Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
281
0
0.0
(
0
)
Added by
Han Hu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and Faster R-CNN, center points in FCOS and RepPoints, and corner points in CornerNet. While these different representations usually drive the frameworks to perform well in different aspects, e.g., better classification or finer localization, it is in general difficult to combine these representations in a single framework to make good use of each strength, due to the heterogeneous or non-grid feature extraction by different representations. This paper presents an attention-based decoder module similar as that in Transformer~cite{vaswani2017attention} to bridge other representations into a typical object detector built on a single representation format, in an end-to-end fashion. The other representations act as a set of emph{key} instances to strengthen the main emph{query} representation features in the vanilla detectors. Novel techniques are proposed towards efficient computation of the decoder module, including a emph{key sampling} approach and a emph{shared location embedding} approach. The proposed module is named emph{bridging visual representations} (BVR). It can perform in-place and we demonstrate its broad effectiveness in bridging other representations into prevalent object detection frameworks, including RetinaNet, Faster R-CNN, FCOS and ATSS, where about $1.5sim3.0$ AP improvements are achieved. In particular, we improve a state-of-the-art framework with a strong backbone by about $2.0$ AP, reaching $52.7$ AP on COCO test-dev. The resulting network is named RelationNet++. The code will be available at https://github.com/microsoft/RelationNet2.
rate research
Read More
Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years. In this paper, we apply the state-of-the-art video object tracklet detection pipeline MEGA and deepSORT to generate tracklet proposals. Then we perform VidVRD in a tracklet-based manner without any pre-cutting operations. Specifically, we design a tracklet-based visual Transformer. It contains a temporal-aware decoder which performs feature interactions between the tracklets and learnable predicate query embeddings, and finally predicts the relations. Experimental results strongly demonstrate the superiority of our method, which outperforms other methods by a large margin on the Video Relation Understanding (VRU) Grand Challenge in ACM Multimedia 2021. Codes are released at https://github.com/Dawn-LX/VidVRD-tracklets.
The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture a global view of its previous layer, adjacent layers can implicitly maximize the representation differences and minimize the redundant features, making that every output feature of transformer layers contributes uniquely for final prediction. To decode features from the transformer, we propose a simple yet effective deeply-transformed decoder. The decoder densely decodes and upsamples the transformer features, generating the final saliency map with less noise injection. Experimental results demonstrate that our method significantly outperforms other FCN-based and transformer-based methods in five benchmarks by a large margin, with an average of 12.17% improvement in terms of Mean Absolute Error (MAE). Code will be available at https://github.com/OliverRensu/GLSTR.
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large context information, which is crucial for object recognition and localization, owing to the limited receptive fields. In this paper, we resolve the problem by introducing a Transformer-based architecture that enables long-range relationships between voxels by self-attention. Given the fact that non-empty voxels are naturally sparse but numerous, directly applying standard Transformer on voxels is non-trivial. To this end, we propose the sparse voxel module and the submanifold voxel module, which can operate on the empty and non-empty voxel positions effectively. To further enlarge the attention range while maintaining comparable computational overhead to the convolutional counterparts, we propose two attention mechanisms for multi-head attention in those two modules: Local Attention and Dilated Attention, and we further propose Fast Voxel Query to accelerate the querying process in multi-head attention. VoTr contains a series of sparse and submanifold voxel modules and can be applied in most voxel-based detectors. Our proposed VoTr shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Waymo Open dataset.
The transformer networks are particularly good at modeling long-range dependencies within a long sequence. In this paper, we conduct research on applying the transformer networks for salient object detection (SOD). We adopt the dense transformer backbone for fully supervised RGB image based SOD, RGB-D image pair based SOD, and weakly supervised SOD within a unified framework based on the observation that the transformer backbone can provide accurate structure modeling, which makes it powerful in learning from weak labels with less structure information. Further, we find that the vision transformer architectures do not offer direct spatial supervision, instead encoding position as a feature. Therefore, we investigate the contributions of two strategies to provide stronger spatial supervision through the transformer layers within our unified framework, namely deep supervision and difficulty-aware learning. We find that deep supervision can get gradients back into the higher level features, thus leads to uniform activation within the same semantic object. Difficulty-aware learning on the other hand is capable of identifying the hard pixels for effective hard negative mining. We also visualize features of conventional backbone and transformer backbone before and after fine-tuning them for SOD, and find that transformer backbone encodes more accurate object structure information and more distinct semantic information within the lower and higher level features respectively. We also apply our model to camouflaged object detection (COD) and achieve similar observations as the above three SOD tasks. Extensive experimental results on various SOD and COD tasks illustrate that transformer networks can transform SOD and COD, leading to new benchmarks for each related task. The source code and experimental results are available via our project page: https://github.com/fupiao1998/TrasformerSOD.
When interacting with objects through cameras, or pictures, users often have a specific intent. For example, they may want to perform a visual search. However, most object detection models ignore the user intent, relying on image pixels as their only input. This often leads to incorrect results, such as lack of a high-confidence detection on the object of interest, or detection with a wrong class label. In this paper we investigate techniques to modulate standard object detectors to explicitly account for the user intent, expressed as an embedding of a simple query. Compared to standard object detectors, query-modulated detectors show superior performance at detecting objects for a given label of interest. Thanks to large-scale training data synthesized from standard object detection annotations, query-modulated detectors can also outperform specialized referring expression recognition systems. Furthermore, they can be simultaneously trained to solve for both query-modulated detection and standard object detection.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
