Recent work has shown that the attention maps of Vision Transformers (VTs), when trained with self-supervision, can contain a semantic segmentation structure which does not spontaneously emerge when training is supervised. In this paper, we explicitly encourage the emergence of this spatial clustering as a form of training regularization, this way including a self-supervised pretext task into the standard supervised learning. In more detail, we propose a VT regularization method based on a spatial formulation of the information entropy. By minimizing the proposed spatial entropy, we explicitly ask the VT to produce spatially ordered attention maps, this way including an object-based prior during training. Using extensive experiments, we show that the proposed regularization approach is beneficial with different training scenarios, datasets, downstream tasks and VT architectures. The code will be available upon acceptance.
相關內容
In recent past, several domain generalization (DG) methods have been proposed, showing encouraging performance, however, almost all of them build on convolutional neural networks (CNNs). There is little to no progress on studying the DG performance of vision transformers (ViTs), which are challenging the supremacy of CNNs on standard benchmarks, often built on i.i.d assumption. This renders the real-world deployment of ViTs doubtful. In this paper, we attempt to explore ViTs towards addressing the DG problem. Similar to CNNs, ViTs also struggle in out-of-distribution scenarios and the main culprit is overfitting to source domains. Inspired by the modular architecture of ViTs, we propose a simple DG approach for ViTs, coined as self-distillation for ViTs. It reduces the overfitting to source domains by easing the learning of input-output mapping problem through curating non-zero entropy supervisory signals for intermediate transformer blocks. Further, it does not introduce any new parameters and can be seamlessly plugged into the modular composition of different ViTs. We empirically demonstrate notable performance gains with different DG baselines and various ViT backbones in five challenging datasets. Moreover, we report favorable performance against recent state-of-the-art DG methods. Our code along with pre-trained models are publicly available at: //github.com/maryam089/SDViT
Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions
Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the problem of weakly-supervised fine-grained temporal action detection in videos for the first time. Without the careful design to capture subtle differences between fine-grained actions, previous weakly-supervised models for general action detection cannot perform well in the fine-grained setting. We propose to model actions as the combinations of reusable atomic actions which are automatically discovered from data through self-supervised clustering, in order to capture the commonality and individuality of fine-grained actions. The learnt atomic actions, represented by visual concepts, are further mapped to fine and coarse action labels leveraging the semantic label hierarchy. Our approach constructs a visual representation hierarchy of four levels: clip level, atomic action level, fine action class level and coarse action class level, with supervision at each level. Extensive experiments on two large-scale fine-grained video datasets, FineAction and FineGym, show the benefit of our proposed weakly-supervised model for fine-grained action detection, and it achieves state-of-the-art results.
This paper studies category-level object pose estimation based on a single monocular image. Recent advances in pose-aware generative models have paved the way for addressing this challenging task using analysis-by-synthesis. The idea is to sequentially update a set of latent variables, e.g., pose, shape, and appearance, of the generative model until the generated image best agrees with the observation. However, convergence and efficiency are two challenges of this inference procedure. In this paper, we take a deeper look at the inference of analysis-by-synthesis from the perspective of visual navigation, and investigate what is a good navigation policy for this specific task. We evaluate three different strategies, including gradient descent, reinforcement learning and imitation learning, via thorough comparisons in terms of convergence, robustness and efficiency. Moreover, we show that a simple hybrid approach leads to an effective and efficient solution. We further compare these strategies to state-of-the-art methods, and demonstrate superior performance on synthetic and real-world datasets leveraging off-the-shelf pose-aware generative models.
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out on a joint solution. Transformers recently allowed to cast the entire VIS task as a single set-prediction problem. Nevertheless, the quadratic complexity of existing Transformer-based methods requires long training times, high memory requirements, and processing of low-single-scale feature maps. Deformable attention provides a more efficient alternative but its application to the temporal domain or the segmentation task have not yet been explored. In this work, we present Deformable VIS (DeVIS), a VIS method which capitalizes on the efficiency and performance of deformable Transformers. To reason about all VIS subtasks jointly over multiple frames, we present temporal multi-scale deformable attention with instance-aware object queries. We further introduce a new image and video instance mask head with multi-scale features, and perform near-online video processing with multi-cue clip tracking. DeVIS reduces memory as well as training time requirements, and achieves state-of-the-art results on the YouTube-VIS 2021, as well as the challenging OVIS dataset. Code is available at //github.com/acaelles97/DeVIS.
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video understanding, it is non-trivial to design an efficient architecture for action detection due to the prohibitively expensive self-attentions over a long sequence of video clips. To this end, we present an efficient hierarchical Spatio-Temporal Pyramid Transformer (STPT) for action detection, building upon the fact that the early self-attention layers in Transformers still focus on local patterns. Specifically, we propose to use local window attention to encode rich local spatio-temporal representations in the early stages while applying global attention modules to capture long-term space-time dependencies in the later stages. In this way, our STPT can encode both locality and dependency with largely reduced redundancy, delivering a promising trade-off between accuracy and efficiency. For example, with only RGB input, the proposed STPT achieves 53.6% mAP on THUMOS14, surpassing I3D+AFSD RGB model by over 10% and performing favorably against state-of-the-art AFSD that uses additional flow features with 31% fewer GFLOPs, which serves as an effective and efficient end-to-end Transformer-based framework for action detection.
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage the advantage of self-attention in visual Transformer for long-range dependency to re-active semantic regions, aiming to avoid partial activation in traditional class activation mapping (CAM). However, the long-range modeling in Transformer neglects the inherent spatial coherence of the object, and it usually diffuses the semantic-aware regions far from the object boundary, making localization results significantly larger or far smaller. To address such an issue, we introduce a simple yet effective Spatial Calibration Module (SCM) for accurate WSOL, incorporating semantic similarities of patch tokens and their spatial relationships into a unified diffusion model. Specifically, we introduce a learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation. In practice, SCM is designed as an external module of Transformer, and can be removed during inference to reduce the computation cost. The object-sensitive localization ability is implicitly embedded into the Transformer encoder through optimization in the training phase. It enables the generated attention maps to capture the sharper object boundaries and filter the object-irrelevant background area. Extensive experimental results demonstrate the effectiveness of the proposed method, which significantly outperforms its counterpart TS-CAM on both CUB-200 and ImageNet-1K benchmarks. The code is available at //github.com/164140757/SCM.
Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative triple extraction may struggle to capture long-term dependencies and generate unfaithful triples, we introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object. Moreover, we introduce two mechanisms to further improve model performance (i.e., batch-wise dynamic attention-masking and triple-wise calibration). Experimental results on three datasets (i.e., NYT, WebNLG, and MIE) show that our approach achieves better performance than that of baselines.
Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently, vision transformer has shown excellent capability in capturing long-range dependencies. Inspired by this, we propose a novel transformer-based edge detector, \emph{Edge Detection TransformER (EDTER)}, to extract clear and crisp object boundaries and meaningful edges by exploiting the full image context information and detailed local cues simultaneously. EDTER works in two stages. In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches. Then in Stage II, a local transformer encoder works on fine-grained patches to excavate the short-range local cues. Each transformer encoder is followed by an elaborately designed Bi-directional Multi-Level Aggregation decoder to achieve high-resolution features. Finally, the global context and local cues are combined by a Feature Fusion Module and fed into a decision head for edge prediction. Extensive experiments on BSDS500, NYUDv2, and Multicue demonstrate the superiority of EDTER in comparison with state-of-the-arts.
Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are already the methods of choice. The recent literature suggests that the transformers are becoming increasingly popular also in computer vision. So far, the vision transformers have been shown to work well when pretrained either using a large scale supervised data or with some kind of co-supervision, e.g. in terms of teacher network. These supervised pretrained vision transformers achieve very good results in downstream tasks with minimal changes. In this work we investigate the merits of self-supervised learning for pretraining image/vision transformers and then using them for downstream classification tasks. We propose Self-supervised vIsion Transformers (SiT) and discuss several self-supervised training mechanisms to obtain a pretext model. The architectural flexibility of SiT allows us to use it as an autoencoder and work with multiple self-supervised tasks seamlessly. We show that a pretrained SiT can be finetuned for a downstream classification task on small scale datasets, consisting of a few thousand images rather than several millions. The proposed approach is evaluated on standard datasets using common protocols. The results demonstrate the strength of the transformers and their suitability for self-supervised learning. We outperformed existing self-supervised learning methods by large margin. We also observed that SiT is good for few shot learning and also showed that it is learning useful representation by simply training a linear classifier on top of the learned features from SiT. Pretraining, finetuning, and evaluation codes will be available under: //github.com/Sara-Ahmed/SiT.
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.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191