Swathikiran Sudhakaran, Sergio Escalera, & Oswald Lanz. (2023). Gate-Shift-Fuse for Video Action Recognition. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10913–10928.
Abstract: Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.
Keywords: Action Recognition; Video Classification; Spatial Gating; Channel Fusion
|
Daniel Marczak, Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, & Bartłomiej Twardowski. (2023). Generalized Continual Category Discovery.
Abstract: Most of Continual Learning (CL) methods push the limit of supervised learning settings, where an agent is expected to learn new labeled tasks and not forget previous knowledge. However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes. Drawing inspiration from Generalized Category Discovery (GCD), we introduce a novel framework that relaxes this assumption. Precisely, in any task, we allow for the existence of novel and known classes, and one must use continual version of unsupervised learning methods to discover them. We call this setting Generalized Continual Category Discovery (GCCD). It unifies CL and GCD, bridging the gap between synthetic benchmarks and real-life scenarios. With a series of experiments, we present that existing methods fail to accumulate knowledge from subsequent tasks in which unlabeled samples of novel classes are present. In light of these limitations, we propose a method that incorporates both supervised and unsupervised signals and mitigates the forgetting through the use of centroid adaptation. Our method surpasses strong CL methods adopted for GCD techniques and presents a superior representation learning performance.
|
Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, & Joost Van de Weijer. (2023). Generative Multi-Label Zero-Shot Learning. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14611–14624.
Abstract: Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.
Keywords: Generalized zero-shot learning; Multi-label classification; Zero-shot object detection; Feature synthesis
|
Benjia Zhou, Zhigang Chen, Albert Clapes, Jun Wan, Yanyan Liang, Sergio Escalera, et al. (2023). Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining. In IEEE/CVF International Conference on Computer Vision (ICCV) Workshops.
Abstract: Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods.
|
Chenshen Wu. (2023). Going beyond Classification Problems for the Continual Learning of Deep Neural Networks (Joost Van de Weijer, & Bogdan Raducanu, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Deep learning has made tremendous progress in the last decade due to the explosion of training data and computational power. Through end-to-end training on a
large dataset, image representations are more discriminative than the previously
used hand-crafted features. However, for many real-world applications, training
and testing on a single dataset is not realistic, as the test distribution may change over time. Continuous learning takes this situation into account, where the learner must adapt to a sequence of tasks, each with a different distribution. If you would naively continue training the model with a new task, the performance of the model would drop dramatically for the previously learned data. This phenomenon is known as catastrophic forgetting.
Many approaches have been proposed to address this problem, which can be divided into three main categories: regularization-based approaches, rehearsal-based
approaches, and parameter isolation-based approaches. However, most of the existing works focus on image classification tasks and many other computer vision tasks
have not been well-explored in the continual learning setting. Therefore, in this
thesis, we study continual learning for image generation, object re-identification,
and object counting.
For the image generation problem, since the model can generate images from the previously learned task, it is free to apply rehearsal without any limitation. We developed two methods based on generative replay. The first one uses the generated image for joint training together with the new data. The second one is based on
output pixel-wise alignment. We extensively evaluate these methods on several
benchmarks.
Next, we study continual learning for object Re-Identification (ReID). Although
most state-of-the-art methods of ReID and continual ReID use softmax-triplet loss,
we found that it is better to solve the ReID problem from a meta-learning perspective because continual learning of reID can benefit a lot from the generalization of metalearning. We also propose a distillation loss and found that the removal of the positive pairs before the distillation loss is critical.
Finally, we study continual learning for the counting problem. We study the mainstream method based on density maps and propose a new approach for density
map distillation. We found that fixing the counter head is crucial for the continual learning of object counting. To further improve results, we propose an adaptor to adapt the changing feature extractor for the fixed counter head. Extensive evaluation shows that this results in improved continual learning performance.
|
Mohammad Momeny, Ali Asghar Neshat, Ahmad Jahanbakhshi, Majid Mahmoudi, Yiannis Ampatzidis, & Petia Radeva. (2023). Grading and fraud detection of saffron via learning-to-augment incorporated Inception-v4 CNN. FC - Food Control, 147, 109554.
Abstract: Saffron is a well-known product in the food industry. It is one of the spices that are sometimes adulterated with the sole motive of gaining more economic profit. Today, machine vision systems are widely used in controlling the quality of food and agricultural products as a new, non-destructive, and inexpensive approach. In this study, a machine vision system based on deep learning was used to detect fraud and saffron quality. A dataset of 1869 images was created and categorized in 6 classes including: dried saffron stigma using a dryer; dried saffron stigma using pressing method; pure stem of saffron; sunflower; saffron stem mixed with food coloring; and corn silk mixed with food coloring. A Learning-to-Augment incorporated Inception-v4 Convolutional Neural Network (LAII-v4 CNN) was developed for grading and fraud detection of saffron in images captured by smartphones. The best policies of data augmentation were selected with the proposed LAII-v4 CNN using images corrupted by Gaussian, speckle, and impulse noise to address overfitting the model. The proposed LAII-v4 CNN compared with regular CNN-based methods and traditional classifiers. Ensemble of Bagged Decision Trees, Ensemble of Boosted Decision Trees, k-Nearest Neighbor, Random Under-sampling Boosted Trees, and Support Vector Machine were used for classification of the features extracted by Histograms of Oriented Gradients and Local Binary Patterns, and selected by the Principal Component Analysis. The results showed that the proposed LAII-v4 CNN with an accuracy of 99.5% has achieved the best performance by employing batch normalization, Dropout, and leaky ReLU.
|
Ruben Tito, Dimosthenis Karatzas, & Ernest Valveny. (2023). Hierarchical multimodal transformers for Multi-Page DocVQA. PR - Pattern Recognition, 144, 109834.
Abstract: Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.
|
Ruben Tito, Dimosthenis Karatzas, & Ernest Valveny. (2023). Hierarchical multimodal transformers for Multipage DocVQA. PR - Pattern Recognition, 144(109834).
Abstract: Existing work on DocVQA only considers single-page documents. However, in real applications documents are mostly composed of multiple pages that should be processed altogether. In this work, we propose a new multimodal hierarchical method Hi-VT5, that overcomes the limitations of current methods to process long multipage documents. In contrast to previous hierarchical methods that focus on different semantic granularity (He et al., 2021) or different subtasks (Zhou et al., 2022) used in image classification. Our method is a hierarchical transformer architecture where the encoder learns to summarize the most relevant information of every page and then, the decoder uses this summarized representation to generate the final answer, following a bottom-up approach. Moreover, due to the lack of multipage DocVQA datasets, we also introduce MP-DocVQA, an extension of SP-DocVQA where questions are posed over multipage documents instead of single pages. Through extensive experimentation, we demonstrate that Hi-VT5 is able, in a single stage, to answer the questions and provide the page that contains the answer, which can be used as a kind of explainability measure.
|
Asma Bensalah, Antonio Parziale, Giuseppe De Gregorio, Angelo Marcelli, Alicia Fornes, & Josep Llados. (2023). I Can’t Believe It’s Not Better: In-air Movement for Alzheimer Handwriting Synthetic Generation. In 21st International Graphonomics Conference (136–148).
Abstract: During recent years, there here has been a boom in terms of deep learning use for handwriting analysis and recognition. One main application for handwriting analysis is early detection and diagnosis in the health field. Unfortunately, most real case problems still suffer a scarcity of data, which makes difficult the use of deep learning-based models. To alleviate this problem, some works resort to synthetic data generation. Lately, more works are directed towards guided data synthetic generation, a generation that uses the domain and data knowledge to generate realistic data that can be useful to train deep learning models. In this work, we combine the domain knowledge about the Alzheimer’s disease for handwriting and use it for a more guided data generation. Concretely, we have explored the use of in-air movements for synthetic data generation.
|
Wenwen Yu, Mingyu Liu, Mingrui Chen, Ning Lu, Yinlong We, Yuliang Liu, et al. (2023). ICDAR 2023 Competition on Reading the Seal Title. In 17th International Conference on Document Analysis and Recognition (Vol. 14188, 522–535). LNCS.
Abstract: Reading seal title text is a challenging task due to the variable shapes of seals, curved text, background noise, and overlapped text. However, this important element is commonly found in official and financial scenarios, and has not received the attention it deserves in the field of OCR technology. To promote research in this area, we organized ICDAR 2023 competition on reading the seal title (ReST), which included two tasks: seal title text detection (Task 1) and end-to-end seal title recognition (Task 2). We constructed a dataset of 10,000 real seal data, covering the most common classes of seals, and labeled all seal title texts with text polygons and text contents. The competition opened on 30th December, 2022 and closed on 20th March, 2023. The competition attracted 53 participants and received 135 submissions from academia and industry, including 28 participants and 72 submissions for Task 1, and 25 participants and 63 submissions for Task 2, which demonstrated significant interest in this challenging task. In this report, we present an overview of the competition, including the organization, challenges, and results. We describe the dataset and tasks, and summarize the submissions and evaluation results. The results show that significant progress has been made in the field of seal title text reading, and we hope that this competition will inspire further research and development in this important area of OCR technology.
|
George Tom, Minesh Mathew, Sergi Garcia Bordils, Dimosthenis Karatzas, & CV Jawahar. (2023). ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. In 17th International Conference on Document Analysis and Recognition (Vol. 14188, 577–586). LNCS.
Abstract: In this report, we present the final results of the ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. The RoadText challenge is based on the RoadText-1K dataset and aims to assess and enhance current methods for scene text detection, recognition, and tracking in videos. The RoadText-1K dataset contains 1000 dash cam videos with annotations for text bounding boxes and transcriptions in every frame. The competition features an end-to-end task, requiring systems to accurately detect, track, and recognize text in dash cam videos. The paper presents a comprehensive review of the submitted methods along with a detailed analysis of the results obtained by the methods. The analysis provides valuable insights into the current capabilities and limitations of video text detection, tracking, and recognition systems for dashcam videos.
|
Wenwen Yu, Chengquan Zhang, Haoyu Cao, Wei Hua, Bohan Li, Huang Chen, et al. (2023). ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images. In 17th International Conference on Document Analysis and Recognition (Vol. 14188, 536–552). LNCS.
Abstract: Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on the submodules of the structured text extraction scheme. In order to eliminate these problems, we organized the ICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD). We set up two tracks for SVRD including Track 1: HUST-CELL and Track 2: Baidu-FEST, where HUST-CELL aims to evaluate the end-to-end performance of Complex Entity Linking and Labeling, and Baidu-FEST focuses on evaluating the performance and generalization of Zero-shot/Few-shot Structured Text extraction from an end-to-end perspective. Compared to the current document benchmarks, our two tracks of competition benchmark enriches the scenarios greatly and contains more than 50 types of visually-rich document images (mainly from the actual enterprise applications). The competition opened on 30th December, 2022 and closed on 24th March, 2023. There are 35 participants and 91 valid submissions received for Track 1, and 15 participants and 26 valid submissions received for Track 2. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, and submission summaries. According to the performance of the submissions, we believe there is still a large gap on the expected information extraction performance for complex and zero-shot scenarios. It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
|
Weijia Wu, Yuzhong Zhao, Zhuang Li, Jiahong Li, Mike Zheng Shou, Umapada Pal, et al. (2023). ICDAR 2023 Competition on Video Text Reading for Dense and Small Text. In 17th International Conference on Document Analysis and Recognition (Vol. 14188, 405–419). LNCS.
Abstract: Recently, video text detection, tracking and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenario, while ignore extreme video texts challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a video text reading benchmark, named DSText, which focuses on dense and small text reading challenge in the video with various scenarios. Compared with the previous datasets, the proposed dataset mainly include three new challenges: 1) Dense video texts, new challenge for video text spotter. 2) High-proportioned small texts. 3) Various new scenarios, e.g., ‘Game’, ‘Sports’, etc. The proposed DSText includes 100 video clips from 12 open scenarios, supporting two tasks (i.e., video text tracking (Task 1) and end-to-end video text spotting (Task2)). During the competition period (opened on 15th February, 2023 and closed on 20th March, 2023), a total of 24 teams participated in the three proposed tasks with around 30 valid submissions, respectively. In this article, we describe detailed statistical information of the dataset, tasks, evaluation protocols and the results summaries of the ICDAR 2023 on DSText competition. Moreover, we hope the benchmark will promise the video text research in the community.
Keywords: Video Text Spotting; Small Text; Text Tracking; Dense Text
|
Dawid Rymarczyk, Joost van de Weijer, Bartosz Zielinski, & Bartlomiej Twardowski. (2023). ICICLE: Interpretable Class Incremental Continual Learning. Dawid Rymarczyk. In 20th IEEE International Conference on Computer Vision (pp. 1887–1898).
Abstract: Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new challenges for interpretability, as the rationale behind model predictions may change over time, leading to interpretability concept drift. We address this problem by proposing Interpretable Class-InCremental LEarning (ICICLE), an exemplar-free approach that adopts a prototypical part-based approach. It consists of three crucial novelties: interpretability regularization that distills previously learned concepts while preserving user-friendly positive reasoning; proximity-based prototype initialization strategy dedicated to the fine-grained setting; and task-recency bias compensation devoted to prototypical parts. Our experimental results demonstrate that ICICLE reduces the interpretability concept drift and outperforms the existing exemplar-free methods of common class-incremental learning when applied to concept-based models.
|
Albin Soutif, Antonio Carta, & Joost Van de Weijer. (2023). Improving Online Continual Learning Performance and Stability with Temporal Ensembles. In 2nd Conference on Lifelong Learning Agents.
Abstract: Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online setup, which limits the availability of data, (2) due to catastrophic forgetting because of the non-stationary nature of the data. Furthermore, several recent works (Caccia et al., 2022; Lange et al., 2023) arXiv:2205.13452 showed that replay methods used in continual learning suffer from the stability gap, encountered when evaluating the model continually (rather than only on task boundaries). In this article, we study the effect of model ensembling as a way to improve performance and stability in online continual learning. We notice that naively ensembling models coming from a variety of training tasks increases the performance in online continual learning considerably. Starting from this observation, and drawing inspirations from semi-supervised learning ensembling methods, we use a lightweight temporal ensemble that computes the exponential moving average of the weights (EMA) at test time, and show that it can drastically increase the performance and stability when used in combination with several methods from the literature.
|
