In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large image database, some approaches quantize deep local features with a large codebook and match images with aggregated match kernel. However, the complexity of these approaches is non-trivial with large memory footprint, which limits their capability to jointly perform feature learning and aggregation. To generate compact global representations while maintaining regional matching capability, we propose a unified framework to jointly learn local feature representation and aggregation. In our framework, we first extract deep local features using CNNs. Then, we design a tokenizer module to aggregate them into a few visual tokens, each corresponding to a specific visual pattern. This helps to remove background noise, and capture more discriminative regions in the image. Next, a refinement block is introduced to enhance the visual tokens with self-attention and cross-attention. Finally, different visual tokens are concatenated to generate a compact global representation. The whole framework is trained end-to-end with image-level labels. Extensive experiments are conducted to evaluate our approach, which outperforms the state-of-the-art methods on the Revisited Oxford and Paris datasets.
Existing unsupervised person re-identification methods only rely on visual clues to match pedestrians under different cameras. Since visual data is essentially susceptible to occlusion, blur, clothing changes, etc., a promising solution is to introduce heterogeneous data to make up for the defect of visual data. Some works based on full-scene labeling introduce wireless positioning to assist cross-domain person re-identification, but their GPS labeling of entire monitoring scenes is laborious. To this end, we propose to explore unsupervised person re-identification with both visual data and wireless positioning trajectories under weak scene labeling, in which we only need to know the locations of the cameras. Specifically, we propose a novel unsupervised multimodal training framework (UMTF), which models the complementarity of visual data and wireless information. Our UMTF contains a multimodal data association strategy (MMDA) and a multimodal graph neural network (MMGN). MMDA explores potential data associations in unlabeled multimodal data, while MMGN propagates multimodal messages in the video graph based on the adjacency matrix learned from histogram statistics of wireless data. Thanks to the robustness of the wireless data to visual noise and the collaboration of various modules, UMTF is capable of learning a model free of the human label on data. Extensive experimental results conducted on two challenging datasets, i.e., WP-ReID and DukeMTMC-VideoReID demonstrate the effectiveness of the proposed method.
Compared to flatbed scanners, portable smartphones are much more convenient for physical documents digitizing. However, such digitized documents are often distorted due to uncontrolled physical deformations, camera positions, and illumination variations. To this end, this work presents DocScanner, a new deep network architecture for document image rectification. Different from existing methods, DocScanner addresses this issue by introducing a progressive learning mechanism. Specifically, DocScanner maintains a single estimate of the rectified image, which is progressively corrected with a recurrent architecture. The iterative refinements make DocScanner converge to a robust and superior performance, and the lightweight recurrent architecture ensures the running efficiency. In addition, before the above rectification process, observing the corrupted rectified boundaries existing in prior works, DocScanner exploits a document localization module to explicitly segment the foreground document from the cluttered background environments. To further improve the rectification quality, based on the geometric priori between the distorted and the rectified images, a geometric regularization is introduced during training to further facilitate the performance. Extensive experiments are conducted on the Doc3D dataset and the DocUNet benchmark dataset, and the quantitative and qualitative evaluation results verify the effectiveness of DocScanner, which outperforms previous methods on OCR accuracy, image similarity, and our proposed distortion metric by a considerable margin. Furthermore, our DocScanner shows the highest efficiency in inference time and parameter count.
In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques. In image retrieval, it is observed that the contextual similarity among the top-ranked images is an important clue to distinguish the semantic relevance. Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. In our approach, for each image in the top-K ranking list, we represent it into an affinity feature vector by comparing it with a set of anchor images. Then, the affinity features of the top-K images are refined by aggregating the contextual information with a transformer encoder. Finally, the affinity features are used to recalculate the similarity scores between the query and the top-K images for re-ranking of the latter. To further improve the robustness of our re-ranking model and enhance the performance of our method, a new data augmentation scheme is designed. Since our re-ranking model is not directly involved with the visual feature used in the initial retrieval, it is ready to be applied to retrieval result lists obtained from various retrieval algorithms. We conduct comprehensive experiments on four benchmark datasets to demonstrate the generality and effectiveness of our proposed visual re-ranking method.
In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarping transformer and an illumination correction transformer. By setting a set of learned query embedding, the geometric unwarping transformer captures the global context of the document image by self-attention mechanism and decodes the pixel-wise displacement solution to correct the geometric distortion. After geometric unwarping, our illumination correction transformer further removes the shading artifacts to improve the visual quality and OCR accuracy. Extensive evaluations are conducted on several datasets, and superior results are reported against the state-of-the-art methods. Remarkably, our DocTr achieves 20.02% Character Error Rate (CER), a 15% absolute improvement over the state-of-the-art methods. Moreover, it also shows high efficiency on running time and parameter count. The results will be available at https://github.com/fh2019ustc/DocTr for further comparison.
Hand gesture serves as a critical role in sign language. Current deep-learning-based sign language recognition (SLR) methods may suffer insufficient interpretability and overfitting due to limited sign data sources. In this paper, we introduce the first self-supervised pre-trainable SignBERT with incorporated hand prior for SLR. SignBERT views the hand pose as a visual token, which is derived from an off-the-shelf pose extractor. The visual tokens are then embedded with gesture state, temporal and hand chirality information. To take full advantage of available sign data sources, SignBERT first performs self-supervised pre-training by masking and reconstructing visual tokens. Jointly with several mask modeling strategies, we attempt to incorporate hand prior in a model-aware method to better model hierarchical context over the hand sequence. Then with the prediction head added, SignBERT is fine-tuned to perform the downstream SLR task. To validate the effectiveness of our method on SLR, we perform extensive experiments on four public benchmark datasets, i.e., NMFs-CSL, SLR500, MSASL and WLASL. Experiment results demonstrate the effectiveness of both self-supervised learning and imported hand prior. Furthermore, we achieve state-of-the-art performance on all benchmarks with a notable gain.
Generative adversarial networks have been widely used in image synthesis in recent years and the quality of the generated image has been greatly improved. However, the flexibility to control and decouple facial attributes (e.g., eyes, nose, mouth) is still limited. In this paper, we propose a novel approach, called ChildGAN, to generate a child's image according to the images of parents with heredity prior. The main idea is to disentangle the latent space of a pre-trained generation model and precisely control the face attributes of child images with clear semantics. We use distances between face landmarks as pseudo labels to figure out the most influential semantic vectors of the corresponding face attributes by calculating the gradient of latent vectors to pseudo labels. Furthermore, we disentangle the semantic vectors by weighting irrelevant features and orthogonalizing them with Schmidt Orthogonalization. Finally, we fuse the latent vector of the parents by leveraging the disentangled semantic vectors under the guidance of biological genetic laws. Extensive experiments demonstrate that our approach outperforms the existing methods with encouraging results.
Contrastive learning shows great potential in unpaired image-to-image translation, but sometimes the translated results are in poor quality and the contents are not preserved consistently. In this paper, we uncover that the negative examples play a critical role in the performance of contrastive learning for image translation. The negative examples in previous methods are randomly sampled from the patches of different positions in the source image, which are not effective to push the positive examples close to the query examples. To address this issue, we present instance-wise hard Negative Example Generation for Contrastive learning in Unpaired image-to-image Translation (NEGCUT). Specifically, we train a generator to produce negative examples online. The generator is novel from two perspectives: 1) it is instance-wise which means that the generated examples are based on the input image, and 2) it can generate hard negative examples since it is trained with an adversarial loss. With the generator, the performance of unpaired image-to-image translation is significantly improved. Experiments on three benchmark datasets demonstrate that the proposed NEGCUT framework achieves state-of-the-art performance compared to previous methods.
Semi-supervised video object segmentation is a task of segmenting the target object in a video sequence given only a mask annotation in the first frame. The limited information available makes it an extremely challenging task. Most previous best-performing methods adopt matching-based transductive reasoning or online inductive learning. Nevertheless, they are either less discriminative for similar instances or insufficient in the utilization of spatio-temporal information. In this work, we propose to integrate transductive and inductive learning into a unified framework to exploit the complementarity between them for accurate and robust video object segmentation. The proposed approach consists of two functional branches. The transduction branch adopts a lightweight transformer architecture to aggregate rich spatio-temporal cues while the induction branch performs online inductive learning to obtain discriminative target information. To bridge these two diverse branches, a two-head label encoder is introduced to learn the suitable target prior for each of them. The generated mask encodings are further forced to be disentangled to better retain their complementarity. Extensive experiments on several prevalent benchmarks show that, without the need of synthetic training data, the proposed approach sets a series of new state-of-the-art records. Code is available at https://github.com/maoyunyao/JOINT.
As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely distributed in the 3D space, and with unstructured storage, which makes it difficult to represent them for effective 3D object detection. To this end, in this work, we regard point clouds as hollow-3D data and propose a new architecture, namely Hallucinated Hollow-3D R-CNN ($\text{H}^2$3D R-CNN), to address the problem of 3D object detection. In our approach, we first extract the multi-view features by sequentially projecting the point clouds into the perspective view and the bird-eye view. Then, we hallucinate the 3D representation by a novel bilaterally guided multi-view fusion block. Finally, the 3D objects are detected via a box refinement module with a novel Hierarchical Voxel RoI Pooling operation. The proposed $\text{H}^2$3D R-CNN provides a new angle to take full advantage of complementary information in the perspective view and the bird-eye view with an efficient framework. We evaluate our approach on the public KITTI Dataset and Waymo Open Dataset. Extensive experiments demonstrate the superiority of our method over the state-of-the-art algorithms with respect to both effectiveness and efficiency. The code will be made available at \url{https://github.com/djiajunustc/H-23D_R-CNN}.