Patch-based models, e.g., Vision Transformers (ViTs) and Mixers, have shown impressive results on various visual recognition tasks, alternating classic convolutional networks. While the initial patch-based models (ViTs) treated all patches equally, recent studies reveal that incorporating inductive bias like spatiality benefits the representations. However, most prior works solely focused on the location of patches, overlooking the scene structure of images. Thus, we aim to further guide the interaction of patches using the object information. Specifically, we propose OAMixer (object-aware mixing layer), which calibrates the patch mixing layers of patch-based models based on the object labels. Here, we obtain the object labels in unsupervised or weakly-supervised manners, i.e., no additional human-annotating cost is necessary. Using the object labels, OAMixer computes a reweighting mask with a learnable scale parameter that intensifies the interaction of patches containing similar objects and applies the mask to the patch mixing layers. By learning an object-centric representation, we demonstrate that OAMixer improves the classification accuracy and background robustness of various patch-based models, including ViTs, MLP-Mixers, and ConvMixers. Moreover, we show that OAMixer enhances various downstream tasks, including large-scale classification, self-supervised learning, and multi-object recognition, verifying the generic applicability of OAMixer
相關內容
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers inferior performance on dense predictions due to weak prior assumptions. To address this issue, we propose the ViT-Adapter, which allows plain ViT to achieve comparable performance to vision-specific transformers. Specifically, the backbone in our framework is a plain ViT that can learn powerful representations from large-scale multi-modal data. When transferring to downstream tasks, a pre-training-free adapter is used to introduce the image-related inductive biases into the model, making it suitable for these tasks. We verify ViT-Adapter on multiple dense prediction tasks, including object detection, instance segmentation, and semantic segmentation. Notably, without using extra detection data, our ViT-Adapter-L yields state-of-the-art 60.9 box AP and 53.0 mask AP on COCO test-dev. We hope that the ViT-Adapter could serve as an alternative for vision-specific transformers and facilitate future research. The code and models will be released at //github.com/czczup/ViT-Adapter.
Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.
Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also triggered great interest in the time series community. Among multiple advantages of Transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review Transformer schemes for time series modeling by highlighting their strengths as well as limitations. In particular, we examine the development of time series Transformers in two perspectives. From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis. From the perspective of applications, we categorize time series Transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance. A corresponding resource that has been continuously updated can be found in the GitHub repository. To the best of our knowledge, this paper is the first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data. We hope this survey will ignite further research interests in time series Transformers.
More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information. Motivated by this, we devise a cross-layer attention mechanism, called multi-head recurrent layer attention (MRLA), that sends a query representation of the current layer to all previous layers to retrieve query-related information from different levels of receptive fields. A light-weighted version of MRLA is also proposed to reduce the quadratic computation cost. The proposed layer attention mechanism can enrich the representation power of many state-of-the-art vision networks, including CNNs and vision transformers. Its effectiveness has been extensively evaluated in image classification, object detection and instance segmentation tasks, where improvements can be consistently observed. For example, our MRLA can improve 1.6% Top-1 accuracy on ResNet-50, while only introducing 0.16M parameters and 0.07B FLOPs. Surprisingly, it can boost the performances by a large margin of 3-4% box AP and mask AP in dense prediction tasks. Our code is available at //github.com/joyfang1106/MRLA.
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. First, we develop an asymmetric encoder-decoder architecture, with an encoder that operates only on the visible subset of patches (without mask tokens), along with a lightweight decoder that reconstructs the original image from the latent representation and mask tokens. Second, we find that masking a high proportion of the input image, e.g., 75%, yields a nontrivial and meaningful self-supervisory task. Coupling these two designs enables us to train large models efficiently and effectively: we accelerate training (by 3x or more) and improve accuracy. Our scalable approach allows for learning high-capacity models that generalize well: e.g., a vanilla ViT-Huge model achieves the best accuracy (87.8%) among methods that use only ImageNet-1K data. Transfer performance in downstream tasks outperforms supervised pre-training and shows promising scaling behavior.
In many visual systems, visual tracking often bases on RGB image sequences, in which some targets are invalid in low-light conditions, and tracking performance is thus affected significantly. Introducing other modalities such as depth and infrared data is an effective way to handle imaging limitations of individual sources, but multi-modal imaging platforms usually require elaborate designs and cannot be applied in many real-world applications at present. Near-infrared (NIR) imaging becomes an essential part of many surveillance cameras, whose imaging is switchable between RGB and NIR based on the light intensity. These two modalities are heterogeneous with very different visual properties and thus bring big challenges for visual tracking. However, existing works have not studied this challenging problem. In this work, we address the cross-modal object tracking problem and contribute a new video dataset, including 654 cross-modal image sequences with over 481K frames in total, and the average video length is more than 735 frames. To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process. It is plug-and-play and could thus be flexibly embedded into different tracking frameworks. Extensive experiments on the dataset are conducted, and we demonstrate the effectiveness of the proposed algorithm in two representative tracking frameworks against 17 state-of-the-art tracking methods. We will release the dataset for free academic usage, dataset download link and code will be released soon.
The canonical approach to video-and-language learning (e.g., video question answering) dictates a neural model to learn from offline-extracted dense video features from vision models and text features from language models. These feature extractors are trained independently and usually on tasks different from the target domains, rendering these fixed features sub-optimal for downstream tasks. Moreover, due to the high computational overload of dense video features, it is often difficult (or infeasible) to plug feature extractors directly into existing approaches for easy finetuning. To provide a remedy to this dilemma, we propose a generic framework ClipBERT that enables affordable end-to-end learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that ClipBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end-to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full-length videos, proving the proverbial less-is-more principle. Videos in the datasets are from considerably different domains and lengths, ranging from 3-second generic domain GIF videos to 180-second YouTube human activity videos, showing the generalization ability of our approach. Comprehensive ablation studies and thorough analyses are provided to dissect what factors lead to this success. Our code is publicly available at //github.com/jayleicn/ClipBERT
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at //github.com/redwang/DTGRM.
Object detection with transformers (DETR) reaches competitive performance with Faster R-CNN via a transformer encoder-decoder architecture. Inspired by the great success of pre-training transformers in natural language processing, we propose a pretext task named random query patch detection to unsupervisedly pre-train DETR (UP-DETR) for object detection. Specifically, we randomly crop patches from the given image and then feed them as queries to the decoder. The model is pre-trained to detect these query patches from the original image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade-off multi-task learning of classification and localization in the pretext task, we freeze the CNN backbone and propose a patch feature reconstruction branch which is jointly optimized with patch detection. (2) To perform multi-query localization, we introduce UP-DETR from single-query patch and extend it to multi-query patches with object query shuffle and attention mask. In our experiments, UP-DETR significantly boosts the performance of DETR with faster convergence and higher precision on PASCAL VOC and COCO datasets. The code will be available soon.
We study the problem of named entity recognition (NER) from electronic medical records, which is one of the most fundamental and critical problems for medical text mining. Medical records which are written by clinicians from different specialties usually contain quite different terminologies and writing styles. The difference of specialties and the cost of human annotation makes it particularly difficult to train a universal medical NER system. In this paper, we propose a label-aware double transfer learning framework (La-DTL) for cross-specialty NER, so that a medical NER system designed for one specialty could be conveniently applied to another one with minimal annotation efforts. The transferability is guaranteed by two components: (i) we propose label-aware MMD for feature representation transfer, and (ii) we perform parameter transfer with a theoretical upper bound which is also label aware. We conduct extensive experiments on 12 cross-specialty NER tasks. The experimental results demonstrate that La-DTL provides consistent accuracy improvement over strong baselines. Besides, the promising experimental results on non-medical NER scenarios indicate that La-DTL is potential to be seamlessly adapted to a wide range of NER tasks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191