local" kernel alignment, which only requires that the similarity of a sample to its k-nearest neighbours be aligned with the ideal similarity matrix. Such an alignment helps the clustering algorithm to focus on closer sample pairs that shall stay together and avoids involving unreliable similarity evaluation for farther sample pairs. After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix. Based on this observation, the proposed localized SimpleMKKM can be readily implemented by existing SimpleMKKM package. Moreover, we conduct extensive experiments on several widely used benchmark datasets to evaluate the clustering performance of localized SimpleMKKM. The experimental results have demonstrated that our algorithm consistently outperforms the state-of-the-art ones, verifying the effectiveness of the proposed local kernel alignment criterion. The code of Localized SimpleMKKM is publicly available at: https://github.com/xinwangliu/LocalizedSMKKM.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
PDF ↗This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a classification loss and utilizes a top-down attention mechanism to enhance the separability of latent foreground-background embeddings. The denoising loss term explicitly addresses the foreground-background noise in class activations by simultaneously maximizing intra-video and inter-video mutual information using a bottom-up attention mechanism. As a result, activations in the foreground regions are emphasized whereas those in the background regions are suppressed, thereby leading to more robust predictions. Comprehensive experiments are performed on multiple benchmarks, including THUMOS14 and ActivityNet1.2. Our D2-Net performs favorably in comparison to the existing methods on all datasets, achieving gains as high as 2.3% in terms of mAP at IoU=0.5 on THUMOS14. Source code is available at https://github.com/naraysa/D2-Net.
Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. Even though growing efforts have been devoted to cross-view recognition, academia is restricted by current existing databases captured in the controlled environment. In this paper, we contribute a new benchmark for Gait REcognition in the Wild (GREW). The GREW dataset is constructed from natural videos, which contains hundreds of cameras and thousands of hours streams in open systems. With tremendous manual annotations, the GREW consists of 26K identities and 128K sequences with rich attributes for unconstrained gait recognition. Moreover, we add a distractor set of over 233K sequences, making it more suitable for real-world applications. Compared with prevailing predefined cross-view datasets, the GREW has diverse and practical view variations, as well as more natural challenging factors. To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild. Equipped with this benchmark, we dissect the unconstrained gait recognition problem. Representative appearance-based and model-based methods are explored, and comprehensive baselines are established. Experimental results show (1) The proposed GREW benchmark is necessary for training and evaluating gait recognizer in the wild. (2) For state-of-the-art gait recognition approaches, there is a lot of room for improvement. (3) The GREW benchmark can be used as effective pre-training for controlled gait recognition. Benchmark website is https://www.grew-benchmark.org/.
The field of face recognition (FR) has witnessed remarkable progress with the surge of deep learning. The effective loss functions play an important role for FR. In this paper, we observe that a majority of loss functions, including the widespread triplet loss and softmax-based cross-entropy loss, embed inter-class (negative) similarity s_n and intra-class (positive) similarity s_p into similarity pairs and optimize to reduce (s_n - s_p) in the training process. However, in the verification process, existing metrics directly take the absolute similarity between two features as the confidence of belonging to the same identity, which inevitably causes a gap between the training and verification process. To bridge the gap, we propose a new metric called Discrepancy Alignment Metric (DAM) for verification, which introduces the Local Inter-class Discrepancy (LID) for each face image to normalize the absolute similarity score. To estimate the LID of each face image in the verification process, we propose two types of LID Estimation (LIDE) methods, which are reference-based and learning-based estimation methods, respectively. The proposed DAM is plug-and-play and can be easily applied to the most existing methods. Extensive experiments on multiple popular face recognition benchmark datasets demonstrate the effectiveness of our proposed method.
Research in media forensics has gained traction to combat the spread of misinformation. However, most of this research has been directed towards content generated on social media. Biomedical image forensics is a related problem, where manipulation or misuse of images reported in biomedical research documents is of serious concern. The problem has failed to gain momentum beyond an academic discussion due to an absence of benchmark datasets and standardized tasks. In this paper we present BioFors -- the first dataset for benchmarking common biomedical image manipulations. BioFors comprises 47,805 images extracted from 1,031 open-source research papers. Images in BioFors are divided into four categories -- Microscopy, Blot/Gel, FACS and Macroscopy. We also propose three tasks for forensic analysis -- external duplication detection, internal duplication detection and cut/sharp-transition detection. We benchmark BioFors on all tasks with suitable state-of-the-art algorithms. Our results and analysis show that existing algorithms developed on common computer vision datasets are not robust when applied to biomedical images, validating that more research is required to address the unique challenges of biomedical image forensics.
Editing an image automatically via a linguistic request can significantly save laborious manual work and is friendly to photography novice. In this paper, we focus on the task of language-guided global image editing. Existing works suffer from imbalanced data distribution of real-world datasets and thus fail to understand language requests well. To handle this issue, we propose to create a cycle with our image generator by creating another model called Editing Description Network (EDNet) which predicts an editing embedding given a pair of images. Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset. In addition, two other novel ideas are proposed: an Image-Request Attention (IRA) module which allows our method to edit an image spatial-adaptively when the image requires different editing degree at different regions, as well as a new evaluation metric for this task which is more semantic and reasonable than conventional pixel losses (eg L1). Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method over existing approaches.
Occluded person re-identification (ReID) aims at re-identifying occluded pedestrians from occluded or holistic images taken across multiple cameras. Current state-of-the-art (SOTA) occluded ReID models rely on some auxiliary modules, including pose estimation, feature pyramid and graph matching modules, to learn multi-scale and/or part-level features to tackle the occlusion challenges. This unfortunately leads to complex ReID models that (i) fail to generalize to challenging occlusions of diverse appearance, shape or size, and (ii) become ineffective in handling non-occluded pedestrians. However, real-world ReID applications typically have highly diverse occlusions and involve a hybrid of occluded and non-occluded pedestrians. To address these two issues, we introduce a novel ReID model that learns discriminative single-scale global-level pedestrian features by enforcing a novel exponentially sensitive yet bounded distance loss on occlusion-based augmented data. We show for the first time that learning single-scale global features without using these auxiliary modules is able to outperform those SOTA multi-scale and/or part-level feature-based models. Further, our simple model can achieve new SOTA performance in both occluded and non-occluded ReID, as shown by extensive results on three occluded and two general ReID benchmarks. Additionally, we create a large-scale occluded person ReID dataset with both indoor and outdoor occlusions in different scenes, which is significantly larger and contains substantially more diverse occlusions and pedestrian dressings than existing occluded ReID datasets, providing a more faithful occluded ReID benchmark.
Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark
PDF ↗Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime benchmarks. However, they produce weird outputs in more challenging nighttime scenarios because of low visibility and varying illuminations, which bring weak textures and break brightness-consistency assumption, respectively. To address these problems, in this paper we propose a novel framework with several improvements: (1) we introduce Priors-Based Regularization to learn distribution knowledge from unpaired depth maps and prevent model from being incorrectly trained; (2) we leverage Mapping-Consistent Image Enhancement module to enhance image visibility and contrast while maintaining brightness consistency; and (3) we present Statistics-Based Mask strategy to tune the number of removed pixels within textureless regions, using dynamic statistics. Experimental results demonstrate the effectiveness of each component. Meanwhile, our framework achieves remarkable improvements and state-of-the-art results on two nighttime datasets.
Class-incremental learning (CIL) aims at continuously updating a trained model with new classes (plasticity) without forgetting previously learned old ones (stability). Contemporary studies resort to storing representative exemplars for rehearsal or preventing consolidated model parameters from drifting, but the former requires an additional space for storing exemplars at every incremental phase while the latter usually shows poor model generalization. In this paper, we focus on resolving the stability-plasticity dilemma in class-incremental learning where no exemplars from old classes are stored. To make a trade-off between learning new information and maintaining old knowledge, we reformulate a simple yet effective baseline method based on a cosine classifier framework and reciprocal adaptive weights. With the reformulated baseline, we present two new approaches to CIL by learning class-independent knowledge and multi-perspective knowledge, respectively. The former exploits class-independent knowledge to bridge learning new and old classes, while the latter learns knowledge from different perspectives to facilitate CIL. Extensive experiments on several widely used CIL benchmark datasets show the superiority of our approaches over the state-of-the-art methods.
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire test set is available concurrently, and semi-supervised learning, where more unlabeled data is available. Focusing on these two settings, we introduce a new algorithm that leverages the manifold structure of the labeled and unlabeled data distribution to predict pseudo-labels, while balancing over classes and using the loss value distribution of a limited-capacity classifier to select the cleanest labels, iteratively improving the quality of pseudo-labels. Our solution surpasses or matches the state of the art results on four benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS, while being robust over feature space pre-processing and the quantity of available data. The publicly available source code can be found in https://github.com/MichalisLazarou/iLPC
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent studies have successfully discretized a full-precision network, they still incur large quantization errors after training, thus giving rise to a significant performance gap between a full-precision network and its quantized counterpart. In this work, we propose a novel quantization method for neural networks, Cluster-Promoting Quantization (CPQ) that finds the optimal quantization grids while naturally encouraging the underlying full-precision weights to gather around those quantization grids cohesively during training. This property of CPQ is thanks to our two main ingredients that enable differentiable quantization: i) the use of the categorical distribution designed by a specific probabilistic parametrization in the forward pass and ii) our proposed multi-class straight-through estimator (STE) in the backward pass. Since our second component, multi-class STE, is intrinsically biased, we additionally propose a new bit-drop technique, DropBits, that revises the standard dropout regularization to randomly drop bits instead of neurons. As a natural extension of DropBits, we further introduce the way of learning heterogeneous quantization levels to find proper bit-length for each layer by imposing an additional regularization on DropBits. We experimentally validate our method on various benchmark datasets and network architectures, and also support a new hypothesis for quantization: learning heterogeneous quantization levels outperforms the case using the same but fixed quantization levels from scratch.
Time-to-event analysis is an important statistical tool for allocating clinical resources such as ICU beds. However, classical techniques like the Cox model cannot directly incorporate images due to their high dimensionality. We propose a deep learning approach that naturally incorporates multiple, time-dependent imaging studies as well as non-imaging data into time-to-event analysis. Our techniques are benchmarked on a clinical dataset of 1,894 COVID-19 patients, and show that image sequences significantly improve predictions. For example, classical time-to-event methods produce a concordance error of around 30-40% for predicting hospital admission, while our error is 25% without images and 20% with multiple X-rays included. Ablation studies suggest that our models are not learning spurious features such as scanner artifacts. While our focus and evaluation is on COVID-19, the methods we develop are broadly applicable.
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in undesirable ways. In this work, we study bias propagation pathways within image captioning, focusing specifically on the COCO dataset. Prior work has analyzed gender bias in captions using automatically-derived gender labels; here we examine racial and intersectional biases using manual annotations. Our first contribution is in annotating the perceived gender and skin color of 28,315 of the depicted people after obtaining IRB approval. Using these annotations, we compare racial biases present in both manual and automatically-generated image captions. We demonstrate differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people. Further, we find the magnitude of these differences to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Code and data is available at https://princetonvisualai.github.io/imagecaptioning-bias/.
We propose a novel approach that integrates under-parameterized RANSAC (UPRANSAC) with Hough Transform to detect vanishing points (VPs) from un-calibrated monocular images. In our algorithm, the UPRANSAC chooses one hypothetical inlier in a sample set to find a portion of the VP's degrees of freedom, which is followed by a highly reliable brute-force voting scheme (1-D Hough Transform) to find the VP's remaining degrees of freedom along the extension line of the hypothetical inlier. Our approach is able to sequentially find a series of VPs by repeatedly removing inliers of any detected VPs from minimal sample sets until the stop criterion is reached. Compared to traditional RANSAC that selects 2 edges as a hypothetical inlier pair to fit a model of VP hypothesis and requires hitting a pair of inliners, the UPRANSAC has a higher likelihood to hit one inliner and is more reliable in VP detection. Meanwhile, the tremendously scaled-down voting space with the requirement of only 1 parameter for processing significantly increased the performance efficiency of Hough Transform in our scheme. Testing results with well-known benchmark datasets show that the detection accuracies of our approach were higher or on par with the SOTA while running in deeply real-time zone.