The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training objective. In this paper, we propose PreSTU, a novel pre-training recipe dedicated to scene-text understanding (STU). PreSTU introduces OCR-aware pre-training objectives that encourage the model to recognize text from an image and connect it to the rest of the image content. We implement PreSTU using a simple transformer-based encoder-decoder architecture, combined with large-scale image-text datasets with scene text obtained from an off-the-shelf OCR system. We empirically demonstrate the effectiveness of this pre-training approach on eight visual question answering and four image captioning benchmarks.
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 introduce the Aria Digital Twin (ADT) - an egocentric dataset captured using Aria glasses with extensive object, environment, and human level ground truth. This ADT release contains 200 sequences of real-world activities conducted by Aria wearers in two real indoor scenes with 398 object instances (344 stationary and 74 dynamic). Each sequence consists of: a) raw data of two monochrome camera streams, one RGB camera stream, two IMU streams; b) complete sensor calibration; c) ground truth data including continuous 6-degree-of-freedom (6DoF) poses of the Aria devices, object 6DoF poses, 3D eye gaze vectors, 3D human poses, 2D image segmentations, image depth maps; and d) photo-realistic synthetic renderings. To the best of our knowledge, there is no existing egocentric dataset with a level of accuracy, photo-realism and comprehensiveness comparable to ADT. By contributing ADT to the research community, our mission is to set a new standard for evaluation in the egocentric machine perception domain, which includes very challenging research problems such as 3D object detection and tracking, scene reconstruction and understanding, sim-to-real learning, human pose prediction - while also inspiring new machine perception tasks for augmented reality (AR) applications. To kick start exploration of the ADT research use cases, we evaluated several existing state-of-the-art methods for object detection, segmentation and image translation tasks that demonstrate the usefulness of ADT as a benchmarking dataset.
TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective
PDF ↗Vision Transformers (ViTs) have demonstrated powerful representation ability in various visual tasks thanks to their intrinsic data-hungry nature. However, we unexpectedly find that ViTs perform vulnerably when applied to face recognition (FR) scenarios with extremely large datasets. We investigate the reasons for this phenomenon and discover that the existing data augmentation approach and hard sample mining strategy are incompatible with ViTs-based FR backbone due to the lack of tailored consideration on preserving face structural information and leveraging each local token information. To remedy these problems, this paper proposes a superior FR model called TransFace, which employs a patch-level data augmentation strategy named DPAP and a hard sample mining strategy named EHSM. Specially, DPAP randomly perturbs the amplitude information of dominant patches to expand sample diversity, which effectively alleviates the overfitting problem in ViTs. EHSM utilizes the information entropy in the local tokens to dynamically adjust the importance weight of easy and hard samples during training, leading to a more stable prediction. Experiments on several benchmarks demonstrate the superiority of our TransFace. Code and models are available at https://github.com/DanJun6737/TransFace.
Relational Language-Image Pre-training (RLIP) aims to align vision representations with relational texts, thereby advancing the capability of relational reasoning in computer vision tasks. However, hindered by the slow convergence of RLIPv1 architecture and the limited availability of existing scene graph data, scaling RLIPv1 is challenging. In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data. To enable fast scaling, RLIPv2 introduces Asymmetric Language-Image Fusion (ALIF), a mechanism that facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding layers. ALIF leads to comparable or better performance than RLIPv1 in a fraction of the time for pre-training and fine-tuning. To obtain scene graph data at scale, we extend object detection datasets with free-form relation labels by introducing a captioner (e.g., BLIP) and a designed Relation Tagger. The Relation Tagger assigns BLIP-generated relation texts to region pairs, thus enabling larger-scale relational pre-training. Through extensive experiments conducted on Human-Object Interaction Detection and Scene Graph Generation, RLIPv2 shows state-of-the-art performance on three benchmarks under fully-finetuning, few-shot and zero-shot settings. Notably, the largest RLIPv2 achieves 23.29mAP on HICO-DET without any fine-tuning, yields 32.22mAP with just 1% data and yields 45.09mAP with 100% data. Code and models are publicly available at https://github.com/JacobYuan7/RLIPv2.
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded. However, source training can cause the model to overfit to source data distribution and lose applicable target domain knowledge. We propose to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization and provides an alternate view of features and classification decisions different from the source model. We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model. Evaluation on 4 benchmark datasets show that our proposed strategy improves adaptation performance and can be successfully integrated with existing SFDA methods. Leveraging modern pre-trained networks that have stronger representation learning ability in the co-learning strategy further boosts performance.
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
PDF ↗Most existing neural network pruning methods hand-crafted their importance criteria and structures to prune. This constructs heavy and unintended dependencies on heuristics and expert experience for both the objective and the parameters of the pruning approach. In this paper, we try to solve this problem by introducing a principled and unified framework based on Information Bottleneck (IB) theory, which further guides us to an automatic pruning approach. Specifically, we first formulate the channel pruning problem from an IB perspective, and then implement the IB principle by solving a Hilbert-Schmidt Independence Criterion (HSIC) Lasso problem under certain conditions. Based on the theoretical guidance, we then provide an automatic pruning scheme by searching for global penalty coefficients. Verified by extensive experiments, our method yields state-of-the-art performance on various benchmark networks and datasets. For example, with VGG-16, we achieve a 60%-FLOPs reduction by removing 76% of the parameters, with an improvement of 0.40% in top-1 accuracy on CIFAR-10. With ResNet-50, we achieve a 56%-FLOPs reduction by removing 50% of the parameters, with a small loss of 0.08% in the top-1 accuracy on ImageNet. The code is available at https://github.com/sunggo/APIB.
Crowd counting has recently attracted significant attention in the field of computer vision due to its wide applications to image understanding. Numerous methods have been proposed and achieved state-of-the-art performance for real-world tasks. However, existing approaches do not perform well under adverse weather such as haze, rain, and snow since the visual appearances of crowds in such scenes are drastically different from those images in clear weather of typical datasets. In this paper, we propose a method for robust crowd counting in adverse weather scenarios. Instead of using a two-stage approach that involves image restoration and crowd counting modules, our model learns effective features and adaptive queries to account for large appearance variations. With these weather queries, the proposed model can learn the weather information according to the degradation of the input image and optimize with the crowd counting module simultaneously. Experimental results show that the proposed algorithm is effective in counting crowds under different weather types on benchmark datasets. The source code and trained models will be made available to the public.
Novel view synthesis aims to render unseen views given a set of calibrated images. In practical applications, the coverage, appearance or geometry of the scene may change over time, with new images continuously being captured. Efficiently incorporating such continuous change is an open challenge. Standard NeRF benchmarks only involve scene coverage expansion. To study other practical scene changes, we propose a new dataset, World Across Time (WAT), consisting of scenes that change in appearance and geometry over time. We also propose a simple yet effective method, CLNeRF, which introduces continual learning (CL) to Neural Radiance Fields (NeRFs). CLNeRF combines generative replay and the Instant Neural Graphics Primitives (NGP) architecture to effectively prevent catastrophic forgetting and efficiently update the model when new data arrives. We also add trainable appearance and geometry embeddings to NGP, allowing a single compact model to handle complex scene changes. Without the need to store historical images, CLNeRF trained sequentially over multiple scans of a changing scene performs on-par with the upper bound model trained on all scans at once. Compared to other CL baselines CLNeRF performs much better across standard benchmarks and WAT. The source code, a demo, and the WAT dataset are available at https://github.com/IntelLabs/CLNeRF.
Smartphone photography is becoming increasingly popular, but fitting high-performing camera systems within the given space limitations remains a challenge for manufacturers. As a result, powerful mobile camera systems are in high demand. Despite recent progress in computer vision, camera system quality assessment remains a tedious and manual process. In this paper, we present the Smartphone Camera Quality Assessment Dataset (SQAD), which includes natural images captured by 29 devices. SQAD defines camera system quality based on six widely accepted criteria: resolution, color accuracy, noise level, dynamic range, Point Spread Function, and aliasing. Built on thorough examinations in a controlled laboratory environment, SQAD provides objective metrics for quality assessment, overcoming previous subjective opinion scores. Moreover, we introduce the task of automatic camera quality assessment and train deep learning-based models on the collected data to perform a precise quality prediction for arbitrary photos. The dataset, codes and pre-trained models are released at https://github.com/aiff22/SQAD.
HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation
PDF ↗Referring Video Object Segmentation (RVOS) is to segment the object instance from a given video, according to the textual description of this object. However, in the open world, the object descriptions are often diversified in contents and flexible in lengths. This leads to the key difficulty in RVOS, i.e., various descriptions of different ob- jects are corresponding to different temporal scales in the video, which is ignored by most existing approaches with single stride of frame sampling. To tackle this problem, we propose a concise Hybrid Temporal-scale Multimodal Learning (HTML) framework, which can effectively align lingual and visual features to discover core object semantics in the video, by learning multimodal interaction hierarchically from different temporal scales. More specifically, we introduce a novel inter-scale multimodal perception module, where the language queries dynamically interact with visual features across temporal scales. It can effectively reduce complex object confusion by passing video context among different scales. Finally, we conduct extensive experiments on the widely used benchmarks, including Ref- Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB- Sentences, where our HTML achieves state-of-the-art performance on all these datasets.
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task. We propose OFVL-MS, a unified framework that dispenses with the traditional practice of training a model for each individual scene and relieves gradient conflict induced by optimizing multiple scenes collectively, enabling efficient storage yet precise visual localization for all scenes. Technically, in the forward pass of OFVL-MS, we design a layer-adaptive sharing policy with a learnable score for each layer to automatically determine whether the layer is shared or not. Such sharing policy empowers us to acquire task-shared parameters for a reduction of storage cost and task-specific parameters for learning scene-related features to alleviate gradient conflict. In the backward pass of OFVL-MS, we introduce a gradient normalization algorithm that homogenizes the gradient magnitude of the task-shared parameters so that all tasks converge at the same pace. Furthermore, a sparse penalty loss is applied on the learnable scores to facilitate parameter sharing for all tasks without performance degradation. We conduct comprehensive experiments on multiple benchmarks and our new released indoor dataset LIVL, showing that OFVL-MS families significantly outperform the state-of-the-arts with fewer parameters. We also verify that OFVL-MS can generalize to a new scene with much few parameters while gaining superior localization performance. The proposed dataset and evaluation code is available at https://github.com/mooncake199809/UFVL-Net.
Few-shot classification aims to learn a discriminative feature representation to recognize unseen classes with few labeled support samples. While most few-shot learning methods focus on exploiting the spatial information of image samples, frequency representation has also been proven essential in classification tasks. In this paper, we investigate the effect of different frequency components on the few-shot learning tasks. To enhance the performance and generalizability of few-shot methods, we propose a novel Frequency-Guided Few-shot Learning framework (dubbed FGFL), which leverages the task-specific frequency components to adaptively mask the corresponding image information, with a novel multi-level metric learning strategy including a triplet loss among original, masked and unmasked image as well as a contrastive loss between masked and original support and query sets to exploit more discriminative information. Extensive experiments on four benchmarks under several few-shot scenarios, i.e., standard, cross-dataset, cross-domain, and coarse-to-fine annotated classification, are conducted. Both qualitative and quantitative results show that our proposed FGFL scheme can attend to the class-discriminative frequency components, thus integrating those information towards more effective and generalizable few-shot learning.
We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples. However, we show that this metric is unreliable, as even vacuous blind classifiers, which do not use input images for prediction, can achieve unrealistically high online accuracy by exploiting spurious label correlations in the data stream. Our study reveals that existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information, suggesting that they unintentionally learn spurious label correlations. To address this issue, we propose a novel metric for measuring adaptation based on the accuracy on the near-future samples, where spurious correlations are removed. We benchmark existing OCL approaches using our proposed metric on large-scale datasets under various computational budgets and find that better generalization can be achieved by retaining and reusing past seen information. We believe that our proposed metric can aid in the development of truly adaptive OCL methods. We provide code to reproduce our results at https://github.com/drimpossible/EvalOCL.
Deep learning based methods have become the de-facto standard for various computer vision tasks. Nevertheless, they have repeatedly shown their vulnerability to various form of input perturbations such as pixels modification, region anonymization, etc. which are closely related to the adversarial attacks. This research particularly addresses the case of image anonymization, which is significantly important to preserve privacy and hence to secure digitized form of personal information from being exposed and potentially misused by different services that have captured it for various purposes. However, applying anonymization causes the classifier to provide different class decisions before and after applying it and therefore reduces the classifier's reliability and usability. In order to achieve a robust solution to this problem we propose a novel anonymization procedure that allows the existing classifiers to become class decision invariant on the anonymized images without any modification requires to apply on the classification models. We conduct numerous experiments on the popular ImageNet benchmark as well as on a large scale industrial toll classification problem's dataset. Obtained results confirm the efficiency and effectiveness of the proposed method as it obtained 0% rate of class decision change for both datasets compared to 15.95% on ImageNet and 0.18% on toll dataset obtained by applying the naive anonymization approaches. Moreover, it has shown a great potential to be applied to similar problems from different domains.
Rethinking Safe Semi-supervised Learning: Transferring the Open-set Problem to A Close-set One
PDF ↗Conventional semi-supervised learning (SSL) lies in the close-set assumption that the labeled and unlabeled sets contain data with the same seen classes, called in-distribution (ID) data. In contrast, safe SSL investigates a more challenging open-set problem where unlabeled set may involve some out-of-distribution (OOD) data with unseen classes, which could harm the performance of SSL. When we are experimenting with the mainstream safe SSL methods, we have a surprising finding that all OOD data show a clear tendency to gather in the feature space. This inspires us to solve the safe SSL problem from a fresh perspective. Specifically, for a classification task with K seen classes, we utilize a prototype network not only to generate K prototypes of all seen classes, but also explicitly model an additional prototype for the OOD data, transferring the K-way classification on the open-set to the (K+1)-way on the close-set. In this way, the typical SSL techniques (e.g., consistency regularization and pseudo labeling) can be applied to tackle the safe SSL problem without additional consideration of OOD data processing like other safe SSL methods do. Particularly, considering the possible low-confidence pseudo labels, we further propose an iterative negative learning (INL) paradigm to enforce the network learning knowledge from complementary labels on wider classes, improving the network's classification performance. Extensive experiments on four benchmark datasets show that our approach remarkably lifts the performance on safe SSL and outperforms the state-of-the-art methods.
Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great effectiveness in transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes while failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes the inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.
Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can fail in unexpected ways. In this paper, we develop a framework that allows us to systematically identify spurious features in large datasets like ImageNet. It is based on our neural PCA components and their visualization. Previous work on spurious features often operates in toy settings or requires costly pixel-wise annotations. In contrast, we work with ImageNet and validate our results by showing that presence of the harmful spurious feature of a class alone is sufficient to trigger the prediction of that class. We introduce the novel dataset "Spurious ImageNet" which allows to measure the reliance of any ImageNet classifier on harmful spurious features. Moreover, we introduce SpuFix as a simple mitigation method to reduce the dependence of any ImageNet classifier on previously identified harmful spurious features without requiring additional labels or retraining of the model. We provide code and data at https://github.com/YanNeu/spurious_imagenet.
Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art few-shot image segmentation method that combines external support guidance information with adaptive query guidance cues, we propose to leverage multi-grained temporal guidance information for handling the temporal correlation nature of video data. We decompose the query video information into a clip prototype and a memory prototype for capturing local and long-term internal temporal guidance, respectively. Frame prototypes are further used for each frame independently to handle fine-grained adaptive guidance and enable bidirectional clip-frame prototype communication. To reduce the influence of noisy memory, we propose to leverage the structural similarity relation among different predicted regions and the support for selecting reliable memory frames. Furthermore, a new segmentation loss is also proposed to enhance the category discriminability of the learned prototypes. Experimental results demonstrate that our proposed video IPMT model significantly outperforms previous models on two benchmark datasets. Code is available at https://github.com/nankepan/VIPMT.
Current closed-set instance segmentation models rely on predefined class labels for each mask during training and evaluation, limiting their ability to detect novel objects. Open-world instance segmentation (OWIS) models address this challenge by detecting unknown objects in a class-agnostic manner. However, previous OWIS approaches completely erase category information during training to keep the model's ability to generalize to unknown objects. In this work, we propose a novel training mechanism called SegPrompt that utilizes category information to improve the model's class-agnostic segmentation ability for both known and unknown categories. In addition, the previous OWIS training setting exposes the unknown classes to the training set and brings information leakage, which is unreasonable in the real world. Therefore, we provide a new open-world benchmark closer to a real-world scenario by dividing the dataset classes into known-seen-unseen parts. For the first time we focus on the model's ability to discover objects that never appear in the training set images. Experiments show that SegPrompt can improve the overall and unseen detection performance by 5.6% and 6.1% in AR on our new benchmark without affecting the inference efficiency. We further demonstrate the effectiveness of our method on existing cross-dataset transfer and strongly supervised settings, leading to 5.5% and 12.3% relative improvement.
"A picture is worth a thousand words", significantly beyond mere a categorization. Accompanied by that, many patches of the image could have completely irrelevant meanings with the categorization if they were independently observed. This could significantly reduce the efficiency of a large family of few-shot learning algorithms, which have limited data and highly rely on the comparison of image patches. To address this issue, we propose a Class-aware Patch Embedding Adaptation (CPEA) method to learn "class-aware embeddings" of the image patches. The key idea of CPEA is to integrate patch embeddings with class-aware embeddings to make them class-relevant. Furthermore, we define a dense score matrix between class-relevant patch embeddings across images, based on which the degree of similarity between paired images is quantified. Visualization results show that CPEA concentrates patch embeddings by class, thus making them class-relevant. Extensive experiments on four benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and FC-100, indicate that our CPEA significantly outperforms the existing state-of-the-art methods. The source code is available at https://github.com/FushengHao/CPEA.