Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduced a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. Moreover, to boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. Experimental results show that our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency. Code is available at \url{https://github.com/KyleZheng1997/ReSSL}.
This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021). The competition attracted a total of 10 participating teams with valid submissions. The affiliations of these teams are diverse and associated with academia and industry in nine different countries. These teams successfully submitted 18 valid solutions. The competition is designed to motivate solutions aiming at enhancing the face recognition accuracy of masked faces. Moreover, the competition considered the deployability of the proposed solutions by taking the compactness of the face recognition models into account. A private dataset representing a collaborative, multi-session, real masked, capture scenario is used to evaluate the submitted solutions. In comparison to one of the top-performing academic face recognition solutions, 10 out of the 18 submitted solutions did score higher masked face verification accuracy.
Recently, transformers have shown great superiority in solving computer vision tasks by modeling images as a sequence of manually-split patches with self-attention mechanism. However, current architectures of vision transformers (ViTs) are simply inherited from natural language processing (NLP) tasks and have not been sufficiently investigated and optimized. In this paper, we make a further step by examining the intrinsic structure of transformers for vision tasks and propose an architecture search method, dubbed ViTAS, to search for the optimal architecture with similar hardware budgets. Concretely, we design a new effective yet efficient weight sharing paradigm for ViTs, such that architectures with different token embedding, sequence size, number of heads, width, and depth can be derived from a single super-transformer. Moreover, to cater for the variance of distinct architectures, we introduce \textit{private} class token and self-attention maps in the super-transformer. In addition, to adapt the searching for different budgets, we propose to search the sampling probability of identity operation. Experimental results show that our ViTAS attains excellent results compared to existing pure transformer architectures. For example, with $1.3$G FLOPs budget, our searched architecture achieves $74.7\%$ top-$1$ accuracy on ImageNet and is $2.5\%$ superior than the current baseline ViT architecture. Code is available at \url{https://github.com/xiusu/ViTAS}.
An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.
In one-shot weight sharing for NAS, the weights of each operation (at each layer) are supposed to be identical for all architectures (paths) in the supernet. However, this rules out the possibility of adjusting operation weights to cater for different paths, which limits the reliability of the evaluation results. In this paper, instead of counting on a single supernet, we introduce $K$-shot supernets and take their weights for each operation as a dictionary. The operation weight for each path is represented as a convex combination of items in a dictionary with a simplex code. This enables a matrix approximation of the stand-alone weight matrix with a higher rank ($K>1$). A \textit{simplex-net} is introduced to produce architecture-customized code for each path. As a result, all paths can adaptively learn how to share weights in the $K$-shot supernets and acquire corresponding weights for better evaluation. $K$-shot supernets and simplex-net can be iteratively trained, and we further extend the search to the channel dimension. Extensive experiments on benchmark datasets validate that K-shot NAS significantly improves the evaluation accuracy of paths and thus brings in impressive performance improvements.
Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constraints. To fulfill the searching, a one-shot supernet is usually leveraged to efficiently evaluate the performance \wrt~different network widths. However, current methods mainly follow a \textit{unilaterally augmented} (UA) principle for the evaluation of each width, which induces the training unfairness of channels in supernet. In this paper, we introduce a new supernet called Bilaterally Coupled Network (BCNet) to address this issue. In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately. Besides, we leverage a stochastic complementary strategy for training the BCNet, and propose a prior initial population sampling method to boost the performance of the evolutionary search. Extensive experiments on benchmark CIFAR-10 and ImageNet datasets indicate that our method can achieve state-of-the-art or competing performance over other baseline methods. Moreover, our method turns out to further boost the performance of NAS models by refining their network widths. For example, with the same FLOPs budget, our obtained EfficientNet-B0 achieves 77.36\% Top-1 accuracy on ImageNet dataset, surpassing the performance of original setting by 0.48\%.
Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation. Therefore, we propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors. In the decoder, a Language-Guided Feature Selection (LGFS) module is proposed to flexibly integrate spatial and temporal features from the two encoders. We also propose a Cross-Modal Adaptive Modulation (CMAM) module to dynamically recombine spatial- and temporal-relevant linguistic features for multimodal feature interaction in each stage of the two encoders. Our method achieves new state-of-the-art performance on two popular benchmarks with less computational overhead than previous approaches.
The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems for this task often treat tables as plain text based on the assumption that tables are structured as dataframes. However, tables can have complex layouts which indicate diverse dependencies between subtable structures, such as nested headers. As a result, queries may refer to different spans of relevant content that is distributed across these structures. Moreover, such systems fail to generalize to novel scenarios beyond those seen in the training set. Prior methods are still distant from a generalizable solution to the NLTR problem, as they fall short in handling complex table layouts or queries over multiple granularities. To address these issues, we propose Graph-based Table Retrieval (GTR), a generalizable NLTR framework with multi-granular graph representation learning. In our framework, a table is first converted into a tabular graph, with cell nodes, row nodes and column nodes to capture content at different granularities. Then the tabular graph is input to a Graph Transformer model that can capture both table cell content and the layout structures. To enhance the robustness and generalizability of the model, we further incorporate a self-supervised pre-training task based on graph-context matching. Experimental results on two benchmarks show that our method leads to significant improvements over the current state-of-the-art systems. Further experiments demonstrate promising performance of our method on cross-dataset generalization, and enhanced capability of handling complex tables and fulfilling diverse query intents. Code and data are available at https://github.com/FeiWang96/GTR.
The fish target detection algorithm lacks a good quality data set, and the algorithm achieves real-time detection with lower power consumption on embedded devices, and it is difficult to balance the calculation speed and identification ability. To this end, this paper collected and annotated a data set named "Aquarium Fish" of 84 fishes containing 10042 images, and based on this data set, proposed a multi-scale input fast fish target detection network (BTP-yoloV3) and its optimization method. The experiment uses Depthwise convolution to redesign the backbone of the yoloV4 network, which reduces the amount of calculation by 94.1%, and the test accuracy is 92.34%. Then, the training model is enhanced with MixUp, CutMix, and mosaic to increase the test accuracy by 1.27%; Finally, use the mish, swish, and ELU activation functions to increase the test accuracy by 0.76%. As a result, the accuracy of testing the network with 2000 fish images reached 94.37%, and the computational complexity of the network BFLOPS was only 5.47. Comparing the YoloV3~4, MobileNetV2-yoloV3, and YoloV3-tiny networks of migration learning on this data set. The results show that BTP-Yolov3 has smaller model parameters, faster calculation speed, and lower energy consumption during operation while ensuring the calculation accuracy. It provides a certain reference value for the practical application of neural network.
Face detector frequently confronts extreme scale variance challenge. The famous solutions are Multi-scale training, Data-anchor-sampling and Random crop strategy. In this paper, we indicate 2 significant elements to resolve extreme scale variance problem by investigating the difference among the previous solutions, including the fore-ground and back-ground information of an image and the scale information. However, current excellent solutions can only utilize the former information while neglecting to absorb the latter one effectively. In order to help the detector utilize the scale information efficiently, we analyze the relationship between the detector performance and the scale distribution of the training data. Based on this analysis, we propose a Selective Scale Enhancement (SSE) strategy which can assimilate these two information efficiently and simultaneously. Finally, our method achieves state-of-the-art detection performance on all common face detection benchmarks, including AFW, PASCAL face, FDDB and Wider Face datasets. Note that our result achieves six champions on the Wider Face dataset.