Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we innovatively propose ConTNet (ConvolutionTransformer Network), combining transformer with ConvNet architectures to provide large receptive fields. Unlike the recently-proposed transformer-based models (e.g., ViT, DeiT) that are sensitive to hyper-parameters and extremely dependent on a pile of data augmentations when trained from scratch on a midsize dataset (e.g., ImageNet1k), ConTNet can be optimized like normal ConvNets (e.g., ResNet) and preserve an outstanding robustness. It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet. We present its superiority and effectiveness on image classification and downstream tasks. For example, our ConTNet achieves 81.8% top-1 accuracy on ImageNet which is the same as DeiT-B with less than 40% computational complexity. ConTNet-M also outperforms ResNet50 as the backbone of both Faster-RCNN (by 2.6%) and Mask-RCNN (by 3.2%) on COCO2017 dataset. We hope that ConTNet could serve as a useful backbone for CV tasks and bring new ideas for model design
The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this paper investigates the idea of combining multiple trained neural networks using unlabeled data. In addition, combining multiple models into one can speed up the inference, result in stronger, more capable models, and allows us to select efficient device-friendly target network architectures. To this end, the proposed method makes use of generation, filtering, and aggregation of reliable pseudo-labels collected from unlabeled data. Our method supports using an arbitrary number of input models with arbitrary architectures and categories. Extensive performance evaluations demonstrated that our method is very effective. For example, for the task of object detection and without using any ground-truth labels, an EfficientDet-D0 trained on Pascal-VOC and an EfficientDet-D1 trained on COCO, can be combined to a RetinaNet-ResNet50 model, with a similar mAP as the supervised training. If fine-tuned in a semi-supervised setting, the combined model achieves +18.6%, +12.6%, and +8.1% mAP improvements over supervised training with 1%, 5%, and 10% of labels.
Existing RGB-D SOD methods mainly rely on a symmetric two-stream CNN-based network to extract RGB and depth channel features separately. However, there are two problems with the symmetric conventional network structure: first, the ability of CNN in learning global contexts is limited; second, the symmetric two-stream structure ignores the inherent differences between modalities. In this paper, we propose a Transformer-based asymmetric network (TANet) to tackle the issues mentioned above. We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure information from depth data without pre-training. The asymmetric hybrid encoder (AHE) effectively reduces the number of parameters in the model while increasing speed without sacrificing performance. Then, we design a cross-modal feature fusion module (CMFFM), which enhances and fuses RGB and depth features with each other. Finally, we add edge prediction as an auxiliary task and propose an edge enhancement module (EEM) to generate sharper contours. Extensive experiments demonstrate that our method achieves superior performance over 14 state-of-the-art RGB-D methods on six public datasets. Our code will be released at https://github.com/lc012463/TANet.
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome model design complexity and high maintenance costs. Moreover, they often focus on learning the visual modality alone and single-label classification whilst neglecting other available information sources (e.g., class name text) and the concurrent occurrence of multiple actions. To overcome these limitations, we propose a new approach called 'actor-agnostic multi-modal multi-label action recognition,' which offers a unified solution for various types of actors, including humans and animals. We further formulate a novel Multi-modal Semantic Query Network (MSQNet) model in a transformer-based object detection framework (e.g., DETR), characterized by leveraging visual and textual modalities to represent the action classes better. The elimination of actor-specific model designs is a key advantage, as it removes the need for actor pose estimation altogether. Extensive experiments on five publicly available benchmarks show that our MSQNet consistently outperforms the prior arts of actor-specific alternatives on human and animal single- and multi-label action recognition tasks by up to 50%. Code is made available at https://github.com/mondalanindya/MSQNet.
Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention. Existing event-based backbones mainly rely on image-based designs to extract spatial information within the image transformed from events, overlooking important event properties like time and polarity. To address this issue, we propose a novel Group-based vision Transformer backbone for Event-based vision, called Group Event Transformer (GET), which de-couples temporal-polarity information from spatial infor-mation throughout the feature extraction process. Specifi-cally, we first propose a new event representation for GET, named Group Token, which groups asynchronous events based on their timestamps and polarities. Then, GET ap-plies the Event Dual Self-Attention block, and Group Token Aggregation module to facilitate effective feature commu-nication and integration in both the spatial and temporal-polarity domains. After that, GET can be integrated with different downstream tasks by connecting it with vari-ous heads. We evaluate our method on four event-based classification datasets (Cifar10-DVS, N-MNIST, N-CARS, and DVS128Gesture) and two event-based object detection datasets (1Mpx and Gen1), and the results demonstrate that GET outperforms other state-of-the-art methods. The code is available at https://github.com/Peterande/GET-Group-Event-Transformer.
Teeth segmentation and recognition are critical in various dental applications and dental diagnosis. Automatic and accurate segmentation approaches have been made possible by integrating deep learning models. Although teeth segmentation has been studied in the past, only some techniques were able to effectively classify and segment teeth simultaneously. This article offers a pipeline of two deep learning models, U-Net and YOLOv8, which results in BB-UNet, a new architecture for the classification and segmentation of teeth on panoramic X-rays that is efficient and reliable. We have improved the quality and reliability of teeth segmentation by utilising the YOLOv8 and U-Net capabilities. The proposed networks have been evaluated using the mean average precision (mAP) and dice coefficient for YOLOv8 and BB-UNet, respectively. We have achieved a 3\% increase in mAP score for teeth classification compared to existing methods, and a 10-15\% increase in dice coefficient for teeth segmentation compared to U-Net across different categories of teeth. A new Dental dataset was created based on UFBA-UESC dataset with Bounding-Box and Polygon annotations of 425 dental panoramic X-rays. The findings of this research pave the way for a wider adoption of object detection models in the field of dental diagnosis.
In the fields of Optical Character Recognition (OCR) and Natural Language Processing (NLP), integrating multilingual capabilities remains a critical challenge, especially when considering languages with complex scripts such as Arabic. This paper introduces the Comprehensive Post-OCR Parsing and Receipt Understanding Dataset (CORU), a novel dataset specifically designed to enhance OCR and information extraction from receipts in multilingual contexts involving Arabic and English. CORU consists of over 20,000 annotated receipts from diverse retail settings, including supermarkets and clothing stores, alongside 30,000 annotated images for OCR that were utilized to recognize each detected line, and 10,000 items annotated for detailed information extraction. These annotations capture essential details such as merchant names, item descriptions, total prices, receipt numbers, and dates. They are structured to support three primary computational tasks: object detection, OCR, and information extraction. We establish the baseline performance for a range of models on CORU to evaluate the effectiveness of traditional methods, like Tesseract OCR, and more advanced neural network-based approaches. These baselines are crucial for processing the complex and noisy document layouts typical of real-world receipts and for advancing the state of automated multilingual document processing. Our datasets are publicly accessible (https://github.com/Update-For-Integrated-Business-AI/CORU).
Deep learning models often function as black boxes, providing no straightforward reasoning for their predictions. This is particularly true for computer vision models, which process tensors of pixel values to generate outcomes in tasks such as image classification and object detection. To elucidate the reasoning of these models, class activation maps (CAMs) are used to highlight salient regions that influence a model's output. This research introduces KPCA-CAM, a technique designed to enhance the interpretability of Convolutional Neural Networks (CNNs) through improved class activation maps. KPCA-CAM leverages Principal Component Analysis (PCA) with the kernel trick to capture nonlinear relationships within CNN activations more effectively. By mapping data into higher-dimensional spaces with kernel functions and extracting principal components from this transformed hyperplane, KPCA-CAM provides more accurate representations of the underlying data manifold. This enables a deeper understanding of the features influencing CNN decisions. Empirical evaluations on the ILSVRC dataset across different CNN models demonstrate that KPCA-CAM produces more precise activation maps, providing clearer insights into the model's reasoning compared to existing CAM algorithms. This research advances CAM techniques, equipping researchers and practitioners with a powerful tool to gain deeper insights into CNN decision-making processes and overall behaviors.
Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the cross-modality transfer learning (CMTL) systems are scarce. In this work, we study CMTL from 2D to 3D sensor to explore the upper bound performance of 3D sensor only systems, which play critical roles in robotic navigation and perform well in low light scenarios. While most CMTL pipelines from 2D to 3D vision are complicated and based on Convolutional Neural Networks (ConvNets), ours is easy to implement, expand and based on both ConvNets and Vision transformers(ViTs): 1) By converting point clouds to pseudo-images, we can use an almost identical network from pre-trained models based on 2D images. This makes our system easy to implement and expand. 2) Recently ViTs have been showing good performance and robustness to occlusions, one of the key reasons for poor performance of 3D vision systems. We explored both ViT and ConvNet with similar model sizes to investigate the performance difference. We name our approach simCrossTrans: simple cross-modality transfer learning with ConvNets or ViTs. Experiments on SUN RGB-D dataset show: with simCrossTrans we achieve $13.2\%$ and $16.1\%$ absolute performance gain based on ConvNets and ViTs separately. We also observed the ViTs based performs $9.7\%$ better than the ConvNets one, showing the power of simCrossTrans with ViT. simCrossTrans with ViTs surpasses the previous state-of-the-art (SOTA) by a large margin of $+15.4\%$ mAP50. Compared with the previous 2D detection SOTA based RGB images, our depth image only system only has a $1\%$ gap. The code, training/inference logs and models are publicly available at https://github.com/liketheflower/simCrossTrans
While deep learning-based image reconstruction methods have shown significant success in removing objects from pictures, they have yet to achieve acceptable results for attributing consistency to gender, ethnicity, expression, and other characteristics like the topological structure of the face. The purpose of this work is to extract the mask region from a masked image and rebuild the area that has been detected. This problem is complex because (i) it is difficult to determine the gender of an image hidden behind a mask, which causes the network to become confused and reconstruct the male face as a female or vice versa; (ii) we may receive images from multiple angles, making it extremely difficult to maintain the actual shape, topological structure of the face and a natural image; and (iii) there are problems with various mask forms because, in some cases, the area of the mask cannot be anticipated precisely; certain parts of the mask remain on the face after completion. To solve this complex task, we split the problem into three phases: landmark detection, object detection for the targeted mask area, and inpainting the addressed mask region. To begin, to solve the first problem, we have used gender classification, which detects the actual gender behind a mask, then we detect the landmark of the masked facial image. Second, we identified the non-face item, i.e., the mask, and used the Mask R-CNN network to create the binary mask of the observed mask area. Thirdly, we developed an inpainting network that uses anticipated landmarks to create realistic images. To segment the mask, this article uses a mask R-CNN and offers a binary segmentation map for identifying the mask area. Additionally, we generated the image utilizing landmarks as structural guidance through a GAN-based network. The studies presented in this paper use the FFHQ and CelebA datasets.
Detection of video shot transition is a crucial pre-processing step in video analysis. Previous studies are restricted on detecting sudden content changes between frames through similarity measurement and multi-scale operations are widely utilized to deal with transitions of various lengths. However, localization of gradual transitions are still under-explored due to the high visual similarity between adjacent frames. Cut shot transitions are abrupt semantic breaks while gradual shot transitions contain low-level spatial-temporal patterns caused by video effects in addition to the gradual semantic breaks, e.g. dissolve. In order to address the problem, we propose a structured network which is able to detect these two shot transitions using targeted models separately. Considering speed performance trade-offs, we design a smart framework. With one TITAN GPU, the proposed method can achieve a 30\(\times\) real-time speed. Experiments on public TRECVID07 and RAI databases show that our method outperforms the state-of-the-art methods. In order to train a high-performance shot transition detector, we contribute a new database ClipShots, which contains 128636 cut transitions and 38120 gradual transitions from 4039 online videos. ClipShots intentionally collect short videos for more hard cases caused by hand-held camera vibrations, large object motions, and occlusion.
The quality of images captured in outdoor environments can be affected by poor weather conditions such as fog, dust, and atmospheric scattering of other particles. This problem can bring extra challenges to high-level computer vision tasks like image segmentation and object detection. However, previous studies on image dehazing suffer from a huge computational workload and corruption of the original image, such as over-saturation and halos. In this paper, we present a novel image dehazing approach based on the optical model for haze images and regularized optimization. Specifically, we convert the non-convex, bilinear problem concerning the unknown haze-free image and light transmission distribution to a convex, linear optimization problem by estimating the atmosphere light constant. Our method is further accelerated by introducing a multilevel Haar wavelet transform. The optimization, instead, is applied to the low frequency sub-band decomposition of the original image. This dimension reduction significantly improves the processing speed of our method and exhibits the potential for real-time applications. Experimental results show that our approach outperforms state-of-the-art dehazing algorithms in terms of both image reconstruction quality and computational efficiency. For implementation details, source code can be publicly accessed via http://github.com/JiaxiHe/Image-and-Video-Dehazing.
High performance person Re-Identification (Re-ID) requires the model to focus on both global silhouette and local details of pedestrian. To extract such more representative features, an effective way is to exploit deep models with multiple branches. However, most multi-branch based methods implemented by duplication of part backbone structure normally lead to severe increase of computational cost. In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure. Cooperated by attention modules and our proposed cross orthogonality regularization, FPB significantly prompts the performance of backbone network by only introducing less than 1.5M extra parameters. Extensive experimental results on standard benchmark datasets demonstrate that our proposed FPB based model outperforms state-of-the-art methods with obvious margin as well as much less model complexity. FPB borrows the idea of the Feature Pyramid Network (FPN) from prevailing object detection methods. To our best knowledge, it is the first successful application of similar structure in person Re-ID tasks, which empirically proves that pyramid network as affiliated branch could be a potential structure in related feature embedding models. The source code is publicly available at https://github.com/anocodetest1/FPB.git.
This paper presents a new efficient black-box attribution method based on Hilbert-Schmidt Independence Criterion (HSIC), a dependence measure based on Reproducing Kernel Hilbert Spaces (RKHS). HSIC measures the dependence between regions of an input image and the output of a model based on kernel embeddings of distributions. It thus provides explanations enriched by RKHS representation capabilities. HSIC can be estimated very efficiently, significantly reducing the computational cost compared to other black-box attribution methods. Our experiments show that HSIC is up to 8 times faster than the previous best black-box attribution methods while being as faithful. Indeed, we improve or match the state-of-the-art of both black-box and white-box attribution methods for several fidelity metrics on Imagenet with various recent model architectures. Importantly, we show that these advances can be transposed to efficiently and faithfully explain object detection models such as YOLOv4. Finally, we extend the traditional attribution methods by proposing a new kernel enabling an ANOVA-like orthogonal decomposition of importance scores based on HSIC, allowing us to evaluate not only the importance of each image patch but also the importance of their pairwise interactions. Our implementation is available at https://github.com/paulnovello/HSIC-Attribution-Method.
Nighttime thermal infrared (NTIR) image colorization, also known as translation of NTIR images into daytime color images (NTIR2DC), is a promising research direction to facilitate nighttime scene perception for humans and intelligent systems under unfavorable conditions (e.g., complete darkness). However, previously developed methods have poor colorization performance for small sample classes. Moreover, reducing the high confidence noise in pseudo-labels and addressing the problem of image gradient disappearance during translation are still under-explored, and keeping edges from being distorted during translation is also challenging. To address the aforementioned issues, we propose a novel learning framework called Memory-guided cOllaboRative atteNtion Generative Adversarial Network (MornGAN), which is inspired by the analogical reasoning mechanisms of humans. Specifically, a memory-guided sample selection strategy and adaptive collaborative attention loss are devised to enhance the semantic preservation of small sample categories. In addition, we propose an online semantic distillation module to mine and refine the pseudo-labels of NTIR images. Further, conditional gradient repair loss is introduced for reducing edge distortion during translation. Extensive experiments on the NTIR2DC task show that the proposed MornGAN significantly outperforms other image-to-image translation methods in terms of semantic preservation and edge consistency, which helps improve the object detection accuracy remarkably.
We introduce Epic-Sounds, a large-scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos. We propose an annotation pipeline where annotators temporally label distinguishable audio segments and describe the action that could have caused this sound. We identify actions that can be discriminated purely from audio, through grouping these free-form descriptions of audio into classes. For actions that involve objects colliding, we collect human annotations of the materials of these objects (e.g. a glass object being placed on a wooden surface), which we verify from video, discarding ambiguities. Overall, Epic-Sounds includes 78.4k categorised segments of audible events and actions, distributed across 44 classes as well as 39.2k non-categorised segments. We train and evaluate state-of-the-art audio recognition and detection models on our dataset, for both audio-only and audio-visual methods. We also conduct analysis on: the temporal overlap between audio events, the temporal and label correlations between audio and visual modalities, the ambiguities in annotating materials from audio-only input, the importance of audio-only labels and the limitations of current models to understand actions that sound. Project page : https://epic-kitchens.github.io/epic-sounds/
It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks without any knowledge of the victim model. An effective strategy to improve the transferability is attacking an ensemble of models. However, previous works simply average the outputs of different models, lacking an in-depth analysis on how and why model ensemble methods can strongly improve the transferability. In this paper, we rethink the ensemble in adversarial attacks and define the common weakness of model ensemble with two properties: 1) the flatness of loss landscape; and 2) the closeness to the local optimum of each model. We empirically and theoretically show that both properties are strongly correlated with the transferability and propose a Common Weakness Attack (CWA) to generate more transferable adversarial examples by promoting these two properties. Experimental results on both image classification and object detection tasks validate the effectiveness of our approach to improving the adversarial transferability, especially when attacking adversarially trained models. We also successfully apply our method to attack a black-box large vision-language model -- Google's Bard, showing the practical effectiveness. Code is available at \url{https://github.com/huanranchen/AdversarialAttacks}.
Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a post-training quantization (PTQ) framework for Segment Anything Model, namely PTQ4SAM. First, we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second, SAM encompasses diverse attention mechanisms (i.e., self-attention and two-way cross-attention), resulting in substantial variations in the post-Softmax distributions. Therefore, we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base, which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation, semantic segmentation and object detection), datasets and model variants show the superiority of PTQ4SAM. For example, when quantizing SAM-L to 6-bit, we achieve lossless accuracy for instance segmentation, about 0.5\% drop with theoretical 3.9$\times$ acceleration. The code is available at \url{https://github.com/chengtao-lv/PTQ4SAM}.
Recent studies have shown promising results in utilizing multimodal large language models (MLLMs) for computer vision tasks such as object detection and semantic segmentation. However, many challenging video tasks remain under-explored. Video-language tasks necessitate spatial and temporal comprehension and require significant compute. Therefore, prior works have developed complex, highly specialized architectures or leveraged additional input signals such as video transcripts to best encode contextual and temporal information, which limits their generality and can be impractical. One particularly challenging task is video moment retrieval, which requires precise temporal and contextual grounding. This work demonstrates the surprising effectiveness of leveraging image-text pretrained MLLMs for moment retrieval. We introduce Mr. BLIP (Mr. as in Moment Retrieval), a multimodal, single-stage model that requires no expensive video-language pretraining, no additional input signal (e.g., no transcript or audio), and has a simpler and more versatile design than prior state-of-the-art methods. We achieve a new state-of-the-art in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions. Notably, we attain over 9% (absolute) higher Recall (at 0.5 and 0.7 IoU) on the challenging long-video multi-moment QVHighlights benchmark. Our code is publicly available.
Remote Sensing Vision-Language Models (RS VLMs) have made much progress in the tasks of remote sensing (RS) image comprehension. While performing well in multi-modal reasoning and multi-turn conversations, the existing models lack pixel-level understanding and struggle with multi-image inputs. In this work, we propose RSUniVLM, a unified, end-to-end RS VLM designed for comprehensive vision understanding across multiple granularity, including image-level, region-level, and pixel-level tasks. RSUniVLM also performs effectively in multi-image analysis, with instances of change detection and change captioning. To enhance the model's ability to capture visual information at different levels without increasing model size, we design a novel architecture called Granularity-oriented Mixture of Experts to constraint the model to about 1 billion parameters. We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain, encompassing various tasks such as object localization, visual question answering, and semantic segmentation. Substantial experiments have been conducted to validate the superiority of the proposed RSUniVLM up to state-of-the-art across various RS tasks. Code and model will be available at \href{https://github.com/xuliu-cyber/RSUniVLM}{here}.