Accurate feature matching between image pairs is fundamental for various computer vision applications. In detector-base process, the feature matcher aims to find the optimal feature correspondences, and the match filter is used for further removing mismatches. However, their connection is rarely exploited since they are usually treated as two separate issues in previous method, which may lead to suboptimal results. In this paper, we propose an end-to-end collaborative feature matching (CFM) method, which contains a keypoint learning (KL) module and a correspondence learning (CL) module, to bridge the gap between two types of works. The former improves the discrimination of keypoints, and provides high-quality dynamic matches for CL module. The latter further captures the rich context of matches, and gives effective feedback to KL module. These two modules can reinforce each other in a progressive manner. Besides, we develop an efficient version of CFM, named ECFM, using an adaptive sampling strategy to avoid the negative influence of uninformative keypoints. Experimental results indicate that both methods outperform the state-of-the-art competitors in the tasks of relative pose estimation and visual localization.

Over the last decade, many notable methods have emerged to tackle the computational resource challenge of the high resolution image recognition (HRIR). They typically focus on identifying and aggregating a few salient regions for classification, discarding sub-salient areas for low training consumption. Nevertheless, many HRIR tasks necessitate the exploration of wider regions to model objects and contexts, which limits their performance in such scenarios. To address this issue, we present a DBPS strategy to enable training with more patches at low consumption. Specifically, in addition to a fundamental buffer that stores the embeddings of most salient patches, DBPS further employs an auxiliary buffer to recycle those sub-salient ones. To reduce the computational cost associated with gradients of sub-salient patches, these patches are primarily used in the forward pass to provide sufficient information for classification. Meanwhile, only the gradients of the salient patches are back-propagated to update the entire network. Moreover, we design a Multiple Instance Learning (MIL) architecture that leverages aggregated information from salient patches to filter out uninformative background within sub-salient patches for better accuracy. Besides, we introduce the random patch drop to accelerate training process and uncover informative regions. Experiment results demonstrate the superiority of our method in terms of both accuracy and training consumption against other advanced methods. The code is available in the https://github.com/Qinrong-Nku/DBPS.

Over the last decade, significant efforts have been dedicated to designing efficient models for the challenge of ultra-high resolution (UHR) semantic segmentation. These models mainly follow the dual-stream architecture and generally fall into three subcategories according to the improvement objectives, i.e., dual-stream ensemble, selective zoom, and complementary learning. However, most of them overly concentrate on crafting complex pipelines to pursue one of the above objectives separately, limiting the model performance in both accuracy and inference consumption. In this paper, we suggest simultaneously achieving these objectives by estimating resolution-biased uncertainties in low resolution stream. Here, the resolution-biased uncertainty refers to the degree of prediction unreliability primarily caused by resolution loss from down-sampling operations. Specifically, we propose a dual-stream UHR segmentation framework, where an estimator is used to assess resolution-biased uncertainties through the entropy map and high-frequency feature residual. The framework also includes a selector, an ensembler, and a complementer to boost the model with obtained estimations. They share the uncertainty estimations as the weights to choose difficult regions as the inputs for UHR stream, perform weighted fusion between distinct streams, and enhance the learning for important pixels, respectively. Experiment results demonstrate that our method achieves a satisfactory balance between accuracy and inference consumption against other state-of-the-art (SOTA) methods. The code is available in the https://github.com/Qinrong-NKU/RUE.

In online chatting, people increasingly prefer using stickers to supplement or replace text for replies, as sticker images can express vivid and varied emotions. The Sticker Response Selection (SRS) task aims to predict the sticker image that is most relevant to the history dialogue. Previous researches explore the semantic similarity between context and stickers, overlooking both unimodal and cross-modal emotional information. In this paper, we propose a 'Perceive before Respond' (PBR) training paradigm. PBR perceives sticker emotions through a knowledge distillation module. Variety representations of each emotion category are acquired from the large-scale sticker emotion recognition dataset and distilled into our model to enhance emotion comprehension. We further distinguish stickers with similar subject elements under the same topic. We perform contrastive learning at both inter- and intra-topic levels to obtain discriminative and diverse sticker representations. In addition, we improve the hard negative sampling method for image-text matching based on cross-modal sentiment association, conducting hard sample mining from both semantic similarity and sentiment polarity similarity for sticker-to-dialogue and dialogue-to-sticker. Extensive experiments verify the effectiveness of each proposed component. Ablation experiments on different backbone networks demonstrate the generality of our approach. Our code is released on https://github.com/wuyou-xia/Perceive-before-Respond.

Correspondence pruning plays a crucial role in a variety of feature matching based tasks, which aims at identifying correct correspondences (inliers) from initial ones. Seeking consistent k-nearest neighbors in both coordinate and feature spaces is a prevalent strategy employed in previous approaches. However, the vicinity of an inlier contains numerous irregular false correspondences (outliers), which leads them to mistakenly become neighbors according to the similarity constraint of nearest neighbors. To tackle this issue, we propose a global-graph space to seek consistent neighbors with similar graph structures. This is achieved by using a global connected graph to explicitly render the affinity relationship between correspondences based on the spatial and feature consistency. Furthermore, to enhance the robustness of method for various matching scenes, we develop a neighbor consistency block to adequately leverage the potential of three types of neighbors. The consistency can be progressively mined by sequentially extracting intra-neighbor context and exploring inter-neighbor interactions. Ultimately, we present a Neighbor Consistency Mining Network (NCMNet) to estimate the parametric models and remove outliers. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on various benchmarks for two-view geometry estimation. Meanwhile, four extended tasks, including remote sensing image registration, point cloud registration, 3D reconstruction, and visual localization, are conducted to test the generalization ability.

Abstract There are a large number of cameras in modern transportation system that capture numerous vehicle images continuously. Therefore, automatic analysis of these vehicle images is helpful for traffic flow management, criminal investigations and vehicle inspections. Vehicle matching, which aims to determine whether two input images depict an identical vehicle, is one of the core tasks in vehicle analysis. Recent relevant studies have focused on local feature extraction instead of global extraction, since local details can provide crucial cues to distinguish between cars. However, these methods do not select local features; that is, they do not assign weights to local features. Therefore, in this research, we systematically study the vehicle matching task, and present a novel annotation‐free local‐based deep learning method called Adaptive super‐pixel discriminative feature‐selective learning (ASDFL) to address this issue. In ASDFL, vehicle images are segmented into clusters of super‐pixels of similar size by considering the location and colour similarities of pixels without using any component‐level annotation. These super‐pixels are deemed to be the virtual components of vehicles. Moreover, a convolutional neural network is used to extract the deep features of these virtual components. Thereafter, an instance‐specific mask generation module driven by the extracted global features is enhanced to produce a mask to select the most distinctive virtual components of each vehicle image pair in the feature space. Finally, the vehicle matching task is accomplished by classifying the selected virtual component features of each imaged vehicle pair. Extensive experiments on two popular vehicle identification benchmarks demonstrate that our method is 1.57% and 0.8% more accurate than the previous baselines in a vehicle matching task on the VeRi and VehicleID datasets, respectively, which demonstrates the effectiveness of our method.

Application Programming Interface (API) recommendation based on graphs is a valuable task in the fields of data visualization and software engineering. However, this task was previously undefined until a recently published paper coining the task as Plot2API and utilizing a deep learning-based method named SPGNN. Compared to general image classification methods, this dedicated approach uses semantic parsing to exploit deep features and yields better performance. However, its performance declines sharply in unbalanced datasets, thus limiting its generalizability. To address this issue, we propose a method named Multi-cue Shape and software engineering-aware Transferable Imbalance Learning (MSTIL), consisting of three major components: Cross-Language Shape-Aware Plot Transfer Learning (CLSAPTL), Cross-Language API Semantic Similarity-based Data Augmentation (CLASSDA), and Imbalance Plot2API Learning (IPL). Motivated by the hierarchical classification of the graphs, CLSAPTL guides the model to learn the graphs’ class hierarchy and thereby enabling the model to learn more transferable visual features. Given that a graph can be associated with multiple APIs and motivated by the fact that many APIs that exert similar functions in different languages have semantically similar names, CLASSDA leverages the samples of APIs with semantically similar names to assist in feature learning. Finally, inspired by the essence of softmax cross entropy loss, IPL alleviates the imbalances between positive and negative samples during training. We conduct our experiments on two public datasets. Extensive experimental results shows that MSTIL improves the performance of classic CNNs along with the state-of-the-art method, demonstrating its effectiveness. Specifically, MSTIL has an average relative mAP improvement of 12.94% across the models on all datasets.